Compare commits
22 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Claude
|
4da23c3902 | ||
|
Claude
|
6ad376adce | ||
|
Claude
|
6d1aaf9302 | ||
|
Claude
|
5c40d35d41 | ||
|
Claude
|
a53e3eeae3 | ||
|
Claude
|
03f5b86228 | ||
|
Claude Routine
|
b030439eab | ||
|
Claude Routine
|
4ed6f00757 | ||
|
Claude Routine
|
998b600854 | ||
 Shayan Rais
|
8495a74828 | ||
|
Claude
|
9329519848 | ||
|
Claude
|
b4de05fe3e | ||
|
Claude
|
a37d9733ac | ||
|
Claude
|
f0b29189ad | ||
|
Claude
|
ecc8d592fd | ||
|
Claude
|
5b3273f90d | ||
|
Claude
|
95a7233500 | ||
|
Claude
|
40553e6e43 | ||
|
Claude
|
982882f8bf | ||
|
Claude
|
b4d5ffc5b9 | ||
|
Claude Routine
|
a338ff68f3 | ||
|
Claude Routine
|
950f88e7d4 |
@@ -1,8 +1,7 @@
|
||||
# claude-code-best-practice
|
||||
from vibe coding to agentic engineering - practice makes claude perfect
|
||||
|
||||
-white?style=flat&labelColor=555) <a href="https://github.com/shanraisshan/claude-code-best-practice/stargazers"><img src="https://img.shields.io/github/stars/shanraisshan/claude-code-best-practice?style=flat&label=%E2%98%85&labelColor=555&color=white" alt="GitHub Stars"></a><br>
|
||||
|
||||
-white?style=flat&labelColor=555) <a href="https://github.com/shanraisshan/claude-code-best-practice/stargazers"><img src="https://img.shields.io/github/stars/shanraisshan/claude-code-best-practice?style=flat&label=%E2%98%85&labelColor=555&color=white" alt="GitHub Stars"></a><br>
|
||||
|
||||
[](best-practice/) [](implementation/) [](orchestration-workflow/orchestration-workflow.md) [](https://code.claude.com/docs) [](#-tips-and-tricks) [](#-subscribe) <br>
|
||||
<img src="!/tags/a.svg" height="14"> = Agents · <img src="!/tags/c.svg" height="14"> = Commands · <img src="!/tags/s.svg" height="14"> = Skills
|
||||
@@ -61,7 +60,7 @@ from vibe coding to agentic engineering - practice makes claude perfect
|
||||
| [**GitHub Actions**](https://code.claude.com/docs/en/github-actions) | `.github/workflows/` | [GitLab CI/CD](https://code.claude.com/docs/en/gitlab-ci-cd) |
|
||||
| [**Remote Control**](https://code.claude.com/docs/en/remote-control) | `/remote-control`, `/rc` | [](https://x.com/noahzweben/status/2032533699116355819) [Headless Mode](https://code.claude.com/docs/en/headless) |
|
||||
| [**Deep Links**](https://code.claude.com/docs/en/deep-links) | `claude-cli://open?repo=…&q=…` | |
|
||||
| [**Dynamic Workflows**](https://code.claude.com/docs/en/workflows)  | `/workflows`, `workflow` keyword, `/effort ultracode`, `.claude/workflows/` | [Deep Research](https://code.claude.com/docs/en/workflows#run-a-bundled-workflow) |
|
||||
| [**Dynamic Workflows**](https://code.claude.com/docs/en/workflows)  | `/workflows`, `ultracode` keyword, `/effort ultracode`, `.claude/workflows/` | [Deep Research](https://code.claude.com/docs/en/workflows#run-a-bundled-workflow) |
|
||||
| [**Agent Teams**](https://code.claude.com/docs/en/agent-teams)  | built-in (env var) | [](https://x.com/bcherny/status/2019472394696683904) [](implementation/claude-agent-teams-implementation.md) |
|
||||
| [**Agent View**](https://code.claude.com/docs/en/agent-view)  | `claude agents`, `--bg`, `/bg` | |
|
||||
| [**Scheduled Tasks**](https://code.claude.com/docs/en/scheduled-tasks) | `/loop`, `/schedule`, cron tools | [](https://x.com/bcherny/status/2030193932404150413) [](implementation/claude-scheduled-tasks-implementation.md) [Desktop scheduled tasks](https://code.claude.com/docs/en/desktop-scheduled-tasks) · [Announcement](https://x.com/noahzweben/status/2036129220959805859) |
|
||||
@@ -108,18 +107,18 @@ All major workflows converge on the same architectural pattern: **Research → P
|
||||
|
||||
| Name | ★ | Workflow | <img src="!/tags/a.svg" height="14"> | <img src="!/tags/c.svg" height="14"> | <img src="!/tags/s.svg" height="14"> |
|
||||
|------|---|----------|---|---|---|
|
||||
| [Superpowers](https://github.com/obra/superpowers) | 214k | <img src="https://img.shields.io/badge/brainstorming-ddf4ff" alt="brainstorming" align="middle"> → <img src="https://img.shields.io/badge/using--git--worktrees-ddf4ff" alt="using-git-worktrees" align="middle"> → <img src="https://img.shields.io/badge/writing--plans-ddf4ff" alt="writing-plans" align="middle"> → <img src="https://img.shields.io/badge/subagent--driven--development-fff3b0" alt="subagent-driven-development" align="middle"> → <img src="https://img.shields.io/badge/test--driven--development-fff3b0" alt="test-driven-development" align="middle"> → <img src="https://img.shields.io/badge/requesting--code--review-fff3b0" alt="requesting-code-review" align="middle"> → <img src="https://img.shields.io/badge/verification--before--completion-fff3b0" alt="verification-before-completion" align="middle"> → <img src="https://img.shields.io/badge/finishing--a--development--branch-ddf4ff" alt="finishing-a-development-branch" align="middle"> | 0 | 0 | 14 |
|
||||
| [Everything Claude Code](https://github.com/affaan-m/everything-claude-code) | 200k | <img src="https://img.shields.io/badge/%2Fecc:plan-ddf4ff" alt="/ecc:plan" align="middle"> → <img src="https://img.shields.io/badge/%2Ftdd-ddf4ff" alt="/tdd" align="middle"> → <img src="https://img.shields.io/badge/%2Fcode--review-ddf4ff" alt="/code-review" align="middle"> → <img src="https://img.shields.io/badge/%2Fsecurity--scan-ddf4ff" alt="/security-scan" align="middle"> → <img src="https://img.shields.io/badge/%2Fe2e-ddf4ff" alt="/e2e" align="middle"> → <img src="https://img.shields.io/badge/merge-ddf4ff" alt="merge" align="middle"> | 63 | 121 | 300+ |
|
||||
| [Matt Pocock Skills](https://github.com/mattpocock/skills) | 113k | <img src="https://img.shields.io/badge/%2Fgrill--with--docs-ddf4ff" alt="/grill-with-docs" align="middle"> → <img src="https://img.shields.io/badge/%2Fto--prd-ddf4ff" alt="/to-prd" align="middle"> → <img src="https://img.shields.io/badge/%2Fto--issues-ddf4ff" alt="/to-issues" align="middle"> → <img src="https://img.shields.io/badge/%2Ftriage-ddf4ff" alt="/triage" align="middle"> → <img src="https://img.shields.io/badge/%2Ftdd-fff3b0" alt="/tdd" align="middle"> → <img src="https://img.shields.io/badge/%2Fdiagnose-fff3b0" alt="/diagnose" align="middle"> → <img src="https://img.shields.io/badge/%2Fimprove--codebase--architecture-ddf4ff" alt="/improve-codebase-architecture" align="middle"> → <img src="https://img.shields.io/badge/%2Fzoom--out-ddf4ff" alt="/zoom-out" align="middle"> | 0 | 0 | 29 |
|
||||
| [Spec Kit](https://github.com/github/spec-kit) | 107k | <img src="https://img.shields.io/badge/%2Fspeckit.constitution-ddf4ff" alt="/speckit.constitution" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.specify-ddf4ff" alt="/speckit.specify" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.clarify-ddf4ff" alt="/speckit.clarify" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.plan-ddf4ff" alt="/speckit.plan" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.tasks-ddf4ff" alt="/speckit.tasks" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.analyze-ddf4ff" alt="/speckit.analyze" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.implement-ddf4ff" alt="/speckit.implement" align="middle"> | 0 | 9 | 0 |
|
||||
| [gstack](https://github.com/garrytan/gstack) | 105k | <img src="https://img.shields.io/badge/%2Foffice--hours-ddf4ff" alt="/office-hours" align="middle"> → <img src="https://img.shields.io/badge/%2Fplan--ceo--review-ddf4ff" alt="/plan-ceo-review" align="middle"> → <img src="https://img.shields.io/badge/%2Fplan--eng--review-ddf4ff" alt="/plan-eng-review" align="middle"> → <img src="https://img.shields.io/badge/%2Fplan--design--review-ddf4ff" alt="/plan-design-review" align="middle"> → <img src="https://img.shields.io/badge/%2Fdesign--shotgun-ddf4ff" alt="/design-shotgun" align="middle"> → <img src="https://img.shields.io/badge/%2Fdesign--html-ddf4ff" alt="/design-html" align="middle"> → <img src="https://img.shields.io/badge/%2Freview-ddf4ff" alt="/review" align="middle"> → <img src="https://img.shields.io/badge/%2Fcodex-ddf4ff" alt="/codex" align="middle"> → <img src="https://img.shields.io/badge/%2Fqa-ddf4ff" alt="/qa" align="middle"> → <img src="https://img.shields.io/badge/%2Fship-ddf4ff" alt="/ship" align="middle"> → <img src="https://img.shields.io/badge/%2Fland--and--deploy-ddf4ff" alt="/land-and-deploy" align="middle"> → <img src="https://img.shields.io/badge/%2Fretro-ddf4ff" alt="/retro" align="middle"> | 0 | 0 | 47 |
|
||||
| [Get Shit Done](https://github.com/gsd-build/get-shit-done) | 64k | <img src="https://img.shields.io/badge/%2Fgsd--new--project-ddf4ff" alt="/gsd-new-project" align="middle"> → <img src="https://img.shields.io/badge/%2Fgsd--discuss--phase-ddf4ff" alt="/gsd-discuss-phase" align="middle"> → <img src="https://img.shields.io/badge/%2Fgsd--plan--phase-ddf4ff" alt="/gsd-plan-phase" align="middle"> → <img src="https://img.shields.io/badge/%2Fgsd--execute--phase-ddf4ff" alt="/gsd-execute-phase" align="middle"> → <img src="https://img.shields.io/badge/%2Fgsd--verify--work-fff3b0" alt="/gsd-verify-work" align="middle"> → <img src="https://img.shields.io/badge/%2Fgsd--ship-ddf4ff" alt="/gsd-ship" align="middle"> → <img src="https://img.shields.io/badge/%2Fgsd--complete--milestone-ddf4ff" alt="/gsd-complete-milestone" align="middle"> | 33 | 96 | 0 |
|
||||
| [OpenSpec](https://github.com/Fission-AI/OpenSpec) | 52k | <img src="https://img.shields.io/badge/%2Fopsx:propose-ddf4ff" alt="/opsx:propose" align="middle"> → <img src="https://img.shields.io/badge/%2Fopsx:apply-ddf4ff" alt="/opsx:apply" align="middle"> → <img src="https://img.shields.io/badge/%2Fopsx:archive-ddf4ff" alt="/opsx:archive" align="middle"> | 0 | 9 | 0 |
|
||||
| [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) | 48k | <img src="https://img.shields.io/badge/bmad--product--brief-ddf4ff" alt="bmad-product-brief" align="middle"> → <img src="https://img.shields.io/badge/bmad--create--prd-ddf4ff" alt="bmad-create-prd" align="middle"> → <img src="https://img.shields.io/badge/bmad--create--architecture-ddf4ff" alt="bmad-create-architecture" align="middle"> → <img src="https://img.shields.io/badge/bmad--create--epics--and--stories-ddf4ff" alt="bmad-create-epics-and-stories" align="middle"> → <img src="https://img.shields.io/badge/bmad--sprint--planning-ddf4ff" alt="bmad-sprint-planning" align="middle"> → <img src="https://img.shields.io/badge/bmad--create--story-fff3b0" alt="bmad-create-story" align="middle"> → <img src="https://img.shields.io/badge/bmad--dev--story-fff3b0" alt="bmad-dev-story" align="middle"> → <img src="https://img.shields.io/badge/bmad--code--review-fff3b0" alt="bmad-code-review" align="middle"> → <img src="https://img.shields.io/badge/bmad--retrospective-ddf4ff" alt="bmad-retrospective" align="middle"> | 6 | 0 | 40 |
|
||||
| [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) | 35k | <img src="https://img.shields.io/badge/%2Fdeep--interview-ddf4ff" alt="/deep-interview" align="middle"> → <img src="https://img.shields.io/badge/%2Fteam-ddf4ff" alt="/team" align="middle"> → <img src="https://img.shields.io/badge/team--plan-fff3b0" alt="team-plan" align="middle"> → <img src="https://img.shields.io/badge/team--prd-fff3b0" alt="team-prd" align="middle"> → <img src="https://img.shields.io/badge/team--exec-fff3b0" alt="team-exec" align="middle"> → <img src="https://img.shields.io/badge/team--verify-fff3b0" alt="team-verify" align="middle"> → <img src="https://img.shields.io/badge/team--fix-fff3b0" alt="team-fix" align="middle"> → <img src="https://img.shields.io/badge/%2Fralph-ddf4ff" alt="/ralph" align="middle"> → <img src="https://img.shields.io/badge/merge-ddf4ff" alt="merge" align="middle"> | 19 | 0 | 47 |
|
||||
| [Superpowers](https://github.com/obra/superpowers) | 215k | <img src="https://img.shields.io/badge/brainstorming-ddf4ff" alt="brainstorming" align="middle"> → <img src="https://img.shields.io/badge/using--git--worktrees-ddf4ff" alt="using-git-worktrees" align="middle"> → <img src="https://img.shields.io/badge/writing--plans-ddf4ff" alt="writing-plans" align="middle"> → <img src="https://img.shields.io/badge/subagent--driven--development-ddf4ff" alt="subagent-driven-development" align="middle"> → <img src="https://img.shields.io/badge/test--driven--development-fff3b0" alt="test-driven-development" align="middle"> → <img src="https://img.shields.io/badge/requesting--code--review-ddf4ff" alt="requesting-code-review" align="middle"> → <img src="https://img.shields.io/badge/receiving--code--review-fff3b0" alt="receiving-code-review" align="middle"> → <img src="https://img.shields.io/badge/verification--before--completion-ddf4ff" alt="verification-before-completion" align="middle"> → <img src="https://img.shields.io/badge/finishing--a--development--branch-ddf4ff" alt="finishing-a-development-branch" align="middle"> | 0 | 0 | 14 |
|
||||
| [Everything Claude Code](https://github.com/affaan-m/everything-claude-code) | 202k | <img src="https://img.shields.io/badge/%2Fecc:plan-ddf4ff" alt="/ecc:plan" align="middle"> → <img src="https://img.shields.io/badge/%2Ftdd-ddf4ff" alt="/tdd" align="middle"> → <img src="https://img.shields.io/badge/%2Fcode--review-ddf4ff" alt="/code-review" align="middle"> → <img src="https://img.shields.io/badge/%2Fsecurity--scan-ddf4ff" alt="/security-scan" align="middle"> → <img src="https://img.shields.io/badge/%2Fe2e-ddf4ff" alt="/e2e" align="middle"> → <img src="https://img.shields.io/badge/merge-ddf4ff" alt="merge" align="middle"> | 63 | 121 | 300+ |
|
||||
| [Matt Pocock Skills](https://github.com/mattpocock/skills) | 114k | <img src="https://img.shields.io/badge/%2Fgrill--me-ddf4ff" alt="/grill-me" align="middle"> → <img src="https://img.shields.io/badge/%2Fgrill--with--docs-ddf4ff" alt="/grill-with-docs" align="middle"> → <img src="https://img.shields.io/badge/%2Fto--prd-ddf4ff" alt="/to-prd" align="middle"> → <img src="https://img.shields.io/badge/%2Fto--issues-ddf4ff" alt="/to-issues" align="middle"> → <img src="https://img.shields.io/badge/%2Ftdd-ddf4ff" alt="/tdd" align="middle"> → <img src="https://img.shields.io/badge/%2Fdiagnose-fff3b0" alt="/diagnose" align="middle"> → <img src="https://img.shields.io/badge/%2Fimprove--codebase--architecture-ddf4ff" alt="/improve-codebase-architecture" align="middle"> | 0 | 0 | 29 |
|
||||
| [Spec Kit](https://github.com/github/spec-kit) | 108k | <img src="https://img.shields.io/badge/%2Fspeckit.constitution-ddf4ff" alt="/speckit.constitution" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.specify-ddf4ff" alt="/speckit.specify" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.clarify-ddf4ff" alt="/speckit.clarify" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.plan-ddf4ff" alt="/speckit.plan" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.tasks-ddf4ff" alt="/speckit.tasks" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.taskstoissues-ddf4ff" alt="/speckit.taskstoissues" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.implement-ddf4ff" alt="/speckit.implement" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.analyze-ddf4ff" alt="/speckit.analyze" align="middle"> → <img src="https://img.shields.io/badge/%2Fspeckit.checklist-ddf4ff" alt="/speckit.checklist" align="middle"> | 0 | 9 | 0 |
|
||||
| [gstack](https://github.com/garrytan/gstack) | 106k | <img src="https://img.shields.io/badge/%2Foffice--hours-ddf4ff" alt="/office-hours" align="middle"> → <img src="https://img.shields.io/badge/%2Fplan--ceo--review-ddf4ff" alt="/plan-ceo-review" align="middle"> → <img src="https://img.shields.io/badge/%2Fplan--eng--review-fff3b0" alt="/plan-eng-review" align="middle"> → <img src="https://img.shields.io/badge/%2Fplan--design--review-fff3b0" alt="/plan-design-review" align="middle"> → <img src="https://img.shields.io/badge/%2Fplan--devex--review-fff3b0" alt="/plan-devex-review" align="middle"> → <img src="https://img.shields.io/badge/%2Fspec-ddf4ff" alt="/spec" align="middle"> → <img src="https://img.shields.io/badge/%2Fdesign--consultation-fff3b0" alt="/design-consultation" align="middle"> → <img src="https://img.shields.io/badge/%2Freview-ddf4ff" alt="/review" align="middle"> → <img src="https://img.shields.io/badge/%2Fqa-ddf4ff" alt="/qa" align="middle"> → <img src="https://img.shields.io/badge/%2Fship-ddf4ff" alt="/ship" align="middle"> → <img src="https://img.shields.io/badge/%2Fland--and--deploy-ddf4ff" alt="/land-and-deploy" align="middle"> → <img src="https://img.shields.io/badge/%2Fcanary-ddf4ff" alt="/canary" align="middle"> → <img src="https://img.shields.io/badge/%2Fretro-ddf4ff" alt="/retro" align="middle"> | 0 | 0 | 61 |
|
||||
| [Get Shit Done](https://github.com/gsd-build/get-shit-done) | 64k | <img src="https://img.shields.io/badge/%2Fgsd--new--project-ddf4ff" alt="/gsd-new-project" align="middle"> → <img src="https://img.shields.io/badge/%2Fgsd--spec--phase-ddf4ff" alt="/gsd-spec-phase" align="middle"> → <img src="https://img.shields.io/badge/%2Fgsd--plan--phase-ddf4ff" alt="/gsd-plan-phase" align="middle"> → <img src="https://img.shields.io/badge/%2Fgsd--execute--phase-ddf4ff" alt="/gsd-execute-phase" align="middle"> → <img src="https://img.shields.io/badge/%2Fgsd--code--review-fff3b0" alt="/gsd-code-review" align="middle"> → <img src="https://img.shields.io/badge/%2Fgsd--validate--phase-fff3b0" alt="/gsd-validate-phase" align="middle"> → <img src="https://img.shields.io/badge/%2Fgsd--ship-ddf4ff" alt="/gsd-ship" align="middle"> → <img src="https://img.shields.io/badge/%2Fgsd--extract--learnings-ddf4ff" alt="/gsd-extract-learnings" align="middle"> | 33 | 67 | 0 |
|
||||
| [OpenSpec](https://github.com/Fission-AI/OpenSpec) | 52k | <img src="https://img.shields.io/badge/%2Fopsx:propose-ddf4ff" alt="/opsx:propose" align="middle"> → <img src="https://img.shields.io/badge/%2Fopsx:apply-fff3b0" alt="/opsx:apply" align="middle"> → <img src="https://img.shields.io/badge/%2Fopsx:verify-fff3b0" alt="/opsx:verify" align="middle"> → <img src="https://img.shields.io/badge/%2Fopsx:archive-ddf4ff" alt="/opsx:archive" align="middle"> → <img src="https://img.shields.io/badge/%2Fopsx:bulk--archive-ddf4ff" alt="/opsx:bulk-archive" align="middle"> | 0 | 9 | 0 |
|
||||
| [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) | 49k | <img src="https://img.shields.io/badge/bmad--product--brief-ddf4ff" alt="bmad-product-brief" align="middle"> → <img src="https://img.shields.io/badge/bmad--prfaq-fff3b0" alt="bmad-prfaq" align="middle"> → <img src="https://img.shields.io/badge/bmad--create--prd-ddf4ff" alt="bmad-create-prd" align="middle"> → <img src="https://img.shields.io/badge/bmad--validate--prd-fff3b0" alt="bmad-validate-prd" align="middle"> → <img src="https://img.shields.io/badge/bmad--create--architecture-ddf4ff" alt="bmad-create-architecture" align="middle"> → <img src="https://img.shields.io/badge/bmad--check--implementation--readiness-ddf4ff" alt="bmad-check-implementation-readiness" align="middle"> → <img src="https://img.shields.io/badge/bmad--create--epics--and--stories-ddf4ff" alt="bmad-create-epics-and-stories" align="middle"> → <img src="https://img.shields.io/badge/bmad--dev--story-fff3b0" alt="bmad-dev-story" align="middle"> → <img src="https://img.shields.io/badge/bmad--code--review-fff3b0" alt="bmad-code-review" align="middle"> → <img src="https://img.shields.io/badge/bmad--qa--generate--e2e--tests-ddf4ff" alt="bmad-qa-generate-e2e-tests" align="middle"> → <img src="https://img.shields.io/badge/bmad--retrospective-ddf4ff" alt="bmad-retrospective" align="middle"> | 6 | 0 | 42 |
|
||||
| [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) | 36k | <img src="https://img.shields.io/badge/team--plan-ddf4ff" alt="team-plan" align="middle"> → <img src="https://img.shields.io/badge/team--prd-ddf4ff" alt="team-prd" align="middle"> → <img src="https://img.shields.io/badge/team--exec-ddf4ff" alt="team-exec" align="middle"> → <img src="https://img.shields.io/badge/team--verify-ddf4ff" alt="team-verify" align="middle"> → <img src="https://img.shields.io/badge/team--fix-fff3b0" alt="team-fix" align="middle"> → <img src="https://img.shields.io/badge/team--verify-fff3b0" alt="team-verify" align="middle"> | 19 | 0 | 39 |
|
||||
| [agent-skills](https://github.com/addyosmani/agent-skills) | 27k | <img src="https://img.shields.io/badge/%2Fspec-ddf4ff" alt="/spec" align="middle"> → <img src="https://img.shields.io/badge/%2Fplan-ddf4ff" alt="/plan" align="middle"> → <img src="https://img.shields.io/badge/%2Fbuild-ddf4ff" alt="/build" align="middle"> → <img src="https://img.shields.io/badge/%2Ftest-ddf4ff" alt="/test" align="middle"> → <img src="https://img.shields.io/badge/%2Freview-ddf4ff" alt="/review" align="middle"> → <img src="https://img.shields.io/badge/%2Fship-ddf4ff" alt="/ship" align="middle"> | 3 | 7 | 21 |
|
||||
| [Compound Engineering](https://github.com/EveryInc/compound-engineering-plugin) | 19k | <img src="https://img.shields.io/badge/%2Fce--ideate-ddf4ff" alt="/ce-ideate" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--brainstorm-ddf4ff" alt="/ce-brainstorm" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--plan-ddf4ff" alt="/ce-plan" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--work-ddf4ff" alt="/ce-work" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--code--review-ddf4ff" alt="/ce-code-review" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--debug-fff3b0" alt="/ce-debug" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--optimize-fff3b0" alt="/ce-optimize" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--compound-ddf4ff" alt="/ce-compound" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--compound--refresh-fff3b0" alt="/ce-compound-refresh" align="middle"> | 43 | 4 | 42 |
|
||||
| [HumanLayer](https://github.com/humanlayer/humanlayer) | 11k | <img src="https://img.shields.io/badge/%2Fcreate__plan-ddf4ff" alt="/create_plan" align="middle"> → <img src="https://img.shields.io/badge/%2Fvalidate__plan-ddf4ff" alt="/validate_plan" align="middle"> → <img src="https://img.shields.io/badge/%2Fimplement__plan-ddf4ff" alt="/implement_plan" align="middle"> → <img src="https://img.shields.io/badge/%2Fiterate__plan-fff3b0" alt="/iterate_plan" align="middle"> → <img src="https://img.shields.io/badge/%2Flocal__review-ddf4ff" alt="/local_review" align="middle"> → <img src="https://img.shields.io/badge/%2Fcommit-ddf4ff" alt="/commit" align="middle"> | 6 | 27 | 0 |
|
||||
| [Compound Engineering](https://github.com/EveryInc/compound-engineering-plugin) | 19k | <img src="https://img.shields.io/badge/%2Fce--strategy-ddf4ff" alt="/ce-strategy" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--brainstorm-ddf4ff" alt="/ce-brainstorm" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--ideate-fff3b0" alt="/ce-ideate" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--plan-ddf4ff" alt="/ce-plan" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--work-ddf4ff" alt="/ce-work" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--debug-fff3b0" alt="/ce-debug" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--code--review-ddf4ff" alt="/ce-code-review" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--compound-ddf4ff" alt="/ce-compound" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--update-fff3b0" alt="/ce-update" align="middle"> → <img src="https://img.shields.io/badge/%2Fce--release--notes-ddf4ff" alt="/ce-release-notes" align="middle"> | 47 | 4 | 39 |
|
||||
| [HumanLayer](https://github.com/humanlayer/humanlayer) | 11k | <img src="https://img.shields.io/badge/%2Fresearch__codebase-ddf4ff" alt="/research_codebase" align="middle"> → <img src="https://img.shields.io/badge/%2Fcreate__plan-ddf4ff" alt="/create_plan" align="middle"> → <img src="https://img.shields.io/badge/%2Fvalidate__plan-fff3b0" alt="/validate_plan" align="middle"> → <img src="https://img.shields.io/badge/%2Fiterate__plan-fff3b0" alt="/iterate_plan" align="middle"> → <img src="https://img.shields.io/badge/%2Fimplement__plan-ddf4ff" alt="/implement_plan" align="middle"> → <img src="https://img.shields.io/badge/%2Flocal__review-ddf4ff" alt="/local_review" align="middle"> → <img src="https://img.shields.io/badge/%2Fcreate__handoff-ddf4ff" alt="/create_handoff" align="middle"> → <img src="https://img.shields.io/badge/%2Fcommit-ddf4ff" alt="/commit" align="middle"> → <img src="https://img.shields.io/badge/%2Fdescribe__pr-ddf4ff" alt="/describe_pr" align="middle"> | 6 | 27 | 0 |
|
||||
|
||||
> *Note: yellow tags are sub-loops — steps that repeat inside a parent step (e.g. per task, per story, or until a verify condition passes).*
|
||||
|
||||
@@ -182,7 +181,7 @@ Repos primarily known as curated libraries of subagent definitions (`.claude/age
|
||||
|
||||
| Name | ★ | <img src="!/tags/a.svg" height="14"> |
|
||||
|------|---|---|
|
||||
| [msitarzewski/agency-agents](https://github.com/msitarzewski/agency-agents) | 106k | 144 |
|
||||
| [msitarzewski/agency-agents](https://github.com/msitarzewski/agency-agents) | 107k | 144 |
|
||||
| [VoltAgent/awesome-claude-code-subagents](https://github.com/VoltAgent/awesome-claude-code-subagents) | 21k | 156 |
|
||||
|
||||
<p align="center">
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Commands Best Practice
|
||||
|
||||
 <br>
|
||||
 <br>
|
||||
[](../implementation/claude-commands-implementation.md)
|
||||
|
||||
Claude Code commands — frontmatter fields and official built-in slash commands.
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
# Settings Best Practice
|
||||
|
||||
 <br>
|
||||
 <br>
|
||||
[](../.claude/settings.json)
|
||||
|
||||
A comprehensive guide to all available configuration options in Claude Code's `settings.json` files. As of v2.1.158, Claude Code exposes **80+ settings** and **180+ environment variables** (use the `"env"` field in `settings.json` to avoid wrapper scripts).
|
||||
A comprehensive guide to all available configuration options in Claude Code's `settings.json` files. As of v2.1.160, Claude Code exposes **80+ settings** and **200+ environment variables** (use the `"env"` field in `settings.json` to avoid wrapper scripts).
|
||||
|
||||
<table width="100%">
|
||||
<tr>
|
||||
@@ -96,7 +96,6 @@ Within the managed tier, precedence is: server-managed > MDM/OS-level policies >
|
||||
| `disableDeepLinkRegistration` | string | - | Set to `"disable"` to prevent Claude Code from registering the `claude-cli://` protocol handler with the operating system on startup. Deep links let external tools open a Claude Code session with a pre-filled prompt via `claude-cli://open?q=...`. The `q` parameter supports multi-line prompts using URL-encoded newlines (`%0A`). Useful in environments where protocol handler registration is restricted or managed separately |
|
||||
| `showThinkingSummaries` | boolean | `false` | Show extended thinking summaries in interactive sessions. When unset or `false` (default in interactive mode), thinking blocks are redacted by the API and shown as a collapsed stub. Redaction only changes what you see, not what the model generates — to reduce thinking spend, lower the budget or disable thinking instead. Non-interactive mode (`-p`) and SDK callers always receive summaries regardless of this setting |
|
||||
| `disableSkillShellExecution` | boolean | `false` | Disable inline shell execution for `` !`...` `` and `` ```! `` blocks in skills and custom commands from user, project, plugin, or additional-directory sources. Commands are replaced with `[shell command execution disabled by policy]` instead of being run. Bundled and managed skills are not affected (v2.1.91) |
|
||||
| `skillOverrides` | string | - | Control automatic skill invocation behavior. Values: `"off"` (skills are not invoked at all), `"user-invocable-only"` (only skills the user explicitly invokes via `/skill-name` run; auto-discovery via skill descriptions is disabled), `"name-only"` (skills are matched by exact name only; description-based auto-discovery is disabled). Use to keep a tighter rein on which skills the model loads or runs (v2.1.129) |
|
||||
| `maxSkillDescriptionChars` | number | `1536` | Per-skill character cap on the combined `description` and `when_to_use` text in the [skill listing](https://code.claude.com/docs/en/skills) Claude sees each turn. Text longer than this is truncated (v2.1.105) |
|
||||
| `skillListingBudgetFraction` | number | `0.01` | Fraction of the model's context window reserved for the [skill listing](https://code.claude.com/docs/en/skills) Claude sees each turn (`0.01` = 1%). When the listing exceeds the budget, descriptions for the least-used skills are collapsed to bare names so Claude can still invoke them but won't see why (v2.1.105) |
|
||||
| `forceRemoteSettingsRefresh` | boolean | `false` | **(Managed only)** Block CLI startup until remote managed settings are freshly fetched. If the fetch fails, the CLI exits (fail-closed). Use in enterprise environments where policy enforcement must be up-to-date before any session begins (v2.1.92) |
|
||||
@@ -107,7 +106,7 @@ Within the managed tier, precedence is: server-managed > MDM/OS-level policies >
|
||||
| `disableRemoteControl` | boolean | `false` | Disable [Remote Control](https://code.claude.com/docs/en/remote-control): blocks `claude remote-control`, the `--remote-control` flag, auto-start, and the in-session toggle. Typically placed in managed settings for per-device MDM enforcement, but works from any scope (v2.1.128) |
|
||||
| `disableAgentView` | boolean | `false` | Set to `true` to turn off [background agents and agent view](https://code.claude.com/docs/en/agent-view): `claude agents`, `--bg`, `/background`, and the on-demand supervisor. Can be set at any scope but typically placed in managed settings. Equivalent to setting the `CLAUDE_CODE_DISABLE_AGENT_VIEW` env var to `1` |
|
||||
| `disableWorkflows` | boolean | `false` | Set to `true` to disable [dynamic workflows](https://code.claude.com/docs/en/workflows) (`/workflows`) and the bundled workflow slash commands. Can be set at any scope. Equivalent to the `CLAUDE_CODE_DISABLE_WORKFLOWS` env var. Workflows were introduced in v2.1.154 |
|
||||
| `workflowKeywordTriggerEnabled` | boolean | `true` | Whether typing the word "workflow" in a prompt can trigger a dynamic workflow. Set to `false` to require explicit `/workflows` invocation. Appears in `/config` (v2.1.157) |
|
||||
| `workflowKeywordTriggerEnabled` | boolean | `true` | Whether typing the word "ultracode" in a prompt triggers a [dynamic workflow](https://code.claude.com/docs/en/workflows). Set to `false` to require explicit `/workflows` invocation. Ultracode, `/workflows`, and saved workflow commands are unaffected by this setting. Appears in `/config` as **Workflow keyword trigger** (v2.1.157; trigger keyword renamed workflow→ultracode in v2.1.160) |
|
||||
| `ultracode` | boolean | - | **(Session-only — not persisted)** When `true`, the harness authors and runs a workflow for every substantive task by default, maximizing thoroughness regardless of token cost. Appears in the official "Available settings" list but is session-scoped: set via `/effort ultracode`, `--settings`, or the SDK rather than written to `settings.json` (v2.1.154) |
|
||||
| `feedbackSurveyRate` | number | - | Probability (0–1) that the session quality survey appears when eligible. Enterprise admins can control how often the survey is shown. Example: `0.05` = 5% of eligible sessions |
|
||||
|
||||
@@ -267,7 +266,7 @@ Control what tools and operations Claude can perform.
|
||||
| Mode | Behavior |
|
||||
|------|----------|
|
||||
| `"default"` | Standard permission checking with prompts |
|
||||
| `"acceptEdits"` | Automatically accepts file edits **and common filesystem commands** (`mkdir`, `touch`, `mv`, `cp`, etc.) for paths in the working directory or `additionalDirectories` |
|
||||
| `"acceptEdits"` | Automatically accepts file edits **and common filesystem commands** (`mkdir`, `touch`, `mv`, `cp`, etc.) for paths in the working directory or `additionalDirectories`. **v2.1.160:** Always prompts before writing build-tool config files that grant code execution (`.npmrc`, `.yarnrc*`, `bunfig.toml`, `.bazelrc`, `.pre-commit-config.yaml`, `.devcontainer/`, etc.) and before writing to shell startup files (`.zshenv`, `.zlogin`, `.bash_login`) and `~/.config/git/` |
|
||||
| `"dontAsk"` | Auto-denies tools unless pre-approved via `/permissions` or `permissions.allow` rules |
|
||||
| `"bypassPermissions"` | Skip all permission checks (dangerous). Writes to protected paths (`.git`, `.claude`, `.vscode`, `.idea`, `.husky`) still prompt. As of v2.1.121, writes to `.claude/commands/`, `.claude/agents/`, `.claude/skills/`, and `.claude/worktrees/` are explicitly exempt from the protected-paths prompt because Claude routinely writes there when creating skills, subagents, and commands. **v2.1.126** further extends the exemption: writes to `.claude/`, `.git/`, `.vscode/`, and shell config files (e.g., `.bashrc`, `.zshrc`) no longer prompt under `--dangerously-skip-permissions`. Removals targeting the filesystem root or home directory (`rm -rf /`, `rm -rf ~`) still prompt as a circuit breaker against model error |
|
||||
| `"auto"` | Auto-approves tool calls with background safety checks that verify actions align with your request. Research preview. Classifier auto-approves read-only and file edits; sends everything else through a safety check. Falls back to prompting after 3 consecutive or 20 total blocks. In the default `Shift+Tab` permission-mode cycle since v2.1.111 (the `--enable-auto-mode` flag was removed in v2.1.111 — start in this mode with `--permission-mode auto`). Configure with the `autoMode` setting |
|
||||
@@ -831,15 +830,22 @@ Set environment variables for all Claude Code sessions.
|
||||
| `ANTHROPIC_BEDROCK_BASE_URL` | Override Bedrock endpoint URL |
|
||||
| `ANTHROPIC_BEDROCK_MANTLE_BASE_URL` | Override the Bedrock Mantle endpoint URL. See [Mantle endpoint](https://code.claude.com/docs/en/amazon-bedrock#use-the-mantle-endpoint) |
|
||||
| `ANTHROPIC_BEDROCK_SERVICE_TIER` | Bedrock service tier: `default`, `flex`, or `priority`. Sent as the `X-Amzn-Bedrock-Service-Tier` header on every request. See [Amazon Bedrock service tiers](https://code.claude.com/docs/en/amazon-bedrock#service-tiers) (v2.1.122) |
|
||||
| `ANTHROPIC_AWS_API_KEY` | Workspace API key for Claude Platform on AWS |
|
||||
| `ANTHROPIC_AWS_BASE_URL` | Override Claude Platform on AWS endpoint URL |
|
||||
| `ANTHROPIC_AWS_WORKSPACE_ID` | Required workspace ID for Claude Platform on AWS |
|
||||
| `CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST` | Set by host platforms that embed Claude Code and manage model provider routing on the user's behalf. When set, provider-selection / endpoint / authentication env vars in `settings.json` (e.g., `CLAUDE_CODE_USE_BEDROCK`, `ANTHROPIC_BASE_URL`, `ANTHROPIC_API_KEY`) are ignored so user settings cannot override the host's routing. The automatic telemetry opt-out for Bedrock/Vertex/Foundry is also skipped, so telemetry follows the standard `DISABLE_TELEMETRY` opt-out (v2.1.126) |
|
||||
| `ANTHROPIC_VERTEX_BASE_URL` | Override Vertex AI endpoint URL |
|
||||
| `ANTHROPIC_BETAS` | Comma-separated Anthropic beta header values |
|
||||
| `ANTHROPIC_VERTEX_PROJECT_ID` | GCP project ID for Vertex AI |
|
||||
| `GCLOUD_PROJECT` | GCP project ID for Vertex AI requests (overrides `ANTHROPIC_VERTEX_PROJECT_ID`) |
|
||||
| `GOOGLE_APPLICATION_CREDENTIALS` | Path to GCP service account credential file for Vertex AI authentication |
|
||||
| `GOOGLE_CLOUD_PROJECT` | GCP project ID for Vertex AI requests (overrides `ANTHROPIC_VERTEX_PROJECT_ID`) |
|
||||
| `ANTHROPIC_CUSTOM_MODEL_OPTION` | Model ID to add as a custom entry in the `/model` picker. Use to make a non-standard or gateway-specific model selectable without replacing built-in aliases |
|
||||
| `ANTHROPIC_CUSTOM_MODEL_OPTION_NAME` | Display name for the custom model entry in the `/model` picker. Defaults to the model ID when not set |
|
||||
| `ANTHROPIC_CUSTOM_MODEL_OPTION_DESCRIPTION` | Display description for the custom model entry in the `/model` picker. Defaults to `Custom model (<model-id>)` when not set |
|
||||
| `ANTHROPIC_CUSTOM_MODEL_OPTION_SUPPORTED_CAPABILITIES` | Override capability detection for the custom model entry. Comma-separated values (e.g., `effort,thinking`). Required when the custom model supports features the auto-detection cannot confirm. See [model configuration](https://code.claude.com/docs/en/model-config#customize-pinned-model-display-and-capabilities) |
|
||||
| `ANTHROPIC_MODEL` | Name of the model to use. Accepts aliases (`sonnet`, `opus`, `haiku`) or full model IDs. Overrides the `model` setting |
|
||||
| `INIT_PROMPT` | Custom system prompt injected at session initialization |
|
||||
| `ANTHROPIC_DEFAULT_HAIKU_MODEL` | Override the Haiku model alias with a custom model ID (e.g., for third-party deployments) |
|
||||
| `ANTHROPIC_DEFAULT_HAIKU_MODEL_NAME` | Customize the Haiku entry label in the `/model` picker when using a pinned model on Bedrock/Vertex/Foundry. Defaults to the model ID |
|
||||
| `ANTHROPIC_DEFAULT_HAIKU_MODEL_DESCRIPTION` | Customize the Haiku entry description in the `/model` picker. Defaults to `Custom model (<model-id>)` |
|
||||
@@ -864,7 +870,9 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_CODE_PACKAGE_MANAGER_AUTO_UPDATE` | Set to `1` to let Claude Code run your package manager's upgrade command in the background when a new version is available. Applies to Homebrew and WinGet installations. Other package managers continue to show the upgrade command without running it. See [Auto updates](https://code.claude.com/docs/en/setup#auto-updates) (v2.1.129) |
|
||||
| `CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY` | Set to `1` to populate the `/model` picker from your gateway's `/v1/models` endpoint when `ANTHROPIC_BASE_URL` points at an Anthropic-compatible gateway such as LiteLLM, Kong, or an internal proxy. Off by default because gateways backed by a shared API key would otherwise expose every model the key can access. Discovered models are still filtered by the `availableModels` allowlist (v2.1.129, opt-in change from prior auto-discovery) |
|
||||
| `DISABLE_TELEMETRY` | Disable telemetry (`1` to disable) |
|
||||
| `DO_NOT_TRACK` | Standard opt-out variable; set to `1` to opt out of telemetry collection. Respected by `DISABLE_TELEMETRY` |
|
||||
| `MCP_TIMEOUT` | MCP startup timeout in ms |
|
||||
| `CLAUDE_CODE_MCP_ALLOWLIST_ENV` | Spawn stdio MCP servers with a safe baseline environment only, stripping most inherited env vars to prevent credential leakage into untrusted server processes |
|
||||
| `MAX_MCP_OUTPUT_TOKENS` | Max MCP output tokens (default: 25000). Warning displayed when output exceeds 10,000 tokens |
|
||||
| `API_TIMEOUT_MS` | Timeout in ms for API requests (default: 600000) |
|
||||
| `BASH_MAX_TIMEOUT_MS` | Bash command timeout |
|
||||
@@ -874,6 +882,7 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR` | Keep cwd between bash calls (`1` to enable) |
|
||||
| `CLAUDE_CODE_DISABLE_BACKGROUND_TASKS` | Disable background tasks (`1` to disable) |
|
||||
| `CLAUDE_CODE_DISABLE_AGENT_VIEW` | Set to `1` to turn off background agents and agent view (`claude agents`, `--bg`, `/background`, on-demand supervisor). Env-var equivalent of the `disableAgentView` setting *(referenced on official settings page; not listed on the env-vars page)* |
|
||||
| `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` | Enable the experimental agent teams feature (`1` to enable). Allows spawning coordinated teams of subagents within a session |
|
||||
| `CLAUDE_CODE_DISABLE_WORKFLOWS` | Set to `1` to disable [dynamic workflows](https://code.claude.com/docs/en/workflows) (`/workflows`) and the bundled workflow slash commands. Env-var equivalent of the `disableWorkflows` setting |
|
||||
| `CLAUDE_CODE_ENABLE_AUTO_MODE` | Set to `1` to enable [auto mode](https://code.claude.com/docs/en/permissions#auto-mode) on Bedrock/Vertex/Foundry for Opus 4.7 and Opus 4.8 (v2.1.158). On the Anthropic API auto mode is available without this flag *(in v2.1.158 changelog, not yet on official env-vars page)* |
|
||||
| `ENABLE_TOOL_SEARCH` | MCP tool search threshold (e.g., `auto:5`) |
|
||||
@@ -900,6 +909,7 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_CODE_DISABLE_1M_CONTEXT` | Disable 1M token context window (`1` to disable) |
|
||||
| `CLAUDE_CODE_ACCOUNT_UUID` | Override account UUID for authentication |
|
||||
| `CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS` | Disable git-related system prompt instructions |
|
||||
| `CLAUDE_CODE_ATTRIBUTION_HEADER` | Set to `0` to omit the Claude Code attribution block from the system prompt |
|
||||
| `CLAUDE_CODE_NEW_INIT` | Set to `true` to make `/init` run an interactive setup flow. Asks which files to generate (CLAUDE.md, skills, hooks) before exploring the codebase. Without this, `/init` generates a CLAUDE.md automatically |
|
||||
| `CLAUDE_CODE_PLUGIN_SEED_DIR` | Path to one or more read-only plugin seed directories, separated by `:` on Unix or `;` on Windows. Bundle pre-populated plugins into a container image. Claude Code registers marketplaces from these directories at startup and uses pre-cached plugins without re-cloning |
|
||||
| `ENABLE_CLAUDEAI_MCP_SERVERS` | Enable Claude.ai MCP servers |
|
||||
@@ -913,7 +923,7 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_CODE_DISABLE_MCP` | Disable all MCP servers (`1` to disable) *(not in official docs — unverified)* |
|
||||
| `CLAUDE_CODE_MAX_OUTPUT_TOKENS` | Max output tokens per response. Default: 32,000 (64,000 for Opus 4.6 as of v2.1.77). Upper bound: 64,000 (128,000 for Opus 4.6 and Sonnet 4.6 as of v2.1.77) |
|
||||
| `CLAUDE_CODE_DISABLE_FAST_MODE` | Disable fast mode entirely (`1` to disable) |
|
||||
| `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE` | Set to `1` to pin [fast mode](https://code.claude.com/docs/en/fast-mode) to Claude Opus 4.6 instead of the default Opus 4.7. With it set, `/fast` runs on Opus 4.6; without it, `/fast` runs on Opus 4.7 (v2.1.142) |
|
||||
| `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE` | **REMOVED in v2.1.160** — the environment variable is now a no-op. Fast mode runs on the default model regardless of this variable. Previously pinned [fast mode](https://code.claude.com/docs/en/fast-mode) to Claude Opus 4.6 instead of the default (v2.1.142–v2.1.159) |
|
||||
| `CLAUDE_CODE_DISABLE_NONSTREAMING_FALLBACK` | Set to `1` to disable the non-streaming fallback when a streaming request fails mid-stream. Streaming errors propagate to the retry layer instead. Useful when a proxy or gateway causes the fallback to produce duplicate tool execution (v2.1.83) |
|
||||
| `CLAUDE_ENABLE_STREAM_WATCHDOG` | Abort stalled streams (`1` to enable) |
|
||||
| `CLAUDE_CODE_ENABLE_FINE_GRAINED_TOOL_STREAMING` | Enable fine-grained tool streaming (`1` to enable) |
|
||||
@@ -921,6 +931,8 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_CODE_DISABLE_FILE_CHECKPOINTING` | Disable file checkpointing for `/rewind` (`1` to disable) |
|
||||
| `CLAUDE_CODE_DISABLE_ATTACHMENTS` | Disable attachment processing (`1` to disable) |
|
||||
| `CLAUDE_CODE_DISABLE_CLAUDE_MDS` | Prevent loading CLAUDE.md files (`1` to disable) |
|
||||
| `CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD` | Load CLAUDE.md memory files from additional directories specified via `--add-dir` at startup (`1` to enable) |
|
||||
| `CLAUDE_CODE_DISABLE_POLICY_SKILLS` | Skip loading skills from the system-wide managed skills directory (`1` to disable) |
|
||||
| `CLAUDE_CODE_RESUME_INTERRUPTED_TURN` | Auto-resume if previous session ended mid-turn (`1` to enable) |
|
||||
| `CLAUDE_CODE_SKIP_PROMPT_HISTORY` | Set to `1` to skip writing prompt history and session transcripts to disk. Sessions started with this variable set do not appear in `--resume`, `--continue`, or up-arrow history. Useful for ephemeral scripted sessions |
|
||||
| `CLAUDE_CODE_USER_EMAIL` | Provide user email synchronously for authentication |
|
||||
@@ -928,6 +940,8 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_CONFIG_DIR` | Custom config directory (overrides default `~/.claude`) |
|
||||
| `CLAUDE_CODE_TMPDIR` | Override the temp directory used for internal temp files. Claude Code appends `/claude/` to this path. Default: `/tmp` on Unix/macOS, `os.tmpdir()` on Windows |
|
||||
| `ANTHROPIC_CUSTOM_HEADERS` | Custom headers for API requests (`Name: Value` format, newline-separated for multiple headers) |
|
||||
| `CLAUDE_CODE_EXTRA_BODY` | JSON object to merge into the top level of every API request body. Use to inject vendor-specific fields (e.g., routing hints for a custom gateway) |
|
||||
| `CLAUDE_CODE_PROPAGATE_TRACEPARENT` | Set to `1` to propagate the W3C `traceparent` header through requests when routing through a custom proxy, linking Claude Code traces to your upstream telemetry |
|
||||
| `ANTHROPIC_FOUNDRY_API_KEY` | API key for Microsoft Foundry authentication |
|
||||
| `ANTHROPIC_FOUNDRY_BASE_URL` | Base URL for Foundry resource |
|
||||
| `ANTHROPIC_FOUNDRY_RESOURCE` | Foundry resource name |
|
||||
@@ -953,6 +967,7 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_CODE_SYNC_PLUGIN_INSTALL` | Wait for plugin install to complete before first query (`1` to enable) |
|
||||
| `CLAUDE_CODE_SYNC_PLUGIN_INSTALL_TIMEOUT_MS` | Timeout in ms for synchronous plugin install |
|
||||
| `CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE` | Set to `1` to keep the existing marketplace cache when a `git pull` fails instead of wiping and re-cloning. Useful in offline or airgapped environments where re-cloning would fail the same way |
|
||||
| `CLAUDE_CODE_ENABLE_BACKGROUND_PLUGIN_REFRESH` | Refresh plugin state at session turn boundaries after a background install completes (`1` to enable). Without this, newly installed plugins take effect on the next session |
|
||||
| `CLAUDE_CODE_HIDE_ACCOUNT_INFO` | Hide email/org info from UI *(not in official docs — unverified)* |
|
||||
| `CLAUDE_CODE_DISABLE_CRON` | Disable scheduled/cron tasks (`1` to disable) |
|
||||
| `DISABLE_INSTALLATION_CHECKS` | Disable installation warnings |
|
||||
@@ -980,6 +995,7 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_CODE_MAX_TOOL_USE_CONCURRENCY` | Max parallel read-only tools (default: 10) |
|
||||
| `CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS` | Disable built-in subagent types in SDK mode (`1` to disable) |
|
||||
| `CLAUDE_AGENT_SDK_MCP_NO_PREFIX` | Skip `mcp__<server>__` prefix for MCP tools in SDK mode (`1` to enable) |
|
||||
| `CLAUDE_ASYNC_AGENT_STALL_TIMEOUT_MS` | Stall timeout in ms for background subagents (default: 600000 / 10 minutes). The subagent is killed if it produces no output for this duration |
|
||||
| `MCP_CONNECTION_NONBLOCKING` | Set to `true` in `-p` mode to skip the MCP connection wait entirely. Bounds `--mcp-config` server connections at 5s instead of blocking on the slowest server *(in v2.1.89 changelog, not yet on official env-vars page)* |
|
||||
| `CLAUDE_CODE_SESSIONEND_HOOKS_TIMEOUT_MS` | SessionEnd hook timeout in ms (replaces hard 1.5s limit) |
|
||||
| `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY` | Disable feedback survey prompts (`1` to disable) |
|
||||
@@ -987,18 +1003,15 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_CODE_DISABLE_TERMINAL_TITLE` | Disable terminal title updates (`1` to disable) |
|
||||
| `CLAUDE_CODE_TMUX_TRUECOLOR` | Set to `1` to allow 24-bit truecolor output inside tmux. By default, Claude Code clamps to 256 colors when `$TMUX` is set because tmux does not pass through truecolor escape sequences unless configured to. Set this after adding `set -ga terminal-overrides ',*:Tc'` to your `~/.tmux.conf` |
|
||||
| `CLAUDE_CODE_NO_FLICKER` | Set to `1` to enable flicker-free alt-screen rendering. Eliminates visual flicker during fullscreen redraws (v2.1.88) |
|
||||
| `CLAUDE_CODE_ALT_SCREEN_FULL_REPAINT` | Set to `1` to repaint the entire screen on every frame in fullscreen rendering. Use when partial redraws produce visual artifacts in unusual terminal emulators |
|
||||
| `CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN` | Set to `1` to disable fullscreen rendering and use the classic main-screen renderer. The conversation stays in your terminal's native scrollback so `Cmd+f` and tmux copy mode work as usual. Takes precedence over `CLAUDE_CODE_NO_FLICKER` and the `tui` setting. You can also switch with `/tui default` (v2.1.132) |
|
||||
| `CLAUDE_CODE_FORCE_SYNC_OUTPUT` | Set to `1` to force-enable DEC private mode 2026 synchronized output when your terminal supports it but is not auto-detected. Useful for emulators such as Emacs `eat` that implement BSU/ESU but do not reply to the capability probe. Has no effect under tmux (v2.1.129) |
|
||||
| `CLAUDE_CODE_SCROLL_SPEED` | Mouse wheel scroll multiplier for fullscreen rendering. Increase for faster scrolling, decrease for finer control |
|
||||
| `CLAUDE_CODE_DISABLE_VIRTUAL_SCROLL` | Set to `1` to disable virtual scrolling in fullscreen rendering and render every message in the transcript. Use if scrolling in fullscreen mode shows blank regions where messages should appear |
|
||||
| `CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN` | Set to `1` to opt out of the alternate-screen (fullscreen) renderer entirely and use the classic scrollback renderer. Useful when terminal multiplexers, recording tools, or accessibility tooling do not handle the alt-screen buffer cleanly (v2.1.132) |
|
||||
| `CLAUDE_CODE_DISABLE_MOUSE` | Set to `1` to disable mouse tracking in fullscreen rendering. Useful when mouse events interfere with terminal multiplexers or accessibility tools |
|
||||
| `CLAUDE_CODE_HIDE_CWD` | Set to `1` to hide the current working directory in the Claude Code startup logo banner. Useful in screen recordings, demos, or shared sessions where the CWD path leaks information about the host or project layout (v2.1.119) |
|
||||
| `CLAUDE_CODE_FORCE_SYNC_OUTPUT` | Set to `1` to force synchronous output flushing for Claude Code's writes to the terminal. Defaults to async/buffered output for performance. Use as a debugging aid when terminal output appears interleaved or out-of-order with subprocess output (v2.1.129) |
|
||||
| `CLAUDE_CODE_PACKAGE_MANAGER_AUTO_UPDATE` | Control background package-manager-based auto-update checking for Claude Code. Set to `0` to disable the background check (Claude Code will not poll the package manager for newer versions); set to `1` (default) to keep the background check enabled. Independent of `DISABLE_AUTOUPDATER`, which gates the npm-registry auto-updater (v2.1.129) |
|
||||
| `CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY` | Set to `1` to opt into fetching the available-models list from the configured LLM gateway (e.g., a corporate proxy in front of Bedrock/Vertex). When enabled, the `/model` picker is populated from the gateway's discovery endpoint instead of the built-in alias list. Use when your gateway exposes a curated subset of models the user should choose from (v2.1.129) |
|
||||
| `CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL` | Set to `1` to re-enable the in-session quality survey for OpenTelemetry-enabled enterprises. The survey is suppressed by default when `OTEL_*` env vars or `feedbackSurveyRate` are configured to avoid leaking survey traffic into enterprise telemetry pipelines. Use when admins want sampled survey data despite an OTel deployment (v2.1.136) |
|
||||
| `CLAUDE_CODE_ACCESSIBILITY` | Set to `1` to keep native terminal cursor visible for screen readers and accessibility tools |
|
||||
| `CLAUDE_CODE_NATIVE_CURSOR` | Set to `1` to show the terminal's own cursor at the input caret position instead of Claude Code's custom cursor character |
|
||||
| `CLAUDE_CODE_SYNTAX_HIGHLIGHT` | Set to `0` to disable syntax highlighting in diff output |
|
||||
| `CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL` | Skip automatic IDE extension installation (`1` to skip) |
|
||||
| `CLAUDE_CODE_AUTO_CONNECT_IDE` | Override auto IDE connection behavior |
|
||||
@@ -1012,6 +1025,11 @@ Set environment variables for all Claude Code sessions.
|
||||
| `OTEL_LOG_TOOL_DETAILS` | Set to `1` to include `tool_parameters` in OpenTelemetry events. Omitted by default for privacy *(in v2.1.85 changelog, not yet on official env-vars page)* |
|
||||
| `OTEL_LOG_RAW_API_BODIES` | Set to `1` to emit full API request and response bodies as OpenTelemetry log events. Omitted by default for privacy and payload size. Useful for debugging at a gateway or proxy *(in v2.1.111 changelog, not yet on official env-vars page)* |
|
||||
| `OTEL_LOG_USER_PROMPTS` | Set to `1` to include the `user_system_prompt` field in OpenTelemetry LLM request spans. Omitted by default for privacy — user prompts can contain sensitive data, so opt in only when you control the OTel collector and have policies in place *(in v2.1.121 changelog, not yet on official env-vars page)* |
|
||||
| `OTEL_EXPORTER_OTLP_ENDPOINT` | OpenTelemetry collector endpoint URL for metrics and logs. See [Monitoring](https://code.claude.com/docs/en/monitoring-usage) |
|
||||
| `OTEL_EXPORTER_OTLP_HEADERS` | OpenTelemetry exporter headers (`Name=Value` format, comma-separated) for authenticating with your collector |
|
||||
| `OTEL_LOG_TOOL_CONTENT` | Set to `1` to emit full tool inputs and outputs as OpenTelemetry log events. Omitted by default for privacy |
|
||||
| `OTEL_METRICS_EXPORTER` | OpenTelemetry metrics exporter type (e.g., `otlp`). See [Monitoring](https://code.claude.com/docs/en/monitoring-usage) |
|
||||
| `OTEL_TRACES_EXPORTER` | OpenTelemetry traces exporter type (e.g., `otlp`). See [Monitoring](https://code.claude.com/docs/en/monitoring-usage) |
|
||||
| `CLAUDE_CODE_FORK_SUBAGENT` | Set to `1` to enable forked subagents on external builds (non-Anthropic-signed distributions). Forked subagents run in an isolated child process instead of sharing the main agent's context *(in v2.1.117 changelog, not yet on official env-vars page)* |
|
||||
| `CLAUDE_CODE_MCP_SERVER_NAME` | Name of the MCP server, passed as an environment variable to `headersHelper` scripts so they can generate server-specific authentication headers *(in v2.1.85 changelog, not yet on official env-vars page)* |
|
||||
| `CLAUDE_CODE_MCP_SERVER_URL` | URL of the MCP server, passed as an environment variable to `headersHelper` scripts alongside `CLAUDE_CODE_MCP_SERVER_NAME` *(in v2.1.85 changelog, not yet on official env-vars page)* |
|
||||
@@ -1025,7 +1043,7 @@ Set environment variables for all Claude Code sessions.
|
||||
| `ANTHROPIC_DEFAULT_SONNET_MODEL_SUPPORTED_CAPABILITIES` | Override capability detection for a pinned Sonnet model. Comma-separated values (e.g., `effort,thinking`). Required when the pinned model supports features the auto-detection cannot confirm |
|
||||
| `MAX_THINKING_TOKENS` | Maximum extended thinking tokens per response |
|
||||
| `CLAUDE_CODE_AUTO_COMPACT_WINDOW` | Set the context capacity in tokens used for auto-compaction calculations. Defaults to the model's context window (200K standard, 1M for extended context models). Use a lower value (e.g., `500000`) on a 1M model to treat it as 500K for compaction. Capped at actual context window. `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` is applied as a percentage of this value. Setting this decouples the compaction threshold from the status line's `used_percentage` |
|
||||
| `DISABLE_AUTO_COMPACT` | Disable automatic context compaction (`1` to disable). Manual `/compact` still works |
|
||||
| `DISABLE_AUTO_COMPACT` | Disable automatic context compaction (`1` to disable). Manual `/compact` still works *(not in official docs — unverified)* |
|
||||
| `DISABLE_COMPACT` | Disable all compaction — both automatic and manual (`1` to disable) |
|
||||
| `CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION` | Enable prompt suggestions |
|
||||
| `CLAUDE_CODE_PLAN_MODE_REQUIRED` | Require plan mode for sessions |
|
||||
@@ -1206,6 +1224,5 @@ Set environment variables for all Claude Code sessions.
|
||||
- [Claude Code Settings JSON Schema](https://json.schemastore.org/claude-code-settings.json)
|
||||
- [Claude Code Changelog](https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md)
|
||||
- [Claude Code GitHub Settings Examples](https://github.com/feiskyer/claude-code-settings)
|
||||
- [Shipyard - Claude Code CLI Cheatsheet](https://shipyard.build/blog/claude-code-cheat-sheet/)
|
||||
- [Claude Code Environment Variables Reference](https://code.claude.com/docs/en/env-vars)
|
||||
- [Claude Code Permissions Reference](https://code.claude.com/docs/en/permissions)
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Skills Best Practice
|
||||
|
||||
 <br>
|
||||
 <br>
|
||||
[](../implementation/claude-skills-implementation.md)
|
||||
|
||||
Claude Code skills — frontmatter fields and official bundled skills.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Sub-agents Best Practice
|
||||
|
||||
 <br>
|
||||
 <br>
|
||||
[](../implementation/claude-subagents-implementation.md)
|
||||
|
||||
Claude Code subagents — frontmatter fields and official built-in agent types.
|
||||
|
||||
@@ -10,6 +10,18 @@ Tracks updates to the AGENT COLLECTIONS table in `README.md`.
|
||||
|
||||
---
|
||||
|
||||
## [2026-06-02 08:43 AM PKT] Agent Collections Update
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|-------|-----------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
||||
| 1 | HIGH | Star | Update msitarzewski/agency-agents ★ from 106k to 107k | COMPLETE (GitHub shows 107k; NEW — milestone crossing) |
|
||||
| 2 | LOW | Count | msitarzewski/agency-agents agents 144 vs 195 (conf 0.82) | INVALID (RECURRING methodological oscillation; 16th+ consecutive INVALID ruling; no commits since April 12, 2026 — 51 days; README self-declares 144; 195 includes strategy/docs boundary judgment calls) |
|
||||
| 3 | LOW | Star | VoltAgent/awesome-claude-code-subagents ★ unchanged (21k) | INVALID (no change required; RECURRING) |
|
||||
| 4 | LOW | Count | VoltAgent/awesome-claude-code-subagents agents 156 vs ~259 (conf 0.78) | INVALID (RECURRING oscillation; +103 swing far exceeds ±5 threshold; confidence 0.78; prior 12 runs consistently 144-156; git-tree methodology differs from per-dir enumeration; 154+ README self-report still consistent with 156 table; no change) |
|
||||
| 5 | LOW | Sort | Verify sort order (107k > 21k — stars descending) | COMPLETE (order preserved; RECURRING) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-05-31 08:46 PM PKT] Agent Collections Update
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|
||||
@@ -332,3 +332,9 @@ _No tracked drift: frontmatter fields 15/15 match official docs, built-in comman
|
||||
| 1 | HIGH | New Field | Add `disallowed-tools` to frontmatter table — tools removed from Claude's available pool while the skill/command is active; clears on next message (count 15 → 16) | ✅ COMPLETE (added after `allowed-tools`, heading updated 15 → 16) |
|
||||
| 2 | HIGH | New Command | Add `/reload-skills` to Extensions tag — re-scan skill/command directories so on-disk changes apply without restart; reports counts added/removed (count 80 → 81) | ✅ COMPLETE (added as #44 after `/reload-plugins`, downstream rows renumbered) |
|
||||
| 3 | HIGH | New Command | Add `/workflows` to Session tag — open the workflow progress view to watch, pause, resume, or save running and completed workflows (count 81 → 82) | ✅ COMPLETE (added as #82 at end of Session group, count heading updated → 82) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-06-01 11:08 AM PKT] Claude Code v2.1.159
|
||||
|
||||
No priority action items — report is fully in sync with official documentation (16 frontmatter fields, 82 built-in commands).
|
||||
|
||||
@@ -647,3 +647,36 @@
|
||||
| 14 | LOW | Suspect Key Recurrence | `OTEL_LOG_TOOL_DETAILS` — v2.1.157 changelog says `OTEL_LOG_TOOL_DETAILS=1` includes tool parameters in telemetry, but still NOT on official /en/env-vars page after 20+ runs. Already in report with annotation (Rule 10B option a) | ✋ ON HOLD (kept — recurring from 2026-04-14 v2.1.107; v2.1.157 changelog re-confirms behavior) |
|
||||
| 15 | LOW | Suspect Key Recurrence | `OTEL_LOG_TOOL_CONTENT` still changelog-only. Defer per Rule 8A | ✋ ON HOLD (kept — recurring from 2026-04-16 v2.1.110) |
|
||||
| 16 | INVALID | Source Guard | Changelog v2.1.158 lists `CLAUDE_CODE_ENABLE_AUTO_MODE` but env-vars page does not yet document it — flagged as changelog-only (item #5), not as a confirmed env-vars-page var, per Rule 8A/5D | ❌ INVALID (changelog-only; annotated rather than treated as docs-confirmed) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-06-01 10:58 AM PKT] Claude Code v2.1.159
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | HIGH | Version Bump | Update report version badge from v2.1.158 → v2.1.159 and header "As of v2.1.158" → "As of v2.1.159"; update env var count from "180+" → "200+" | ✅ COMPLETE (badge, header, and count updated) — NEW |
|
||||
| 2 | HIGH | Duplicate Settings Key | Remove string-type `skillOverrides` duplicate row — NOT in official docs (object-type row at the correct position is confirmed). String-form `"off"`/`"user-invocable-only"`/`"name-only"` values are documented under the object type | ✅ COMPLETE (string-type duplicate removed; object-type row kept) — NEW |
|
||||
| 3 | HIGH | Duplicate Env Vars | Remove 5 duplicate env var rows: `CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN`, `CLAUDE_CODE_FORCE_SYNC_OUTPUT`, `CLAUDE_CODE_PACKAGE_MANAGER_AUTO_UPDATE`, `CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY`, `CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL` — each appeared twice with different (conflicting) descriptions | ✅ COMPLETE (5 duplicate rows removed; first/better-quality instance kept for each) — NEW |
|
||||
| 4 | HIGH | Broken Link | Remove `https://shipyard.build/blog/claude-code-cheat-sheet/` from Sources — returns 403 Forbidden (Rule 9B) | ✅ COMPLETE (dead link removed from Sources section) — NEW |
|
||||
| 5 | HIGH | New Env Vars | Add `ANTHROPIC_AWS_API_KEY`, `ANTHROPIC_AWS_BASE_URL`, `ANTHROPIC_AWS_WORKSPACE_ID` — Claude Platform on AWS vars confirmed on official /en/env-vars page; missing from report | ✅ COMPLETE (added after `ANTHROPIC_BEDROCK_SERVICE_TIER`) — NEW |
|
||||
| 6 | HIGH | New Env Vars | Add `GCLOUD_PROJECT`, `GOOGLE_APPLICATION_CREDENTIALS`, `GOOGLE_CLOUD_PROJECT` — GCP/Vertex AI pass-through vars confirmed on official /en/env-vars page; missing from report | ✅ COMPLETE (added after `ANTHROPIC_VERTEX_PROJECT_ID`) — NEW |
|
||||
| 7 | HIGH | New Env Vars | Add 5 OTEL vars confirmed on official /en/env-vars page: `OTEL_EXPORTER_OTLP_ENDPOINT`, `OTEL_EXPORTER_OTLP_HEADERS`, `OTEL_LOG_TOOL_CONTENT` (RESOLVED from ON HOLD — now official), `OTEL_METRICS_EXPORTER`, `OTEL_TRACES_EXPORTER` | ✅ COMPLETE (added in OTEL section after `OTEL_LOG_USER_PROMPTS`) — NEW |
|
||||
| 8 | HIGH | New Env Vars | Add 13 CLAUDE_CODE_*/other env vars confirmed on official /en/env-vars page: `CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD`, `CLAUDE_CODE_ALT_SCREEN_FULL_REPAINT`, `CLAUDE_CODE_ATTRIBUTION_HEADER`, `CLAUDE_CODE_DISABLE_POLICY_SKILLS`, `CLAUDE_CODE_ENABLE_BACKGROUND_PLUGIN_REFRESH`, `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS`, `CLAUDE_CODE_EXTRA_BODY`, `CLAUDE_CODE_MCP_ALLOWLIST_ENV`, `CLAUDE_CODE_NATIVE_CURSOR`, `CLAUDE_CODE_PROPAGATE_TRACEPARENT`, `CLAUDE_ASYNC_AGENT_STALL_TIMEOUT_MS`, `DO_NOT_TRACK`, `INIT_PROMPT` | ✅ COMPLETE (each added at appropriate section in env vars table) — NEW |
|
||||
| 9 | MED | Unverified Annotation | Mark `DISABLE_AUTO_COMPACT` as *(not in official docs — unverified)* per Rule 5D — confirmed NOT on official /en/env-vars D section (D section has: DISABLE_AUTOUPDATER, DISABLE_COMPACT, DISABLE_ERROR_REPORTING, DISABLE_FEEDBACK_COMMAND, DISABLE_TELEMETRY, DO_NOT_TRACK — no DISABLE_AUTO_COMPACT) | ✅ COMPLETE (annotation added) — NEW |
|
||||
| 10 | LOW | Resolved ON HOLD | `OTEL_LOG_TOOL_CONTENT` — ON HOLD since v2.1.110 (2026-04-16) as changelog-only. Now confirmed on official /en/env-vars O section. Added to report without annotation | ✅ COMPLETE (RESOLVED after 20+ consecutive ON HOLD runs) — RESOLVED (from 2026-04-16 v2.1.110) |
|
||||
| 11 | LOW | Suspect Key Recurrence | `OTEL_LOG_TOOL_DETAILS` — v2.1.157 changelog re-confirms `OTEL_LOG_TOOL_DETAILS=1` includes tool parameters. Still NOT on official /en/env-vars page (O section confirmed). Annotation kept | ✋ ON HOLD (kept — recurring from 2026-04-14 v2.1.107) |
|
||||
| 12 | INVALID | Rule 8A Rejection | Previous session flagged rename `CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR` → `CLAUDE_CODE_BASH_MAINTAIN_PROJECT_WORKING_DIR`. Official env-vars page confirms `CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR` (without `_CODE_`) is the correct name. No rename | ❌ INVALID (official page confirms current name; prior-session finding was wrong) — NEW |
|
||||
| 13 | INVALID | Rule 8A Rejection | Previous session flagged `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE` as REMOVED per changelog v2.1.154. Official env-vars page still lists it without any REMOVED tag. Per Rule 8A, no change | ❌ INVALID (official page still lists var; per Rule 8A, changelog alone insufficient to mark REMOVED) — NEW |
|
||||
| 14 | INVALID | Rule 8A Rejection | Previous session flagged `skipLfs` for plugin marketplace source types. Official settings page makes no mention of `skipLfs` or LFS. Not added per Rule 8A | ❌ INVALID (not found on official settings page) — NEW |
|
||||
|
||||
---
|
||||
|
||||
## [2026-06-02 10:47 AM PKT] Claude Code v2.1.160
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | HIGH | Version Bump | Update report version badge from v2.1.159 → v2.1.160 and header "As of v2.1.159" → "As of v2.1.160" | ✅ COMPLETE (badge and header updated) — NEW |
|
||||
| 2 | HIGH | Changed Behavior | Update `acceptEdits` description: v2.1.160 always prompts before writing build-tool config files that grant code execution (`.npmrc`, `.yarnrc*`, `bunfig.toml`, `.bazelrc`, `.pre-commit-config.yaml`, `.devcontainer/`) and before writing to shell startup files (`.zshenv`, `.zlogin`, `.bash_login`) and `~/.config/git/` | ✅ COMPLETE (description updated per official v2.1.160 changelog) — NEW |
|
||||
| 3 | HIGH | Removed Env Var | Mark `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE` as REMOVED in v2.1.160 — "the environment variable is now a no-op" per changelog | ✅ COMPLETE (marked REMOVED with no-op annotation; v2.1.160 attribution added) — RESOLVED (from 2026-06-01 v2.1.159, where it was INVALID per Rule 8A; v2.1.160 changelog now explicitly states "now a no-op") |
|
||||
| 4 | MED | Changed Description | Update `workflowKeywordTriggerEnabled` description: trigger keyword renamed from "workflow" to "ultracode" in v2.1.160 per official changelog | ✅ COMPLETE (description updated; "ultracode" keyword noted with v2.1.160 attribution) — NEW |
|
||||
| 5 | LOW | Suspect Key Recurrence | `OTEL_LOG_TOOL_DETAILS` — still NOT on official /en/env-vars page after 20+ consecutive runs | ✋ ON HOLD (kept — recurring from 2026-04-14 v2.1.107) |
|
||||
|
||||
@@ -223,3 +223,15 @@ No drift detected — frontmatter fields (15) and bundled skills (6) are fully s
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | HIGH | New Field | Add `disallowed-tools` to frontmatter table — tools removed from Claude's available pool while the skill is active (accepts space/comma-separated string or YAML list; clears on next message). Introduced v2.1.152, reaffirmed v2.1.157. Update count 15→16 | ✅ COMPLETE (added `disallowed-tools` row after `allowed-tools`, count updated 15→16) |
|
||||
| 2 | HIGH | New Skill | Add `simplify` to official bundled skills table — cleanup-only review (reuse, simplification, efficiency, abstraction level), four review agents in parallel; from v2.1.154 it does NOT hunt for correctness bugs (use `/code-review` for that). Update count 9→10 | ✅ COMPLETE (added as row 10, count updated 9→10) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-06-01 10:11 AM PKT] Claude Code v2.1.159
|
||||
|
||||
No drift detected — frontmatter fields (16) and bundled skills (10) are fully synchronized with official docs.
|
||||
|
||||
---
|
||||
|
||||
## [2026-06-02 10:03 AM PKT] Claude Code v2.1.160
|
||||
|
||||
No drift detected — frontmatter fields (16) and bundled skills (10) are fully synchronized with official docs.
|
||||
|
||||
@@ -249,3 +249,9 @@ No drift detected on the two tracked dimensions — all 16 frontmatter fields an
|
||||
## [2026-06-01 12:02 AM PKT] Claude Code v2.1.158
|
||||
|
||||
No drift detected on the two tracked dimensions — all 16 frontmatter fields and 5 built-in agents match.
|
||||
|
||||
---
|
||||
|
||||
## [2026-06-01 11:38 AM PKT] Claude Code v2.1.159
|
||||
|
||||
No drift detected on the two tracked dimensions — all 16 frontmatter fields and 5 built-in agents match.
|
||||
|
||||
@@ -588,3 +588,39 @@ Tracks drift between the README CONCEPTS table and official Claude Code document
|
||||
| 9 | LOW | Verification | Local badge/link target files validated via filesystem check — `best-practice/`, `implementation/`, `reports/` targets exist; `implementation/claude-tasks-implementation.md` is **absent**, so concepts-agent's "add Tasks Implemented badge" suggestion is not actionable (no file to link) | ✅ COMPLETE (no missing local files among linked targets; Tasks-badge suggestion INVALID for lack of target) |
|
||||
| 10 | LOW | Verification | Command rename scan (rule #9) — changelog top 10 shows no NEW renames affecting Location-column command names; `/code-review`,`/batch` in Bundled Skills row still accurate; `/deep-research` is a new bundled workflow command surfaced under the proposed Dynamic Workflows row | ✅ COMPLETE (no rename drift; `/reload-skills` v2.1.152 is a new command, not a rename) |
|
||||
| 11 | LOW | Verification | claude-code-guide cross-check — independent 99-concept sweep corroborated Dynamic Workflows (v2.1.154), Opus 4.8, Ultracode; re-surfaced platform surfaces (RECURRING INVALID); flagged a docs/changelog lag — changelog 2.1.158 says auto mode reached Bedrock/Vertex/Foundry while `/en/permission-modes` still reads "Anthropic API only" (not CONCEPTS-actionable; Auto Mode row makes no provider claim) | ✅ COMPLETE (agents aligned on the NEW finding; lag noted, no action) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-06-01 09:40 AM PKT] Claude Code v2.1.159
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | HIGH | Stale URL (recurring) | Commands URL `/slash-commands` not in official sitemap — redirects to `/skills`; canonical commands reference is `/en/commands` | ❌ INVALID (RECURRING from 2026-03-10; URL still resolves via redirect; user has chosen to keep as-is across 26+ runs) |
|
||||
| 2 | MED | Missing Concept (recurring) | Dedicated + claude-code-guide agents re-flagged Sessions, IDE Integration, Desktop App, Output Styles, Permissions, Sandboxing, Headless Mode, Context Window, .claude Directory as missing standalone rows | ❌ INVALID (RECURRING from 2026-03-10/03-17/04-08/05-01/05-12/05-21/05-25/06-01; user considers all platform/runtime surfaces or covered as Settings/Memory sub-links — not standalone concepts) |
|
||||
| 3 | MED | Missing Concept (recurring) | claude-code-guide flagged Prompt Library (`/en/prompt-library`) as missing concept | ❌ INVALID (reference/utility page with copy-paste prompts, not a feature/concept — consistent with user's pattern of rejecting non-feature docs pages like Glossary, Troubleshooting) |
|
||||
| 4 | LOW | Location Accuracy (NEW) | Concepts-agent questioned Dynamic Workflows Location `/effort ultracode` and `.claude/workflows/` at 0.65 confidence — neither term appears in official `/en/workflows` docs body | ✋ ON HOLD (below 0.7 confidence threshold; `/effort ultracode` may be an alias not yet documented; deferring to next run for re-evaluation) |
|
||||
| 5 | LOW | Verification | Latest version confirmed v2.1.159 via raw CHANGELOG.md — "Internal infrastructure improvements (no user-facing changes)"; nothing CONCEPTS-worthy | ✅ COMPLETE (version verified; badge bumped v2.1.158 → v2.1.159 in Phase 2.6) |
|
||||
| 6 | LOW | Verification | All 40+ external CONCEPTS URLs validated live by dedicated agent — only recurring `/slash-commands` redirect flagged; all other URLs return expected canonical pages including anchors (`#organize-rules-with-clauderules`, `#eliminate-prompts-with-auto-mode`, `#bundled-skills`, `#track-a-running-review`, `#run-a-bundled-workflow`, `#let-claude-use-your-computer`) | ✅ COMPLETE (no NEW broken URLs) |
|
||||
| 7 | LOW | Verification | All 22+ local badge/link target files validated — `best-practice/`, `implementation/`, `reports/`, `.claude/`, `.mcp.json`, `CLAUDE.md`, `orchestration-workflow/` targets all exist | ✅ COMPLETE (no missing local files) |
|
||||
| 8 | LOW | Verification | Beta Badge Currency (rule #7) — Auto Mode (`/en/permission-modes` `<Warning>`: "research preview"), Dynamic Workflows (`/en/workflows` `<Note>`: "research preview"), Fast Mode, Channels, Computer Use, Code Review, Chrome, Agent Teams, Agent View, Ultrareview, Ultraplan, No Flicker Mode, Routines, Voice Dictation — all confirmed research preview banners on their respective docs pages | ✅ COMPLETE (all README beta badges accurate; no demotions warranted) |
|
||||
| 9 | LOW | Verification | Command rename scan (rule #9) — v2.1.159 changelog contains no command/skill renames; `/code-review`, `/batch` in Bundled Skills row remain accurate | ✅ COMPLETE (no rename drift) |
|
||||
| 10 | LOW | Verification | claude-code-guide cross-check — independent 100-concept sweep corroborated all existing CONCEPTS coverage; re-surfaced platform/runtime surfaces and Prompt Library (both RECURRING INVALID per user policy); no contradictions with dedicated agent findings | ✅ COMPLETE (agents aligned; no NEW actionable findings) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-06-02 09:44 AM PKT] Claude Code v2.1.160
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | HIGH | Changed Location (NEW) | Dynamic Workflows row Location column: rename `workflow` keyword → `ultracode` keyword per v2.1.160 CHANGELOG ("Renamed dynamic-workflow trigger from 'workflow' to 'ultracode'"); docs page `/en/workflows` still references `workflow` (docs lag) but CHANGELOG is authoritative for CLI behavior | ✅ COMPLETE (Location updated; `workflow` keyword replaced with `ultracode` keyword) |
|
||||
| 2 | HIGH | Stale URL (recurring) | Commands URL `/slash-commands` not in official sitemap (145 pages) — redirects to `/skills`; canonical commands reference is `/en/commands` | ❌ INVALID (RECURRING from 2026-03-10; URL still resolves via redirect; user has chosen to keep as-is across 27+ runs) |
|
||||
| 3 | MED | Missing Concept (recurring) | Dedicated + claude-code-guide agents re-flagged Sessions, IDE Integration, Desktop App, Output Styles, Permissions, Sandboxing, Headless Mode, Context Window, .claude Directory, Prompt Library as missing standalone rows | ❌ INVALID (RECURRING from 2026-03-10/03-17/04-08/05-01/05-12/05-21/05-25/06-01; user considers all platform/runtime surfaces or covered as Settings/Memory sub-links — not standalone concepts) |
|
||||
| 4 | LOW | Resolved ON HOLD | Previous run (v2.1.159) item #4 questioned Dynamic Workflows Location `/effort ultracode` and `.claude/workflows/` at 0.65 confidence — both terms now confirmed present on live `/en/workflows` docs page body (ultracode section + save-for-reuse section) | ✅ COMPLETE (resolved; docs page confirmed both terms) |
|
||||
| 5 | LOW | Verification | Latest version confirmed v2.1.160 via raw CHANGELOG.md; key changes: "Renamed dynamic-workflow trigger from 'workflow' to 'ultracode'" + security prompts for shell startup files + `acceptEdits` build-tool config guard + single-file grep satisfies read-before-edit | ✅ COMPLETE (version verified; badge bumped v2.1.159 → v2.1.160 in Phase 2.6) |
|
||||
| 6 | LOW | Verification | All 40+ external CONCEPTS URLs validated against llms.txt sitemap (145 pages) — only recurring `/slash-commands` redirect flagged; all other URLs resolve to expected canonical pages including anchors | ✅ COMPLETE (no NEW broken URLs) |
|
||||
| 7 | LOW | Verification | All 22+ local badge/link target files validated — `best-practice/`, `implementation/`, `reports/`, `.claude/`, `.mcp.json`, `CLAUDE.md`, `orchestration-workflow/` targets all exist | ✅ COMPLETE (no missing local files) |
|
||||
| 8 | LOW | Verification | Beta Badge Currency (rule #7) — Auto Mode (`/en/permission-modes` `<Warning>`: "Auto mode is a research preview"), Dynamic Workflows (`/en/workflows` `<Note>`: "Dynamic workflows are in research preview"), plus all other beta-badged rows confirmed research preview on their respective docs pages | ✅ COMPLETE (all README beta badges accurate; no demotions warranted) |
|
||||
| 9 | LOW | Verification | Command rename scan (rule #9) — v2.1.160 CHANGELOG: "Renamed dynamic-workflow trigger from 'workflow' to 'ultracode'" — keyword rename, not a command rename; row uses `ultracode` keyword from the start; `/code-review`, `/batch` in Bundled Skills row remain accurate | ✅ COMPLETE (no command/skill renames affecting existing rows) |
|
||||
| 10 | LOW | Verification | Anchors stable: `#organize-rules-with-clauderules` on /memory, `#eliminate-prompts-with-auto-mode` on /permission-modes, `#bundled-skills` on /skills, `#track-a-running-review` on /ultrareview, `#run-a-bundled-workflow` on /workflows | ✅ COMPLETE (all stable) |
|
||||
| 11 | LOW | Verification | New `/en/agents` hub page found in sitemap ("Run agents in parallel") — comparison page for subagents/agent-view/agent-teams/workflows; not a new concept, individual items already covered | ✅ COMPLETE (hub page, not CONCEPTS-worthy) |
|
||||
| 12 | LOW | Verification | claude-code-guide cross-check — independent 100+ concept sweep corroborated Dynamic Workflows (v2.1.154) and keyword rename; also flagged "Auto Dream" (unverified, not in v2.1.160 CHANGELOG) and "Channels v2.1.164+" (hallucinated future version); re-surfaced platform surfaces (RECURRING INVALID); version numbers unreliable per prior pattern | ✅ COMPLETE (agents aligned on the actionable finding; guide's unverified claims noted, not acted on) |
|
||||
|
||||
@@ -608,3 +608,58 @@
|
||||
| 15 | LOW | Count Update | OpenSpec commands 11→9 — agent low confidence (0.72), commands are TS modules not .md | COMPLETE (user approved; applied 9) |
|
||||
| 16 | LOW | Note | GSD repo deprecated → migrated to open-gsd/gsd-core (prior run said open-gsd/get-shit-done-redux); still tracking original per workflow scope | ON HOLD (RECURRING; user decision on switching tracking to fork) |
|
||||
| 17 | LOW | Note | HumanLayer remains pre-release CodeLayer IDE; .claude/ scaffold empty; counts unchanged (6/27/0) | COMPLETE (context only, no change) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-06-01 09:26 AM PKT] Development Workflows Update
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | HIGH | Star Update | Update Everything Claude Code ★ from 200k to 201k (200,800 actual — continued upward momentum) | COMPLETE (RECURRING — updated previous run 192k→200k; continuing upward) |
|
||||
| 2 | MED | Workflow | Update Superpowers workflow — subagent-driven-development/requesting-code-review/verification-before-completion changed from sub→top (ddf4ff); +receiving-code-review(sub) appended as final step | COMPLETE (NEW — step colors corrected to match v5.1 architecture; receiving-code-review explicitly added) |
|
||||
| 3 | MED | Workflow | Update Matt Pocock workflow — +/grill-me(top) prepended as first step; /triage and /zoom-out removed; /tdd changed from sub→top | COMPLETE (NEW — workflow reflects current active skills: grill-me, /build, /tdd, /review) |
|
||||
| 4 | MED | Workflow | Update Spec Kit workflow — /speckit.analyze moved from before implement to after implement; +/speckit.taskstoissues appended as final step | COMPLETE (NEW — analyze post-implement gate confirmed; taskstoissues export step added) |
|
||||
| 5 | MED | Workflow | Update gstack workflow — plan-eng-review/plan-design-review changed to sub (fff3b0); +plan-devex-review(sub); /spec replaces design-shotgun; design-consultation(sub) replaces design-html; /codex removed; +/canary appended | COMPLETE (NEW — v1.55+ devex-review added; canary deployment step; /codex removed post-Codex deprecation) |
|
||||
| 6 | MED | Workflow | Update GSD workflow — discuss-phase renamed to spec-phase; verify-work(sub) split into code-review(sub)+validate-phase(sub); complete-milestone renamed to extract-learnings | COMPLETE (NEW — GSD workflow updated post-deprecation migration; spec/validate terminology adopted) |
|
||||
| 7 | MED | Workflow | Update OpenSpec workflow — /opsx:apply changed from top→sub (fff3b0); +/opsx:verify(sub) inserted after apply; +/opsx:bulk-archive(top) appended as final step | COMPLETE (NEW — OpenSpec v1.3.x verify-loop and bulk-archive additions) |
|
||||
| 8 | MED | Workflow | Update BMAD workflow — +bmad-prfaq(sub); +bmad-validate-prd(sub); +bmad-check-implementation-readiness(top); +bmad-qa-generate-e2e-tests(sub); sprint-planning and create-story removed | COMPLETE (NEW — BMAD v6.7.x new skills integrated; QA/validate gates added to pipeline) |
|
||||
| 9 | MED | Workflow | Update oh-my-claudecode workflow — /deep-interview and /team removed; team-plan/prd/exec/verify promoted to top (ddf4ff); team-fix changed to sub (fff3b0); +team-verify(sub) added; /ralph and merge removed | COMPLETE (NEW — omc v4.14+ team-mode workflow restructured; team-verify re-check loop added) |
|
||||
| 10 | MED | Workflow | Update Compound Engineering workflow — +/ce-strategy(top) prepended; /ce-ideate changed from top→sub; /ce-optimize removed; +/ce-update(sub) inserted; +/ce-release-notes(top) appended; /ce-compound-refresh removed | COMPLETE (NEW — CE v3.9+ strategy-first pipeline; update/release-notes steps added) |
|
||||
| 11 | MED | Workflow | Update HumanLayer workflow — +/research_codebase(top) prepended; /validate_plan changed from top→sub; /iterate_plan moved before implement_plan; +/create_handoff(top); +/describe_pr(top) appended | COMPLETE (NEW — HumanLayer CodeLayer pivot; research-first + handoff/PR-description steps added) |
|
||||
| 12 | LOW | Count Update | Update GSD commands from 96 to 67 (commands/gsd/ direct enum; deprecated repo cleanup reduced count) | COMPLETE (NEW — reversal of May 25 96-command spike; post-deprecation migration left 67 commands) |
|
||||
| 13 | LOW | Count Update | Update BMAD skills from 40 to 42 (30 bmm-skills + 12 core-skills directly confirmed) | COMPLETE (RECURRING — oscillating 40↔42; 40 was applied in 12:07 AM run due to arithmetic inconsistency; 42 confirmed by directory count) |
|
||||
| 14 | LOW | Count Update | Update Compound Engineering skills from 42 to 39 (39 skill folders directly enumerated; prior 42 was not fully enumerated) | COMPLETE (NEW — correcting 12:07 AM run's unenumerated 42; 39 is authoritative directory count) |
|
||||
| 15 | LOW | Count Update | Update oh-my-claudecode skills from 47 to 39 (39 skill folders directly enumerated; 47 was padded enumeration in 12:07 AM run) | COMPLETE (RECURRING — 47 was explicitly flagged as padded in previous changelog entry; reverting to 39) |
|
||||
| 16 | LOW | Count Verify | ECC agents 63, commands 121, skills 300+ — directory-enum vs README self-report conflict persists | ON HOLD (RECURRING — 9th consecutive run: Apr 13/16/18/24/26 + May 1/12/21 + Jun 1 AM; keeping current values) |
|
||||
| 17 | LOW | Count Verify | gstack skills 47 — agent reported 52 (conf 0.75) with inconsistent listing; kept at 47 | ON HOLD (RECURRING — agent overcount; 47 per AGENTS.md authoritative catalog) |
|
||||
| 18 | LOW | Count Verify | BMAD agents 6 — current value set in 12:07 AM run (persona-skills); methodology for counting persona-skills as agents remains ambiguous | ON HOLD (RECURRING — from May 12/21 + Jun 1 AM; keeping 6 per last approved value) |
|
||||
| 19 | LOW | Count Verify | oh-my-claudecode commands 0 — agent found 27 .md in commands/ but workflow methodology treats skills as the command surface | ON HOLD (RECURRING — keeping 0 per established methodology) |
|
||||
| 20 | LOW | Note | GSD repo deprecated → migrated to open-gsd/gsd-core; still tracking original per workflow scope | ON HOLD (RECURRING — user decision on switching tracking to fork) |
|
||||
| 21 | LOW | Sort Order | No re-sort needed — stars-descending order preserved: Superpowers 214k > ECC 201k > Matt Pocock 113k > Spec Kit 107k > gstack 105k > GSD 64k > OpenSpec 52k > BMAD 48k > omc 35k > agent-skills 27k > CE 19k > HumanLayer 11k | COMPLETE (verified; ECC 200k→201k does not affect position) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-06-02 09:19 AM PKT] Development Workflows Update
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | HIGH | Star Update | Update Superpowers ★ from 214k to 215k (215k actual — v5.1.0 momentum) | COMPLETE (RECURRING — updated README table) |
|
||||
| 2 | HIGH | Star Update | Update Everything Claude Code ★ from 201k to 202k (202k actual — v2.0.0-rc.1 cross-harness agentic OS) | COMPLETE (RECURRING — updated README table) |
|
||||
| 3 | HIGH | Star Update | Update Matt Pocock Skills ★ from 113k to 114k (114k actual — engineering/productivity skill additions) | COMPLETE (RECURRING — updated README table) |
|
||||
| 4 | HIGH | Star Update | Update Spec Kit ★ from 107k to 108k (108k actual — v0.9.0 bundled extension migration) | COMPLETE (RECURRING — updated README table) |
|
||||
| 5 | HIGH | Star Update | Update gstack ★ from 105k to 106k (106k actual — v1.55.x daily releases) | COMPLETE (RECURRING — updated README table) |
|
||||
| 6 | MED | Star Update | Update BMAD-METHOD ★ from 48k to 49k (48.5k actual — v6.8.0 two-spine UX planning, Web Bundles) | COMPLETE (RECURRING — updated README table) |
|
||||
| 7 | MED | Star Update | Update oh-my-claudecode ★ from 35k to 36k (35.5k actual — v4.14.x Ultragoal durable multi-goal workflow) | COMPLETE (RECURRING — updated README table) |
|
||||
| 8 | MED | Count Update | Update gstack skills from 47 to 61 (61 root-level SKILL.md dirs confirmed from AGENTS.md authoritative catalog; v1.55.x added 14 new skills across browser, iOS, safety categories) | COMPLETE (NEW — previous ON HOLD at 52 now confirmed 61 from AGENTS.md; confidence 0.85) |
|
||||
| 9 | MED | Count Update | Update Compound Engineering agents from 43 to 47 (47 .md filenames explicitly enumerated in directory listing; README states 51) | COMPLETE (NEW — partial increase; 47 is directory-confirmed lower bound; 4 more possible from pagination) |
|
||||
| 10 | MED | Workflow | Update Spec Kit workflow — /speckit.taskstoissues moved from last position to before /speckit.implement; +/speckit.checklist appended as final step (checklist.md in templates/commands/ was in the 9-command count but missing from workflow) | COMPLETE (NEW — v0.9.0 canonicalized order: tasks→taskstoissues→implement→analyze→checklist; conf 0.88) |
|
||||
| 11 | LOW | Sort Order | No re-sort needed — stars-descending order preserved: Superpowers 215k > ECC 202k > Matt Pocock 114k > Spec Kit 108k > gstack 106k > GSD 64k > OpenSpec 52k > BMAD 49k > omc 36k > agent-skills 27k > CE 19k > HumanLayer 11k | COMPLETE (verified) |
|
||||
| 12 | LOW | Count Verify | ECC commands 121→106 (agent found 106 .md files, conf 0.78) — 10th consecutive run with directory-enum giving different value | ON HOLD (RECURRING — from Apr 13/16/18/24/26 + May 1/12/21 + Jun 1 AM/PM; keeping 121 until manual verification) |
|
||||
| 13 | LOW | Count Verify | ECC skills 300+→249 (agent reports publisher-stated 249 from v2.0.0-rc.1 release page; directory pagination cut off at 100) | ON HOLD (RECURRING — 10th consecutive run; keeping 300+ per last approved value) |
|
||||
| 14 | LOW | Count Verify | ECC workflow — agent found new v2.0 PRP workflow (plan→prp-plan→prp-prd→feature-dev→prp-implement→prp-commit→code-review→review-pr→prp-pr) vs current /ecc:plan→/tdd→/code-review→/security-scan→/e2e→merge; conf 0.78 | ON HOLD (NEW — v2.0.0-rc.1 workflow change; keeping current v1.x workflow until higher confidence) |
|
||||
| 15 | LOW | Count Verify | gstack workflow — agent found reordered steps (spec before autoplan, plan-ceo-review→sub, design-consultation removed, land-and-deploy removed); conf 0.85 | ON HOLD (NEW — Jun 1 run just updated this; deferring further reorder) |
|
||||
| 16 | LOW | Count Verify | BMAD agents 6 — agent found 6 bmad-agent-* folders, consistent with current value; README "12+" includes Party Mode personas | ON HOLD (RECURRING — keeping 6 per established methodology) |
|
||||
| 17 | LOW | Count Verify | BMAD skills 42→41 (agent found 29 bmm-skills + 12 core-skills = 41; conf 0.82) | ON HOLD (RECURRING — oscillating 40↔41↔42; keeping 42 per last confirmed directory count) |
|
||||
| 18 | LOW | Count Verify | CE agents 47→51 — README states 51 but only 47 filenames visible in paginated listing | ON HOLD (NEW — applied 47 as lower bound; 4 additional agents possible from pagination) |
|
||||
| 19 | LOW | Count Verify | Matt Pocock skills 29→20+ minimum — agent confirmed 20 from fully enumerated subdirs but in-progress/deprecated not counted; prior count of 29 included those | ON HOLD (RECURRING — keeping 29 per directory-count methodology; agent undercount) |
|
||||
| 20 | LOW | Note | GSD repo deprecated → migrated to open-gsd/gsd-core; still tracking original per workflow scope | ON HOLD (RECURRING — user decision on switching tracking to fork) |
|
||||
|
||||
Reference in New Issue
Block a user