diff --git a/README.md b/README.md
index d007f6c..1dd14c5 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
# claude-code-best-practice
from vibe coding to agentic engineering - practice makes claude perfect
--white?style=flat&labelColor=555) 
+-white?style=flat&labelColor=555) 
[](best-practice/) [](implementation/) [](orchestration-workflow/orchestration-workflow.md) [](https://code.claude.com/docs) [](#-tips-and-tricks) [](#-subscribe) 
= Agents ยท
= Commands ยท
= Skills
@@ -41,11 +41,12 @@ from vibe coding to agentic engineering - practice makes claude perfect
| Feature | Location | Description |
|---------|----------|-------------|
| [**Routines**](https://code.claude.com/docs/en/routines)  | `claude.ai/code/routines`, `/schedule` | Cloud automation on Anthropic infrastructure โ scheduled, API-triggered, or GitHub event-driven tasks that run even when your machine is off ยท [Desktop Tasks](https://code.claude.com/docs/en/desktop-scheduled-tasks) |
+| [**Ultrareview**](https://code.claude.com/docs/en/ultrareview)  | `/ultrareview` | Cloud-based multi-agent code review โ every finding independently reproduced and verified in a remote sandbox (5โ10 min, ~$5โ20/run); 3 free runs for Pro/Max ยท [Tasks tracking](https://code.claude.com/docs/en/ultrareview#track-a-running-review) |
| [**Devcontainers**](https://code.claude.com/docs/en/devcontainer) | `.devcontainer/` | Preconfigured development containers with security isolation and firewall rules for consistent Claude Code environments |
| [**Channels**](https://code.claude.com/docs/en/channels)  | `--channels`, plugin-based | Push events from Telegram, Discord, or webhooks into a running session โ Claude reacts while you're away ยท [Reference](https://code.claude.com/docs/en/channels-reference) |
| [**Ultraplan**](https://code.claude.com/docs/en/ultraplan)  | `/ultraplan` | Draft plans in the cloud with browser-based review, inline comments, and flexible execution โ remotely or teleported back to terminal |
-| [**No Flicker Mode**](https://code.claude.com/docs/en/fullscreen)  | `CLAUDE_CODE_NO_FLICKER=1` | [](https://x.com/bcherny/status/2039421575422980329) Flicker-free alt-screen rendering with mouse support, stable memory, and in-app scrolling โ opt-in research preview |
-| [**Auto Mode**](https://code.claude.com/docs/en/permission-modes#eliminate-prompts-with-auto-mode)  | `claude --enable-auto-mode` | [](https://x.com/claudeai/status/2036503582166393240) Background safety classifier replaces manual permission prompts โ Claude decides what's safe while blocking prompt injection and risky escalations ยท Start with `claude --enable-auto-mode` (or `--permission-mode auto`), or cycle to it with `Shift+Tab` during a session ยท [Blog](https://claude.com/blog/auto-mode) |
+| [**No Flicker Mode**](https://code.claude.com/docs/en/fullscreen)  | `/tui fullscreen`, `CLAUDE_CODE_NO_FLICKER=1` | [](https://x.com/bcherny/status/2039421575422980329) Flicker-free alt-screen rendering with mouse support, stable memory, and in-app scrolling โ `/tui fullscreen` is the canonical toggle (v2.1.110+); env var is the legacy path |
+| [**Auto Mode**](https://code.claude.com/docs/en/permission-modes#eliminate-prompts-with-auto-mode)  | `--permission-mode auto`, `Shift+Tab` | [](https://x.com/claudeai/status/2036503582166393240) Background safety classifier replaces manual permission prompts โ Claude decides what's safe while blocking prompt injection and risky escalations ยท `--enable-auto-mode` flag removed (v2.1.111); Max subscribers default with Opus 4.7 ยท [Blog](https://claude.com/blog/auto-mode) |
| [**Power-ups**](best-practice/claude-power-ups.md) | `/powerup` | [](best-practice/claude-power-ups.md) Interactive lessons teaching Claude Code features with animated demos (v2.1.90) |
| [**Computer Use**](https://code.claude.com/docs/en/computer-use)  | `computer-use` MCP server | Let Claude control your screen โ open apps, click, type, and screenshot your display on macOS ยท [Desktop](https://code.claude.com/docs/en/desktop#let-claude-use-your-computer) |
| [**Agent SDK**](https://code.claude.com/docs/en/agent-sdk/overview) | `npm` / `pip` package | Build production AI agents with Claude Code as a library โ Python and TypeScript SDKs with built-in tools, hooks, subagents, and MCP ยท [Quickstart](https://code.claude.com/docs/en/agent-sdk/quickstart) ยท [Examples](https://github.com/anthropics/claude-agent-sdk-demos) |
@@ -57,10 +58,11 @@ from vibe coding to agentic engineering - practice makes claude perfect
| [**GitHub Actions**](https://code.claude.com/docs/en/github-actions) | `.github/workflows/` | Automate PR reviews, issue triage, and code generation in CI/CD pipelines ยท [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) Continue local sessions from any device โ phone, tablet, or browser ยท [Headless Mode](https://code.claude.com/docs/en/headless) |
| [**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) Multiple agents working in parallel on the same codebase with shared task coordination |
-| [**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) `/loop` runs prompts locally on a recurring schedule (up to 7 days) ยท [`/schedule`](https://code.claude.com/docs/en/routines) runs prompts in the cloud on Anthropic infrastructure โ works even when your machine is off ยท [Announcement](https://x.com/noahzweben/status/2036129220959805859) |
+| [**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) `/loop` runs prompts locally on a recurring schedule (up to 7 days) โ supports self-pacing where Claude picks its own interval via the Monitor tool ยท [`/schedule`](https://code.claude.com/docs/en/routines) runs prompts in the cloud on Anthropic infrastructure โ works even when your machine is off ยท [Announcement](https://x.com/noahzweben/status/2036129220959805859) |
+| [**Tasks**](https://code.claude.com/docs/en/ultrareview#track-a-running-review) | `/tasks`, `~/.claude/tasks/` | [](reports/claude-global-vs-project-settings.md) Persistent multi-session task tracking โ view running and completed background work (ultrareview, agents, scheduled tasks) and inspect dependencies; replaces the deprecated TodoWrite tool |
| [**Voice Dictation**](https://code.claude.com/docs/en/voice-dictation)  | `/voice` | [](https://x.com/trq212/status/2028628570692890800) Push-to-talk speech input for prompts with 20-language support and rebindable activation key |
| [**Simplify & Batch**](https://code.claude.com/docs/en/skills#bundled-skills) | `/simplify`, `/batch` | [](https://x.com/bcherny/status/2027534984534544489) Built-in skills for code quality and bulk operations โ simplify refactors for reuse and efficiency, batch runs commands across files |
-| [**Git Worktrees**](https://code.claude.com/docs/en/common-workflows#run-parallel-claude-code-sessions-with-git-worktrees) | built-in | [](https://x.com/bcherny/status/2025007393290272904) Isolated git branches for parallel development โ each agent gets its own working copy |
+| [**Git Worktrees**](https://code.claude.com/docs/en/common-workflows#run-parallel-claude-code-sessions-with-git-worktrees) | built-in, `EnterWorktree`/`ExitWorktree`, `isolation: "worktree"` | [](https://x.com/bcherny/status/2025007393290272904) Isolated git branches for parallel development โ each agent gets its own working copy; subagents can run in temporary worktrees via `isolation: "worktree"` frontmatter (v2.1.106+) |
@@ -98,15 +100,15 @@ All major workflows converge on the same architectural pattern: **Research โ P
| Name | โ
| Uniqueness | Plan |
|
|
|
|------|---|------------|------|---|---|---|
-| [Everything Claude Code](https://github.com/affaan-m/everything-claude-code) | 158k |    |
[planner](https://github.com/affaan-m/everything-claude-code/blob/main/agents/planner.md) | 48 | 143 | 230 |
-| [Superpowers](https://github.com/obra/superpowers) | 156k |    |
[writing-plans](https://github.com/obra/superpowers/tree/main/skills/writing-plans) | 5 | 3 | 14 |
+| [Everything Claude Code](https://github.com/affaan-m/everything-claude-code) | 160k |    |
[planner](https://github.com/affaan-m/everything-claude-code/blob/main/agents/planner.md) | 48 | 143 | 230 |
+| [Superpowers](https://github.com/obra/superpowers) | 159k |    |
[writing-plans](https://github.com/obra/superpowers/tree/main/skills/writing-plans) | 5 | 3 | 14 |
| [Spec Kit](https://github.com/github/spec-kit) | 89k |    |
[speckit.plan](https://github.com/github/spec-kit/blob/main/templates/commands/plan.md) | 0 | 9+ | 0 |
-| [gstack](https://github.com/garrytan/gstack) | 74k |    |
[autoplan](https://github.com/garrytan/gstack/tree/main/autoplan) | 0 | 0 | 46 |
-| [Get Shit Done](https://github.com/gsd-build/get-shit-done) | 54k |    |
[gsd-planner](https://github.com/gsd-build/get-shit-done/blob/main/agents/gsd-planner.md) | 31 | 122 | 0 |
+| [gstack](https://github.com/garrytan/gstack) | 76k |    |
[autoplan](https://github.com/garrytan/gstack/tree/main/autoplan) | 0 | 0 | 37 |
+| [Get Shit Done](https://github.com/gsd-build/get-shit-done) | 55k |    |
[gsd-planner](https://github.com/gsd-build/get-shit-done/blob/main/agents/gsd-planner.md) | 33 | 122 | 0 |
| [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) | 45k |    |
[bmad-create-prd](https://github.com/bmad-code-org/BMAD-METHOD/tree/main/src/bmm-skills/2-plan-workflows/bmad-create-prd) | 0 | 0 | 39 |
-| [OpenSpec](https://github.com/Fission-AI/OpenSpec) | 41k |    |
[opsx:propose](https://github.com/Fission-AI/OpenSpec/blob/main/src/commands/workflow/new-change.ts) | 0 | 10 | 0 |
-| [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) | 29k |    |
[ralplan](https://github.com/Yeachan-Heo/oh-my-claudecode/tree/main/skills/ralplan) | 19 | 0 | 37 |
-| [Compound Engineering](https://github.com/EveryInc/compound-engineering-plugin) | 14k |    |
[ce-plan](https://github.com/EveryInc/compound-engineering-plugin/tree/main/plugins/compound-engineering/skills/ce-plan) | 49 | 3 | 51 |
+| [OpenSpec](https://github.com/Fission-AI/OpenSpec) | 41k |    |
[opsx:propose](https://github.com/Fission-AI/OpenSpec/blob/main/src/commands/workflow/new-change.ts) | 0 | 11 | 0 |
+| [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) | 30k |    |
[ralplan](https://github.com/Yeachan-Heo/oh-my-claudecode/tree/main/skills/ralplan) | 19 | 0 | 37 |
+| [Compound Engineering](https://github.com/EveryInc/compound-engineering-plugin) | 15k |    |
[ce-plan](https://github.com/EveryInc/compound-engineering-plugin/tree/main/plugins/compound-engineering/skills/ce-plan) | 50 | 4 | 44 |
| [HumanLayer](https://github.com/humanlayer/humanlayer) | 10k |    |
[create_plan](https://github.com/humanlayer/humanlayer/blob/main/.claude/commands/create_plan.md) | 6 | 27 | 0 |
### Others
@@ -246,7 +248,7 @@ All major workflows converge on the same architectural pattern: **Research โ P
| [/sandbox](https://code.claude.com/docs/en/sandboxing) to reduce permission prompts with file and network isolation โ 84% reduction internally | [](https://x.com/bcherny/status/2021700506465579443) [](https://creatoreconomy.so/p/inside-claude-code-how-an-ai-native-actually-works-cat-wu) |
| invest in [product verification](https://code.claude.com/docs/en/skills) skills (signup-flow-driver, checkout-verifier) โ worth spending a week to perfect | [](https://x.com/trq212/status/2033949937936085378) |
| use [auto mode](https://code.claude.com/docs/en/permission-modes#eliminate-prompts-with-auto-mode) instead of dangerously-skip-permissions โ a model-based classifier decides if each command is safe and auto-approves, pauses and asks if risky. Shift+Tab to cycle Ask โ Plan โ Auto modes ๐ซ๐ถ | [](tips/claude-boris-6-tips-16-apr-26.md) |
-| use /fewer-permission-prompts skill to scan session history for safe bash/MCP commands that repeatedly prompt, then get a recommended allowlist to paste into [settings](best-practice/claude-settings.md) | [](tips/claude-boris-6-tips-16-apr-26.md) |
+| use /less-permission-prompts skill to scan session history for safe bash/MCP commands that repeatedly prompt, then get a recommended allowlist to paste into [settings](best-practice/claude-settings.md) | [](tips/claude-boris-6-tips-16-apr-26.md) |
| build a /go skill that (1) tests end-to-end via bash/browser/computer use (2) runs /simplify (3) puts up a PR โ so when you come back, you know the code works ๐ซ๐ถ | [](tips/claude-boris-6-tips-16-apr-26.md) |
โ **Git / PR (5)**