diff --git a/.claude/settings.json b/.claude/settings.json
index b0f3822..5ea3f30 100644
--- a/.claude/settings.json
+++ b/.claude/settings.json
@@ -41,7 +41,6 @@
"Bash(kubectl *)",
"Bash(firebase *)",
"Bash(gcloud *)",
- "Bash(curl *)",
"Bash(wget *)",
"Bash(kill *)",
"Bash(killall *)",
diff --git a/README.md b/README.md
index a2ddc31..ef8f9a4 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
# claude-code-best-practice
practice makes claude perfect
--white?style=flat&labelColor=555) 
+-white?style=flat&labelColor=555) 
[](best-practice/) [](implementation/) [](orchestration-workflow/orchestration-workflow.md) [](#-tips-and-tricks) 
= Agents ·
= Commands ·
= Skills
@@ -42,7 +42,7 @@ practice makes claude perfect
|---------|----------|-------------|
| [**Channels**](https://code.claude.com/docs/en/channels)  | `--channels`, plugin-based | Push events from Telegram, Discord, or webhooks into a running session — Claude reacts while you're away · [Reference](https://code.claude.com/docs/en/channels-reference) |
| [**Code Review**](https://code.claude.com/docs/en/code-review)  | GitHub App (managed) | [](https://x.com/claudeai/status/2031088171262554195) Multi-agent PR analysis that catches bugs, security vulnerabilities, and regressions · [Blog](https://claude.com/blog/code-review) |
-| [**Scheduled Tasks**](https://code.claude.com/docs/en/scheduled-tasks) | `/loop`, cron tools | [](https://x.com/bcherny/status/2030193932404150413) [](implementation/claude-scheduled-tasks-implementation.md) Run prompts on a recurring schedule (up to 3 days), set one-time reminders, poll deployments and builds |
+| [**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 3 days) · [`/schedule`](https://code.claude.com/docs/en/web-scheduled-tasks) runs prompts in the cloud on Anthropic infrastructure — works even when your machine is off · [Announcement](https://x.com/noahzweben/status/2036129220959805859) |
| [**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://x.com/bcherny/status/2027534984534544489) | `/simplify`, `/batch` | [](https://x.com/bcherny/status/2027534984534544489) Built-in skills for code quality and bulk operations — simplify refactors for reuse and efficiency, batch runs commands across files |
| [**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 |
@@ -86,13 +86,13 @@ All major workflows converge on the same architectural pattern: **Research → P
| Name | ★ | Uniqueness | Plan |
|
|
|
|------|---|------------|------|---|---|---|
-| [Superpowers](https://github.com/obra/superpowers) | 103k |    |
[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) | 93k |    |
[planner](https://github.com/affaan-m/everything-claude-code/blob/main/agents/planner.md) | 28 | 59 | 116 |
-| [Spec Kit](https://github.com/github/spec-kit) | 79k |    |
[speckit.plan](https://github.com/github/spec-kit/blob/main/templates/commands/plan.md) | 0 | 9+ | 0 |
+| [Superpowers](https://github.com/obra/superpowers) | 107k |    |
[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) | 101k |    |
[planner](https://github.com/affaan-m/everything-claude-code/blob/main/agents/planner.md) | 28 | 60 | 125 |
+| [Spec Kit](https://github.com/github/spec-kit) | 81k |    |
[speckit.plan](https://github.com/github/spec-kit/blob/main/templates/commands/plan.md) | 0 | 9+ | 0 |
| [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) | 42k |    |
[bmad-create-prd](https://github.com/bmad-code-org/BMAD-METHOD/tree/main/src/bmm-skills/2-plan-workflows/bmad-create-prd) | 0 | 0 | 42 |
-| [Get Shit Done](https://github.com/gsd-build/get-shit-done) | 38k |    |
[gsd-planner](https://github.com/gsd-build/get-shit-done/blob/main/agents/gsd-planner.md) | 18 | 52 | 0 |
-| [gstack](https://github.com/garrytan/gstack) | 34k |    |
[plan-eng-review](https://github.com/garrytan/gstack/tree/main/plan-eng-review) | 0 | 0 | 21 |
-| [OpenSpec](https://github.com/Fission-AI/OpenSpec) | 33k |    |
[opsx:propose](https://github.com/Fission-AI/OpenSpec/blob/main/src/commands/workflow/new-change.ts) | 0 | 11 | 11 |
+| [gstack](https://github.com/garrytan/gstack) | 41k |    |
[autoplan](https://github.com/garrytan/gstack/tree/main/autoplan) | 0 | 0 | 27 |
+| [Get Shit Done](https://github.com/gsd-build/get-shit-done) | 40k |    |
[gsd-planner](https://github.com/gsd-build/get-shit-done/blob/main/agents/gsd-planner.md) | 18 | 57 | 0 |
+| [OpenSpec](https://github.com/Fission-AI/OpenSpec) | 33k |    |
[opsx:propose](https://github.com/Fission-AI/OpenSpec/blob/main/src/commands/workflow/new-change.ts) | 0 | 10 | 0 |
| [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
@@ -205,7 +205,7 @@ All major workflows converge on the same architectural pattern: **Research → P
| Tip | Source |
|-----|--------|
| use ASCII diagrams a lot to understand your architecture | [](https://x.com/bcherny/status/2017742759218794768) |
-| use [/loop](https://code.claude.com/docs/en/scheduled-tasks) for recurring monitoring — poll deployments, babysit PRs, check builds (runs up to 3 days) | |
+| use [/loop](https://code.claude.com/docs/en/scheduled-tasks) for local recurring monitoring (up to 3 days) · use [/schedule](https://code.claude.com/docs/en/web-scheduled-tasks) for cloud-based recurring tasks that run even when your machine is off | |
| use [Ralph Wiggum plugin](https://github.com/shanraisshan/novel-llm-26) for long-running autonomous tasks | [](https://x.com/bcherny/status/2007179858435281082) |
| [/permissions](https://code.claude.com/docs/en/permissions) with wildcard syntax (Bash(npm run *), Edit(/docs/**)) instead of dangerously-skip-permissions | [](https://x.com/bcherny/status/2007179854077407667) |
| [/sandbox](https://code.claude.com/docs/en/sandboxing) to reduce permission prompts with file and network isolation — 84% reduction internally | [](https://x.com/bcherny/status/2021700506465579443) [](https://creatoreconomy.so/p/inside-claude-code-how-an-ai-native-actually-works-cat-wu) |
diff --git a/best-practice/claude-commands.md b/best-practice/claude-commands.md
index c6325e2..4cb548a 100644
--- a/best-practice/claude-commands.md
+++ b/best-practice/claude-commands.md
@@ -1,6 +1,6 @@
# Commands Best Practice
-
+
[](../implementation/claude-commands-implementation.md)
Claude Code commands — frontmatter fields and official built-in slash commands.
diff --git a/best-practice/claude-settings.md b/best-practice/claude-settings.md
index c243f5f..0e96b3b 100644
--- a/best-practice/claude-settings.md
+++ b/best-practice/claude-settings.md
@@ -1,6 +1,6 @@
# Claude Code Settings Reference
- 
+ 
A comprehensive guide to all available configuration options in Claude Code's `settings.json` files. As of v2.1.81, Claude Code exposes **60+ settings** and **100+ environment variables** (use the `"env"` field in `settings.json` to avoid wrapper scripts).
@@ -71,11 +71,12 @@ Within the managed tier, precedence is: server-managed > MDM/OS-level policies >
| `autoUpdatesChannel` | string | `"latest"` | Release channel: `"stable"` or `"latest"` |
| `alwaysThinkingEnabled` | boolean | `false` | Enable extended thinking by default for all sessions |
| `skipWebFetchPreflight` | boolean | `false` | Skip WebFetch blocklist check before fetching URLs *(in JSON schema, not on official settings page)* |
-| `availableModels` | array | - | Restrict which models users can select via `/model`, `--model`, or `ANTHROPIC_MODEL`. Does not affect the Default option. Example: `["sonnet", "haiku"]` |
+| `availableModels` | array | - | Restrict which models users can select via `/model`, `--model`, Config tool, or `ANTHROPIC_MODEL`. Does not affect the Default option. Example: `["sonnet", "haiku"]` |
| `fastModePerSessionOptIn` | boolean | `false` | Require users to opt in to fast mode each session |
| `teammateMode` | string | `"auto"` | Agent team display mode: `"auto"` (split panes in tmux/iTerm2, in-process otherwise), `"in-process"`, or `"tmux"` |
| `includeGitInstructions` | boolean | `true` | Include git-related instructions in system prompt |
| `voiceEnabled` | boolean | - | Enable push-to-talk voice dictation. Written automatically when you run `/voice`. Requires a Claude.ai account |
+| `showClearContextOnPlanAccept` | boolean | `false` | Show the "clear context" option on the plan accept screen. Set to `true` to restore the option (hidden by default since v2.1.81) |
| `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 |
**Example:**
@@ -546,9 +547,9 @@ These display preferences are stored in `~/.claude.json`, **not** `settings.json
|-----|------|---------|-------------|
| `autoConnectIde` | boolean | `false` | Automatically connect to a running IDE when Claude Code starts from an external terminal. Appears in `/config` as **Auto-connect to IDE (external terminal)** when running outside a VS Code or JetBrains terminal |
| `autoInstallIdeExtension` | boolean | `true` | Automatically install the Claude Code IDE extension when running from a VS Code terminal. Appears in `/config` as **Auto-install IDE extension**. Can also be disabled via `CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL` env var |
-| `showClearContextOnPlanAccept` | boolean | `false` | When `true`, restores the "clear context" option on plan accept (hidden by default since v2.1.81). *(Source: v2.1.81 changelog — not yet on official settings page; file location unconfirmed)* |
+| `editorMode` | string | `"normal"` | Key binding mode for the input prompt: `"normal"` or `"vim"`. Written automatically when you run `/vim`. Appears in `/config` as **Key binding mode** |
| `showTurnDuration` | boolean | `true` | Show turn duration messages after responses (e.g., "Cooked for 1m 6s"). Edit `~/.claude.json` directly to change |
-| `terminalProgressBarEnabled` | boolean | `true` | Show the terminal progress bar in supported terminals (Windows Terminal, iTerm2). Appears in `/config` as **Terminal progress bar** |
+| `terminalProgressBarEnabled` | boolean | `true` | Show the terminal progress bar in supported terminals (ConEmu, Ghostty 1.2.0+, and iTerm2 3.6.6+). Appears in `/config` as **Terminal progress bar** |
### Status Line Configuration
diff --git a/best-practice/claude-skills.md b/best-practice/claude-skills.md
index 2c45812..0354a65 100644
--- a/best-practice/claude-skills.md
+++ b/best-practice/claude-skills.md
@@ -1,6 +1,6 @@
# Skills Best Practice
-
+
[](../implementation/claude-skills-implementation.md)
Claude Code skills — frontmatter fields and official bundled skills.
diff --git a/best-practice/claude-subagents.md b/best-practice/claude-subagents.md
index de65d91..b0236af 100644
--- a/best-practice/claude-subagents.md
+++ b/best-practice/claude-subagents.md
@@ -1,6 +1,6 @@
# Sub-agents Best Practice
-
+
[](../implementation/claude-subagents-implementation.md)
Claude Code subagents — frontmatter fields and official built-in agent types.
diff --git a/changelog/best-practice/claude-commands/changelog.md b/changelog/best-practice/claude-commands/changelog.md
index 165d50c..898506f 100644
--- a/changelog/best-practice/claude-commands/changelog.md
+++ b/changelog/best-practice/claude-commands/changelog.md
@@ -94,3 +94,9 @@
## [2026-03-21 09:08 PM PKT] Claude Code v2.1.81
No priority action items — report is fully in sync with official documentation (11 frontmatter fields, 63 built-in commands).
+
+---
+
+## [2026-03-23 09:48 PM PKT] Claude Code v2.1.81
+
+No priority action items — report is fully in sync with official documentation (11 frontmatter fields, 63 built-in commands).
diff --git a/changelog/best-practice/claude-settings/changelog.md b/changelog/best-practice/claude-settings/changelog.md
index db5dacb..34152f5 100644
--- a/changelog/best-practice/claude-settings/changelog.md
+++ b/changelog/best-practice/claude-settings/changelog.md
@@ -187,4 +187,15 @@
| 3 | MED | Version Bump | Update report version badge from v2.1.80 to v2.1.81 | ✅ COMPLETE (badge, header version, and header text updated) |
| 4 | MED | New Setting | Add `showClearContextOnPlanAccept` — confirmed in v2.1.81 changelog. When `true`, restores "clear context" option on plan accept (hidden by default). Not yet on official settings page — may be a `~/.claude.json` key | ✅ COMPLETE (added to Global Config Settings table with changelog-source note) |
| 5 | MED | Plugin Documentation | Document `source: 'settings'` as a marketplace source type in Plugin Settings section. Official settings page lists it as one of 7 source types for `extraKnownMarketplaces` | ✅ COMPLETE (added all 7 source types list, inline marketplace example) |
-| 6 | MED | Status Line Fields | Add `rate_limits` field group to Status Line Input Fields table — includes `five_hour.used_percentage`, `five_hour.resets_at`, `seven_day.used_percentage`, `seven_day.resets_at`. Added in v2.1.80 | ✅ COMPLETE (added 4 rate_limits fields to Status Line Input Fields table) |
\ No newline at end of file
+| 6 | MED | Status Line Fields | Add `rate_limits` field group to Status Line Input Fields table — includes `five_hour.used_percentage`, `five_hour.resets_at`, `seven_day.used_percentage`, `seven_day.resets_at`. Added in v2.1.80 | ✅ COMPLETE (added 4 rate_limits fields to Status Line Input Fields table) |
+
+---
+
+## [2026-03-23 10:02 PM PKT] Claude Code v2.1.81
+
+| # | Priority | Type | Action | Status |
+|---|----------|------|--------|--------|
+| 1 | HIGH | Missing Setting (~/.claude.json) | Add `editorMode` (string, default `"normal"`, values: `"normal"` or `"vim"`) to Global Config Settings table. Written automatically when running `/vim`. Confirmed on official settings page | ✅ COMPLETE (added to Global Config Settings table after autoInstallIdeExtension) |
+| 2 | HIGH | File Scope Fix | Move `showClearContextOnPlanAccept` from Global Config Settings (~/.claude.json) to General Settings (settings.json). Official docs now list it in the main Available settings table, not the Global config table. Remove stale annotation "not yet on official settings page" | ✅ COMPLETE (moved to General Settings table before feedbackSurveyRate, removed stale annotation) |
+| 3 | MED | Changed Description | Fix `terminalProgressBarEnabled` supported terminals from "Windows Terminal, iTerm2" to "ConEmu, Ghostty 1.2.0+, and iTerm2 3.6.6+" per official docs | ✅ COMPLETE (terminal list updated) |
+| 4 | MED | Changed Description | Add "Config tool" to `availableModels` description — official docs say "via `/model`, `--model`, Config tool, or `ANTHROPIC_MODEL`". Report currently omits "Config tool" | ✅ COMPLETE (added "Config tool" to description) |
\ No newline at end of file
diff --git a/changelog/best-practice/claude-skills/changelog.md b/changelog/best-practice/claude-skills/changelog.md
index efe1d83..17446fe 100644
--- a/changelog/best-practice/claude-skills/changelog.md
+++ b/changelog/best-practice/claude-skills/changelog.md
@@ -53,3 +53,9 @@ No drift detected — frontmatter fields (10) and bundled skills (5) are fully s
## [2026-03-21 09:07 PM PKT] Claude Code v2.1.81
No drift detected — frontmatter fields (11) and bundled skills (5) are fully synchronized with official docs.
+
+---
+
+## [2026-03-23 09:48 PM PKT] Claude Code v2.1.81
+
+No drift detected — frontmatter fields (11) and bundled skills (5) are fully synchronized with official docs.
diff --git a/changelog/best-practice/claude-subagents/changelog.md b/changelog/best-practice/claude-subagents/changelog.md
index dd2db4a..e0bdb42 100644
--- a/changelog/best-practice/claude-subagents/changelog.md
+++ b/changelog/best-practice/claude-subagents/changelog.md
@@ -88,3 +88,9 @@ No drift detected — report is fully in sync with official docs. All 13 frontma
## [2026-03-21 09:07 PM PKT] Claude Code v2.1.81
No drift detected — report is fully in sync with official docs. All 15 frontmatter fields and 6 built-in agents match.
+
+---
+
+## [2026-03-23 09:49 PM PKT] Claude Code v2.1.81
+
+No drift detected — report is fully in sync with official docs. All 15 frontmatter fields (14 official + 1 unofficial `color`) and 6 built-in agents match.
diff --git a/changelog/best-practice/concepts/changelog.md b/changelog/best-practice/concepts/changelog.md
index 3d8ba7c..ed7b742 100644
--- a/changelog/best-practice/concepts/changelog.md
+++ b/changelog/best-practice/concepts/changelog.md
@@ -166,3 +166,16 @@ Tracks drift between the README CONCEPTS table and official Claude Code document
| 4 | LOW | Verification | Memory anchor `#organize-rules-with-clauderules` confirmed on /memory page | ✅ COMPLETE (section heading exists) |
| 5 | LOW | Verification | Git Worktrees anchor `#run-parallel-claude-code-sessions-with-git-worktrees` confirmed on /common-workflows page | ✅ COMPLETE (section heading exists) |
| 6 | LOW | Verification | All CONCEPTS descriptions checked against official docs — no drift detected | ✅ COMPLETE (all descriptions accurate) |
+
+---
+
+## [2026-03-23 09:53 PM PKT] Claude Code v2.1.81
+
+| # | Priority | Type | Action | Status |
+|---|----------|------|--------|--------|
+| 1 | HIGH | Stale URL | Commands URL `/slash-commands` serves Skills page — docs say "commands merged into skills" | ❌ INVALID (RECURRING from 2026-03-10; URL still resolves; user chose to keep as-is) |
+| 2 | LOW | Verification | All 33 external docs URLs validated — no broken links found | ✅ COMPLETE (all URLs return valid pages including /slash-commands redirect) |
+| 3 | LOW | Verification | All local badge file paths validated — no missing files | ✅ COMPLETE (all 20+ badge targets exist on filesystem) |
+| 4 | LOW | Verification | Memory anchor `#organize-rules-with-clauderules` confirmed on /memory page | ✅ COMPLETE (section heading exists) |
+| 5 | LOW | Verification | Git Worktrees anchor `#run-parallel-claude-code-sessions-with-git-worktrees` confirmed on /common-workflows page | ✅ COMPLETE (section heading exists) |
+| 6 | LOW | Verification | All CONCEPTS descriptions checked against official docs — no drift detected | ✅ COMPLETE (all descriptions accurate) |
diff --git a/changelog/development-workflows/changelog.md b/changelog/development-workflows/changelog.md
index 40e5459..5d33a27 100644
--- a/changelog/development-workflows/changelog.md
+++ b/changelog/development-workflows/changelog.md
@@ -71,3 +71,22 @@
| 8 | MED | Star Update | Update BMAD ★ from 41k to 42k (41,629 actual) | COMPLETE (updated README table) |
| 9 | MED | Star Update | Update OpenSpec ★ from 32k to 33k (32,862 actual) | COMPLETE (updated README table) |
| 10 | MED | Sort Order | Swap gstack (34k) above OpenSpec (33k) — stars descending order | COMPLETE (updated README table) |
+
+---
+
+## [2026-03-23 09:53 PM PKT] Development Workflows Update
+
+| # | Priority | Type | Action | Status |
+|---|----------|------|--------|--------|
+| 1 | HIGH | Star Update | Update Superpowers ★ from 103k to 107k (107,308 actual) | COMPLETE (updated README table) |
+| 2 | HIGH | Star Update | Update ECC ★ from 93k to 101k (101,098 actual — crossed 100k milestone!) | COMPLETE (updated README table) |
+| 3 | HIGH | Count Update | Update ECC commands 59→60, skills 116→125 (v1.9.0 continued: new skills pytorch-patterns, documentation-lookup, claude-devfleet, prompt-optimizer) | COMPLETE (updated README table) |
+| 4 | HIGH | Star Update | Update gstack ★ from 34k to 41k (41,224 actual — v0.9.x multi-AI expansion, CSO security audit) | COMPLETE (updated README table) |
+| 5 | HIGH | Count Update | Update gstack skills 21→27 (6 new: gstack-autoplan, gstack-benchmark, gstack-cso, gstack-design-consultation, gstack-office-hours, gstack-freeze/unfreeze) | COMPLETE (updated README table) |
+| 6 | HIGH | Sort Order | Move gstack (41k) above GSD (40k) — stars descending order | COMPLETE (updated README table) |
+| 7 | HIGH | Star Update | Update GSD ★ from 38k to 40k (39,588 actual) | COMPLETE (updated README table) |
+| 8 | HIGH | Count Update | Update GSD commands 52→57 (v1.28.0: /gsd:forensics, /gsd:milestone-summary, /gsd:plant-seed, /gsd:profile-user, /gsd:workstreams) | COMPLETE (updated README table) |
+| 9 | MED | Star Update | Update Spec Kit ★ from 79k to 81k (81,349 actual — v0.4.0 embedded core pack, 24 platform support) | COMPLETE (updated README table) |
+| 10 | MED | Plan Update | Update gstack Plan from plan-eng-review to autoplan (higher-level orchestrator that reads CEO, design, eng review sequentially) | COMPLETE (updated README table) |
+| 11 | LOW | Count Update | Update OpenSpec commands 11→10 (recount: /opsx:propose, apply, archive, new, continue, ff, verify, sync, bulk-archive, onboard) | COMPLETE (updated README table) |
+| 12 | LOW | Count Correction | Correct OpenSpec skills 11→0 (no skills/ or .claude/skills/ directory exists — OpenSpec is a CLI tool, not skills-based) | COMPLETE (updated README table) |