メニュー
Derive Claude rules from git commit history. Use when extracting implicit decisions from commits or codifying code-style, testing, and API-design rules.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/laurigates/claude-plugins --skill blueprint-derive-rulesコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Install, configure and troubleshoot MCP servers. Use when adding/enabling servers, editing .mcp.json, fixing OAuth, or when a server runs stale code after an upstream fix.
FinOps snapshot — org billing, workflow stats, cache usage. Use when you want a high-level view of CI spending or workflow health before diving deeper.
GitHub Actions billing, workflow efficiency, and waste analysis at org or repo level. Use when investigating CI/CD costs, wasted runs, or optimizing triggers.
SKILL.md を表示中
SOC 職業分類に基づく
| created | "2026-01-30T00:00:00.000Z" |
| modified | "2026-06-18T00:00:00.000Z" |
| reviewed | "2026-05-22T00:00:00.000Z" |
| description | Derive Claude rules from git commit history. Use when extracting implicit decisions from commits or codifying code-style, testing, and API-design rules. |
| args | [--since DATE] [--scope SCOPE] |
| argument-hint | --since 2024-01-01 for date range, --scope api for specific area |
| allowed-tools | Read, Write, Glob, Grep, Bash, AskUserQuestion, Task |
| model | opus |
| name | blueprint-derive-rules |
Extract project decisions from git commit history and codify them as Claude rules. Newer commits override older decisions when conflicts exist.
Use case: Derive implicit project patterns from git history to establish consistent AI-assisted development guidelines.
Usage: /blueprint:derive-rules [--since DATE] [--scope SCOPE]
| Use this skill when... | Use alternative when... |
|---|---|
| Want to extract implicit decisions from git history | Creating rules from requirements (use PRDs instead) |
| Project has significant commit history | New project with little history |
| Establishing project coding standards | Quick manual rule creation |
git rev-parse --git-dirfind . -path '*/docs/blueprint/*' -maxdepth 3 -name 'manifest.json' -type fgit rev-list --count HEADgit log --format="%s"find . -path '*/.claude/rules/*' -maxdepth 3 -name "*.md" -type ffind . -path '*/.claude/rules/blueprint/*' -maxdepth 4 -name "*.md" -type fParse $ARGUMENTS:
--since DATE: Analyze commits from specific date (e.g., --since 2024-01-01)--scope SCOPE: Focus on specific area (e.g., --scope api, --scope testing)Execute the complete git-to-rules derivation workflow:
Read structure.generated_rules_path from docs/blueprint/manifest.json (default .claude/rules/):
RULES_DIR=$(jq -r '.structure.generated_rules_path // ".claude/rules/"' docs/blueprint/manifest.json)
mkdir -p "$RULES_DIR"
Use $RULES_DIR for all subsequent reads/writes and conflict checks. Hand-written files in the parent .claude/rules/ are intentionally invisible to this skill (issue #1043).
/blueprint:init first--since and --scope flags to determine analysis rangeUse parallel agents to analyze git history efficiently (see REFERENCE.md):
refactor: commits for code style patternsfix: commits for repeated issue typesfeat!: and BREAKING CHANGE: commits for architecture decisionschore: and build: commits for tooling decisionsConsolidate findings by domain (code-style, testing, api-design, etc.), chronologically (newest first), and by frequency (most common wins).
When multiple commits address the same topic:
git log --format="%H|%ai|%s" | grep "{topic}"feat!: trumps regular commits$RULES_DIRFor each decision, generate rule file using template from REFERENCE.md. Write each file to $RULES_DIR/<filename>.md (the configured structure.generated_rules_path):
Extract source commit, date, type
Determine confidence level (High/Medium/Low based on commit frequency and clarity)
Generate actionable rule statement
Include code examples from commit diffs
Reference any superseded earlier decisions
REQUIRED: scope every generated rule via paths: frontmatter unless the rule genuinely applies everywhere. Rules without paths: load on every session and pollute context for unrelated work. Pick paths: from the source signal:
| Signal | Source | paths: value |
|---|---|---|
Rule body cites a specific file via "patterns extracted from <path>" | Step 3 / 4 conflict resolution | Glob over that file's directory: <dir>/**/*.<ext> |
Rule was derived from chore(deps) / build: commits | Tooling-decision agent | Lockfiles + manifests: package.json, pyproject.toml, Cargo.toml, go.mod, *.lock, biome.json, etc. |
Rule references a language (refactor: + JS-only code blocks) | Code-style agent | Language Glob: **/*.{js,jsx,ts,tsx}, **/*.py, **/*.rs |
| Rule is about tests | Test-strategy agent | **/*.{test,spec}.*, tests/**/*, test/**/* |
| Rule is about API endpoints | API-design agent | src/{api,routes}/**/*, **/*controller*, **/*handler* |
| Rule is about documentation | Docs agent | docs/**, **/*.md |
| Rule restates global project context (already in CLAUDE.md) | any | Do not emit — that's CLAUDE.md's job; abort the rule |
| Rule genuinely applies to every file (e.g. universal error-handling philosophy, security mindset) | Rare | Omit paths: deliberately and note "global rule" in the rule body |
Default to scoping. The auto-derived starting point: take every code block in the rule body, collect the file extensions / directory roots they reference, and emit those as paths:. Verify the resulting glob set actually matches files in the working tree before writing — an empty match list means the inferred scope is wrong; re-derive.
Generate separate rule files by category (see REFERENCE.md for canonical filenames and default paths: per category):
code-style.md, testing-standards.md, api-conventions.md, error-handling.md, dependencies.md, security-practices.mdCheck for conflicts with existing rules only under $RULES_DIR (never the parent .claude/rules/, which may contain hand-authored content unrelated to blueprint):
Update the task registry entry in docs/blueprint/manifest.json:
jq --arg now "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
--arg sha "$(git rev-parse HEAD 2>/dev/null)" \
--argjson processed "${COMMITS_ANALYZED:-0}" \
--argjson created "${RULES_DERIVED:-0}" \
'.task_registry["derive-rules"].last_completed_at = $now |
.task_registry["derive-rules"].last_result = "success" |
.task_registry["derive-rules"].context.commits_analyzed_up_to = $sha |
.task_registry["derive-rules"].stats.runs_total = ((.task_registry["derive-rules"].stats.runs_total // 0) + 1) |
.task_registry["derive-rules"].stats.items_processed = $processed |
.task_registry["derive-rules"].stats.items_created = $created' \
docs/blueprint/manifest.json > tmp.json && mv tmp.json docs/blueprint/manifest.json
docs/blueprint/manifest.json with derived rules metadata: timestamp, commits analyzed, rules generated, source commits| Context | Command |
|---|---|
| Check git status | git rev-parse --git-dir 2>/dev/null && echo "YES" || echo "NO" |
| Count total commits | git rev-list --count HEAD 2>/dev/null || echo "0" |
| Conventional commits % | git log --format="%s" | grep -c "^(feat|fix|refactor)" || echo 0 |
| Extract decision commits | git log --format="%H|%s|%b" | grep -E "(always|never|must|prefer)" |
| Fast derivation | Use parallel agents (Explore) for multi-domain analysis |
For git analysis patterns, rule templates, conflict resolution, and detailed procedures, see REFERENCE.md.