Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/morodomi/dev-crew/claude-mdgit clone --depth 1 https://github.com/morodomi/dev-crewWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00953 | $0.00953 |
| Opus 5 | $0.00477 | $0.00477 |
| Sonnet 5 | $0.00191 | $0.00191 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
dev-crew CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@AGENTS.md
dev-crew (Claude Code Extensions)
Claude Code Integration
- plan mode: spec + design consolidated in plan file
- /compact: PreCompact hook (scripts/hooks/pre-compact.sh) persists phase summary before compaction
Auto-orchestrate after plan approve (Post-Approve Action): plan review（Claude + Codex）は承認前（plan mode 内、spec Step 8）で完了済み。plan approve後は /orchestrate を起動する。orchestrate が sync-plan（転記）→ architect（転記後検証）→ TDDサイクルを全て管理する。
Codex Integration
Codex が利用可能な場合、Plan Review と Code Review は常時 competitive に実行。RED/GREEN の委譲は codex_mode (full/no) で制御。REFACTOR は Claude が主担当（Codex fallback）。REVIEW は Claude + Codex competitive。詳細は CONSTITUTION.md 参照。
# plan review は承認前（spec Step 8、plan mode 内、read-only sandbox）で実行。
# session ID は plan の Plan Review Record 経由で sync-plan が Cycle doc frontmatter
# codex_session_id へ転記する（orchestrate 自身は取得しない）
codex exec --sandbox read-only "review plan <planファイルパス>"
# RED/GREEN/REVIEW 委譲（codex_session_id があれば resume <session-id>、なければ resume --last）
codex exec resume <session-id> --full-auto "red docs/cycles/xxx.md"
codex exec resume <session-id> --full-auto "green docs/cycles/xxx.md"
codex exec resume <session-id> --full-auto "review code docs/cycles/xxx.md"
Codex 不在時は Claude fallback（既存スキルそのまま）。
Skills
Available skills (28 total): spec, red, green, refactor, review, commit, orchestrate, diagnose, onboard, sync-skills, skill-maker, cycle-retrospective, codify-insight, learn, evolve, security-scan, attack-report, context-review, generate-e2e, security-audit, php-quality, python-quality, ts-quality, js-quality, flask-quality, flutter-quality, hugo-quality, careful
- cycle-retrospective: TDD サイクル末尾で失敗-成功ペアを抽出する advisory スキル (「retrospective」「振り返り」で起動)
- codify-insight: retrospective insights を既定では自動 triage し、
skill候補/低確信時のみ確認する decide gate (「codify」「codify-insight」で起動)
Token Optimization
Phase-boundary compaction:
- Phase output persisted to Cycle doc before compaction
- Context restored from files, not conversation history
- plan review (承認前) → plan approve → compact + accept edits on → auto-orchestrate
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 62 lines · 953 tokens per session scan A a9d5af1146d3
dev-crew CLAUDE.md is an instructions file published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 4d ago), licensed MIT. It adds 953 tokens to every session, about $0.0048 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
nuxt-supabase-starter CLAUDE.md
Instructions for YuDefine/nuxt-supabase-starter, covering claude.md, language, project structure and meta vs template 邊界.
arc AGENTS.md
Instructions for howells/arc, covering arc, shape, gotchas, editing constraints and search order.
gem-team AGENTS.md
Instructions for mubaidr/gem-team, covering agents.md, project overview, key features, setup commands and install apm (agent package manager).
specs-driven-development-spring-angular always-on.instructions.md
Always-on guardrails for spec-driven Spring + Angular development.
specs-driven-development-spring-angular production-code.instructions.md
Production code guardrails — TDD discipline and Spring Boot 4 conventions.
specs-driven-development-spring-angular frontend-code.instructions.md
Frontend code guardrails for Angular implementation, testing, and accessibility.