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 skills add morodomi/dev-crew --skill reviewgit clone --depth 1 https://github.com/morodomi/dev-crewWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/morodomi/dev-crew/review)<a href="https://agentmods.dev/skills/morodomi/dev-crew/review"><img src="https://agentmods.dev/badge/skills/morodomi/dev-crew/review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/morodomi/dev-crew/review"><img src="https://agentmods.dev/badge/skills/morodomi/dev-crew/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00063 | $0.01139 |
| Opus 5.5 | $0.00025 | $0.00456 |
| Sonnet 5.5 | $0.00013 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mode Determination
| 引数/コンテキスト | Mode | 入力ソース |
|---|---|---|
--plan or PLAN直後 |
"plan" | planファイル |
--code or REFACTOR直後 |
"code" | git diff HEAD |
| 引数なし | "code" (default) | git diff HEAD |
Workflow
Gate (mode別)
plan mode: planファイルの存在確認。なければ BLOCK: 「先に spec を実行してください」（plan file 前提: Cycle doc は承認後にのみ生成されるため、plan mode review は Cycle doc 不在でも plan ファイル単体で動作する）
code mode only:
- Cycle Doc Gate (frontmatter のみ):
for f in docs/cycles/*.md; do [ -f "$f" ] || continue; fm=$(awk '/^---$/{c++;next} c==1{print}' "$f"); echo "$fm" | grep -q '^phase:' || continue; echo "$fm" | grep -q 'phase: DONE' && continue; printf '%s\t%s\n' "$(echo "$fm" | awk 'sub(/^updated: */,""){gsub(/T/," ");print;exit}')" "$f"; done | sort | tail -1 | cut -f2→ found: continue / not found: BLOCK(run spec) - Cycle doc を読み、これまでの成果を把握する
- Phase Ordering Gate: Progress Log に
REFACTORのPhase completed記録があるか確認。なければ BLOCK: 「先に refactor を実行してください」 - Repo-state pre-check (cycle 20260424_1119 #3): review 実行前に
git status --shortを先に確認し、??(untracked) orD(unstaged deletion) を検出したら WARN + 対応案内。新規 test file / Cycle doc 等が未 staged のまま review されるのを防ぐ。
Mode を判定し出力: [REVIEW] Mode: plan or [REVIEW] Mode: code
Step 1-5: Review Pipeline
- Risk Classification:
risk-classifier.shで決定論的判定 - Review Brief: review-briefer (haiku) で圧縮 Brief 生成
- Lint-as-Code (code mode のみ): 静的解析ツール実行
- Specialist Panel: Always-on: security-reviewer + correctness-reviewer (code) / design-reviewer (plan)。Risk-gated: performance/product/usability-reviewer。起動前に
.claude/dev-crew.jsonの review_policy を読みモデルを解決する（self=orchestrator の現モデル、explicit=指定モデル、HIGH tierはescalate_high_to）。詳細: steps-subagent.md / reference.md - Verdict Aggregation: critical≥1=BLOCK(plan→PLAN再設計/code→RED/GREEN/REFACTOR) / important≥1=WARN / else=PASS（severity-verdict.sh が決定論集計）
Progress Log 更新
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +1 lines 5ef85e120dd0
- 1mo ago First seen · 55 lines · 63 tokens per session scan A 1329f6ba007f
review is a skill published in the GitHub repository morodomi/dev-crew (1 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 1,139 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
deep-implement
Implements code from /deep-plan section files with TDD methodology, code review, and git workflow. Use when implementing plans created by /deep-plan.
code-review
A structured way to examine code changes before or during a merge. It checks both the project's coding standards and whether the change matches its requested behavior.
oss-polish
A workflow for improving an open-source project's GitHub presentation and public story. It covers the README, repository topics and description, commit history, and positioning among similar projects.
git-workflow
Perform requested Git actions while preserving user work. Triggers on "commit", "提交".
refactoring
A workflow for changing a codebase’s structure while keeping its behavior the same. It covers moving code, splitting files and changing dependency boundaries.
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…