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 redgit 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/red)<a href="https://agentmods.dev/skills/morodomi/dev-crew/red"><img src="https://agentmods.dev/badge/skills/morodomi/dev-crew/red/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/red"><img src="https://agentmods.dev/badge/skills/morodomi/dev-crew/red.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 | $0.00040 | $0.01033 |
| Opus 5 | $0.00020 | $0.00517 |
| Sonnet 5 | $0.00008 | $0.00207 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
red scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Current State
!ls -t docs/cycles/*.md 2>/dev/null | head -1 || echo "(none)"
禁止事項
- 実装コード作成（GREENで行う）
- テストを通すための実装
Workflow
Cycle Doc Gate
for f in docs/cycles/*.md; do [ -f "$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)
Pre-RED Gate (deterministic)
Cycle doc の Progress Log を確認し、以下が全て満たされなければ BLOCK:
- sync-plan完了: Progress Log に
SYNC-PLANまたはsync-planセクションがあり、Phase completed記録がある - Plan Review完了: Progress Log に
Plan Reviewまたはplan-reviewの記録がある
# Cycle doc を取得（Cycle Doc Gate で既に特定済み）
# 1. sync-plan チェック
awk '/SYNC.PLAN|sync-plan/,/Phase completed/' "$CYCLE_DOC" | grep -qi 'Phase completed'
# 2. Plan Review チェック
grep -qiE 'Plan Review|review.*plan' "$CYCLE_DOC"
いずれか失敗 → BLOCK（不足ステップを案内）
Test ListのTODOからテストケースを選択してWIPに移動。
Complexity Gate
Test List に対してREDフェーズ開始時に評価する。詳細: reference.md
| Class | Criteria | Stages |
|---|---|---|
| trivial | 1-2 items, Example only, no escalation triggers | Stage 1 as 1-line GWT; Stage 2 skip; Stage 3 |
| standard | 3-5 items, Example only, no complex escalation triggers | Stage 1 simplified; Stage 2 Review skip; Stage 3 |
| complex | 6+ items OR any non-Example paradigm | Full 3-stage (all stages) |
Stage 1: Test Plan
Cycle doc の Test List を Given/When/Then + 具体テストデータに展開。詳細: reference.md
Stage 2: Test Plan Review
要件とテスト計画を照合（網羅性・カテゴリバランス）。Gap発見時は追加。詳細: reference.md
Stage 3: Test Code
テストファイル依存関係分析 → red-worker並列起動 → 結果収集・マージ → テスト実行で失敗確認。 詳細: reference.md
Stage 3.5: False-pass 自己証明
新規 test の literal が「false-pass 不在を自己証明」できることを確認（対象行除去 → count 0 / FAIL の実証）。手順: reference.md
What ships with it
1 file 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.
- 8d ago First seen · 86 lines · 40 tokens per session scan A 6844e6d5edfe
red is a skill published in the GitHub repository morodomi/dev-crew (1 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,033 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
x-qdev
A compact development workflow for a small, clearly defined code change. It keeps the requirement, initially failing tests, implementation, and real verification results in one task document, following TDD, or test-driven development.
develop-small-feature
Implement a small, well-scoped feature or fix end-to-end from spec to PR — reuse or create a feature branch, implement test-first, run static checks, get user verification, commit, then open a PR to main.
test-driven-development
Runs a recorded red-green-refactor cycle. Use when implementing a feature, bug fix, or behavior change.
tdd
Use when building any T3 feature or bugfix, recommended for T2 on the affected path — write the failing test before the implementation, one behavior at a time, through public interfaces.