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 skills/morodomi/dev-crew/evolvenpx skills add morodomi/dev-crew --skill evolvegit 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 | $0.00042 | $0.00882 |
| Opus 5 | $0.00021 | $0.00441 |
| Sonnet 5 | $0.00008 | $0.00176 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
evolve 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.
What it actually says
Evolve - Instinct からスキル/エージェント進化
蓄積された instinct をクラスタリングし、再利用可能なスキルまたはエージェントに進化させる。
前提
- learn スキルで instinct が蓄積されていること
- ${CLAUDE_PLUGIN_DATA}/instincts/ に JSONL ファイルが存在すること
実行手順
Step 1: instinct 読み込み + Empty State チェック
wc -l ${CLAUDE_PLUGIN_DATA}/instincts/*.jsonl 2>/dev/null
instinct が不足している場合:
現在 X 件の instinct が蓄積されています。
クラスタリングには同一 domain で 3件以上の類似パターンが必要です。
learn を継続して instinct を蓄積してください。
0件の場合: 「instinct が蓄積されていません。まず learn を実行してください。」
Step 2: クラスタリング (ルールベース)
以下のルールで類似 instinct をグルーピング:
- domain 一致: 同一 domain フィールドの instinct を抽出
- trigger キーワード類似: trigger 内のキーワードトークン重複率 > 50%
- 閾値: 3件以上のグループをクラスタとして採用（ブートストラップ期間: 全 instinct 10件未満の場合は 2件で採用）
- 品質条件: グループ内全件が confidence >= 0.5
Step 3: ユーザー承認
クラスタごとにプレビューを表示し、AskUserQuestion で確認:
クラスタ: 「PHPStan 型エラー対応」(3件の instinct)
- inst-20260213-001: array access null check
- inst-20260214-003: return type declaration
- inst-20260215-002: strict_types annotation
このクラスタからスキルを生成しますか?
選択肢: 生成する / スキル名を変更して生成 / スキップ
Step 4: バックアップ + スキル/エージェント生成
承認されたクラスタから定義ファイルを生成:
- バックアップ:
${CLAUDE_PLUGIN_DATA}/backup/YYYYMMDD_HHMM/にスナップショット保存 - 出力先:
${CLAUDE_PLUGIN_DATA}/evolved/(staging のみ) - ローカルの dev-crew プラグインソースは書き換えない
- 生成物に由来 instinct ID をコメントとして埋め込む
Step 5: 結果報告
スキル「phpstan-type-fix」を生成しました。
由来: inst-20260213-001, inst-20260214-003, inst-20260215-002
保存先: ${CLAUDE_PLUGIN_DATA}/evolved/phpstan-type-fix/SKILL.md
Step 6: GitHub Issue 作成 (Contribute)
生成されたスキル/エージェントごとに morodomi/dev-crew リポジトリに Issue を作成。
source-path から dev-crew プラグインルートを解決し、テスト検証 (test-*.sh) 後に Issue 作成。
詳細な Issue テンプレート・plugin.json パス検証: reference.md
Reference
詳細: 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.
- yesterday First seen · 84 lines · 42 tokens per session scan A eba7714e3da0
evolve is a skill published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 882 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 2026-08-31.
Other skills, from other repositories
skill-creator
Use when creating new Agent Skills, upgrading existing skills, running evals to test a skill, benchmarking skill performance, or optimizing a skill's description for better triggering accuracy. Guidelines for Gold Standard skill structures.
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…
subagent-delegation
Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.
creating-skills
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…
skill-creator
Create new custom skills by writing SKILL.md playbooks.