Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/s977043/plangate/ai-dev-plan)<a href="https://agentmods.dev/skills/s977043/plangate/ai-dev-plan"><img src="https://agentmods.dev/badge/skills/s977043/plangate/ai-dev-plan.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.06663 |
| Opus 5 | $0.00034 | $0.03331 |
| Sonnet 5 | $0.00014 | $0.01333 |
| Haiku 4.5 | $0.00007 | $0.00666 |
Grade A, and why
ai-dev-plan 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 6d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Driven Plan (PlanGate / Codex 共用)
PlanGate ワークフローの plan フェーズ（WF-02〜WF-03） を Codex / Claude Code 両方で実行する skill。skill が担うのは読む順序と入出力規約であり、機械化された実行ロジックは上流リポジトリ（s977043/plangate）の scripts/ai-dev-workflow / bin/plangate CLI 側にある。
その CLI は導入先には配布されない（Human 決定 #1144: plugin が配るのは読み物層のみで、CLI と enforcement 層〔
scripts/hooks/〕は含めない）。plan フェーズ自体は CLI 非依存で完結する（本 skill の手順どおりplan.md/todo.md/test-cases.mdを手で作る）。CLI が必須なのはplan_hashの機械検証など一部に限られ、その分離と代替手順は下記「CLI 呼び出し」節と「CLI 不在時のフォールバック」節を正本とする。
本スキルは bundled resources（
references/）で自己完結する。パス表記の規約（重要）: 本 SKILL.md 中の
references/…は、すべて 本スキル ディレクトリからの相対パス（=<skill_dir>/…）であって、導入先リポジトリのルートからの 相対パスではない。実行時はまず<skill_dir>（このファイルが置かれているディレクトリ）を 解決してから使う:
環境 <skill_dir>plugin 導入先（Claude marketplace） <plugin_root>/skills/ai-dev-plan/install.sh --claude導入先.claude/skills/ai-dev-plan/Codex 導入先 .codex/skills/ai-dev-plan/上流リポジトリ（正本側） .agents/skills/ai-dev-plan/導入先が独自の正本（上流リポジトリの
docs/配下に相当するもの）を別途保持している 場合は、そちらを優先すること。
Read First
参照解決順（導入先で必ずこの順に探す）
本 Skill は 上流リポジトリ基準の docs/** パスを直接参照しない（#1232）。docs/** は
install.sh --claude / plugin（Claude marketplace）/ Codex の 3 経路とも配布対象外であり、
書いた時点で導入先では必ず空振りするためである。参照の解決は次の順で行う:
<skill_dir>配下の同梱物（references/）を第一に読む — 契約 doc・テンプレートは 本スキルに同梱されている（「同梱リファレンス」節の一覧）- 導入先リポジトリが独自の正本（上流の
docs/配下に相当するもの）を保持していれば、 そちらを優先する - rules（
rules/*.md）だけは配布経路によって着地が異なるため、次の順で探す:- 導入先リポジトリの相対パス（例:
.claude/rules/mode-classification.md） - 無ければ plugin root 配下（例:
${CLAUDE_PLUGIN_ROOT}/rules/mode-classification.md）- 解決は Bash で
ls "${CLAUDE_PLUGIN_ROOT}/rules/"を実行して確認する。 Read ツールは絶対パスを要求し環境変数を展開しないため、${CLAUDE_PLUGIN_ROOT}/...という文字列をそのまま Read しても必ず失敗する - 変数が空・未設定なら glob（
~/.claude/plugins/cache/**等）で推測せず次へ進む。 キャッシュには複数バージョンが並存しうるため、当て推量は版の取り違えを招く
- 解決は Bash で
- 導入先リポジトリの相対パス（例:
- いずれでも解決できなければ 「正本
<path>を参照できなかった」と明示し、本 Skill 内の 記述と同梱references/を代替正本として扱い、推測で内容を補わない
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.
- 6d ago First seen · 289 lines · 69 tokens per session scan A b40b98ae3862
ai-dev-plan is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed 5d ago), licensed MIT. It adds 69 tokens to every session and 6,663 once invoked, about $0.0003 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-maintenance
Automated skill maintenance tool (v6 — Unified Registry + Snapshots). Full scan: [Orphan] migrate misplaced skills from category dirs OR standalone skills/<name>/ to auto-generated/, [Sync] auto-generated/ vs registry lifecycle diff (new/deleted/revived + description auto-sync via lifecycle field), [Reg]…
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.