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/s977043/plangate/ai-dev-execnpx skills add s977043/PlanGate --skill ai-dev-execgit clone --depth 1 https://github.com/s977043/PlanGateWrote 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-exec)<a href="https://agentmods.dev/skills/s977043/plangate/ai-dev-exec"><img src="https://agentmods.dev/badge/skills/s977043/plangate/ai-dev-exec.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 | $0.00057 | $0.05447 |
| Opus 5 | $0.00028 | $0.02723 |
| Sonnet 5 | $0.00011 | $0.01089 |
| Haiku 4.5 | $0.00006 | $0.00545 |
Grade A, and why
ai-dev-exec 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 3d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Driven Exec (PlanGate / Codex 共用)
PlanGate ワークフローの exec フェーズ(WF-04 Build & Refine) を Codex / Claude Code 両方で実行する skill。
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-exec/install.sh --claude導入先.claude/skills/ai-dev-exec/Codex 導入先 .codex/skills/ai-dev-exec/上流リポジトリ(正本側) .agents/skills/ai-dev-exec/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。
前提条件(exec 開始ゲート)
-
docs/working/TASK-XXXX/approvals/c3.jsonが存在し、そのapproval_kindに応じた承認条件を 満たすこと。判別は python3 の strict JSON で行う(非アンカーなgrep/sedは c3-prime で 誤動作する。契約 §5):record 種別 判別 承認済みと見なす条件 legacy approval_kindキー なしc3_status: APPROVEDc3-prime approval_kind: "c3-prime"decision: "AUTO_APPROVED"(c3_statusは契約 §5 で明示禁止。含まれていたら FAIL)かつ Plan Package 束縛の全数検証 PASS(plan_hash/artifact_hashes6 要素 /plan_package_hash/source_sha/ reviewer verdict 整合)。正本: 同梱references/c3-prime-contract.md§2〜§5それ以外の値 — 受理拒否(exec 不可) -
validate 相当が PASS(plan_hash 整合 / artifact 整合 / EH-3 整合)
-
exec 入口も上記 1 と同じ分岐で承認済み record のみ受理する(CLI がある環境では CLI 側が機械チェック済み。CLI が無い環境では自分で確認する)
これらが満たされなければ exec を開始しない。実際のコマンド表記(bin/plangate /
plangate / CLI 不在)・TASK-XXXX の解決先・CLI が無い環境での代替手順は
「CLI 呼び出し」節を参照する(CLI が無いことを理由にゲートを省略しない)。
settings タスクロック (
plangate doctor --check-settings) は V-1 / handoff 完了の前提条件(.claude/rules/working-context.md→ fallback<plugin_root>/rules/working-context.mdが正本)。exec 入口では block しない。詳細はai-dev-verifyskill。
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:
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.
- 3d ago First seen · 219 lines · 57 tokens per session scan A 6056d8b7229c
ai-dev-exec is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 5,447 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]…
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.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
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.
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.