ai-dev-verify

ai-dev-verify is a skill for Claude Code from s977043/PlanGate. It costs 59 tokens per session (5,412 once invoked), scanned B, original, MIT.

An acceptance-testing and handoff workflow for the PlanGate software process. It checks the completed implementation and produces a handoff document for preparing a pull request.

In plain words
What is it for?
Use it after implementation to run the required V-1 through V-4 checks, document results, and prepare the project for review.
Why use it?
It gives the finished work a defined review stage and records what was checked before it is handed over.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; positional $N argument.

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Install

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.

Made for: Claude Code.

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.

agentmods badge for ai-dev-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/s977043/plangate/ai-dev-verify.svg)](https://agentmods.dev/skills/s977043/plangate/ai-dev-verify)
Your own site
<a href="https://agentmods.dev/skills/s977043/plangate/ai-dev-verify"><img src="https://agentmods.dev/badge/skills/s977043/plangate/ai-dev-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,412 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.05412
Opus 5 $0.00030 $0.02706
Sonnet 5 $0.00012 $0.01082
Haiku 4.5 $0.00006 $0.00541

Measured 6d ago against content hash 3273e81368b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

ai-dev-verify scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

> **CLI 本体の位置**を基準に `<CLI の repo root>/.claude/settings.json` を検査するため、
.agents/skills/ai-dev-verify/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI-Driven Verify (PlanGate / Codex 共用)

PlanGate ワークフローの verify & handoff フェーズ(WF-05) を Codex / Claude Code 両方で実行する skill。Rule 5(最終成果物は毎回 handoff に集約)を担保する。

本スキルは bundled resourcesreferences/)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-verify/
install.sh --claude 導入先 .claude/skills/ai-dev-verify/
Codex 導入先 .codex/skills/ai-dev-verify/
上流リポジトリ(正本側) .agents/skills/ai-dev-verify/

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/**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:

  1. <skill_dir> 配下の同梱物(references/)を第一に読む — 契約 doc と handoff 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)
  2. 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
  3. 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:
    1. 導入先リポジトリの相対パス(例: .claude/rules/working-context.md
    2. 無ければ plugin root 配下(例: <plugin_root>/rules/working-context.md
      • <plugin_root> は Bash で ls "${CLAUDE_PLUGIN_ROOT}/rules/" を実行して得た絶対パス。 Read ツールは絶対パスを要求し環境変数を展開しないため、${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
  4. いずれでも解決できなければ 「解決できなかった」と明示し、同梱 references/ と本 Skill の 記述を代替正本として扱い、推測で内容を補わない

plugin root 直下に docs/ を探しに行かないこと: plugin が配布するのは agents / commands / skills / rules 等の定義ディレクトリのみで docs/ を配布対象として 認識せず、plugin root 配下に相当する配布物が存在しないため必ず空振りする。

参照 install.sh --claude 経由 plugin(Claude marketplace)経由 Codex 経由
rules/*.md(下記 3〜6) .claude/rules/ に着地(解決可) <plugin_root>/rules/ で解決 未配置(解決不可 → 手順 4 へ)
契約 doc・handoff テンプレート <skill_dir>/references/ に同梱(解決可) <skill_dir>/references/ に同梱(解決可) <skill_dir>/references/ に同梱(解決可)
bin/**(CLI) コピー対象外(解決不可) バンドル対象外(解決不可) 未配置(解決不可)
scripts/** コピー対象外(解決不可) <plugin_root>/scripts/ は存在するが install-plangate-skills.sh のみ(apply-claude-settings.sh / check-settings-wiring.sh 等は解決不可) 未配置(解決不可)

Read the full file on GitHub · 215 lines

Changes

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.

  1. 6d ago First seen · 215 lines · 59 tokens per session scan B 3273e81368b9

Subscribe to this mod's changes

ai-dev-verify is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed 6d ago), licensed MIT. It adds 59 tokens to every session and 5,412 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

validate

Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.

semantica-agi/semantica · 0 tokens

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.

SethGammon/Citadel · 40 tokens

qa

Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).

SethGammon/Citadel · 56 tokens

test-gen

Generate and verify tests — happy path, edge cases, error paths — using the project's own framework and patterns.

SethGammon/Citadel · 24 tokens

11-browser-qa

Run post-review browser QA and produce short named videos for a locked happy path and sourced browser edge cases. Use when the user wants concise reviewer evidence for a web journey. Not for API, CLI, automated tests, diff review, or application fixes.

ai-driven-dev/framework · 55 tokens

08-three-amigos

Assesses an Epic or Story through one product, delivery, or quality lens, then reconciles three caller-supplied reports. Use when the user wants to refine one before a backlog change. Not for spawning or writing.

ai-driven-dev/framework · 50 tokens