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/emasoft/claude-plugins-validation/cpv-plugin-validation-skillnpx skills add Emasoft/claude-plugins-validation --skill cpv-plugin-validation-skillgit clone --depth 1 https://github.com/Emasoft/claude-plugins-validationWrote 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/emasoft/claude-plugins-validation/cpv-plugin-validation-skill)<a href="https://agentmods.dev/skills/emasoft/claude-plugins-validation/cpv-plugin-validation-skill"><img src="https://agentmods.dev/badge/skills/emasoft/claude-plugins-validation/cpv-plugin-validation-skill.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 | $0.00063 | $0.01152 |
| Opus 5 | $0.00032 | $0.00576 |
| Sonnet 5 | $0.00013 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
cpv-plugin-validation-skill 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 today.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Validation Skill
Phase 0 — plugin-shape detection (MANDATORY before any other action)
Before validating, fixing, migrating, upgrading, or scaffolding ANY directory, the agent MUST run shape-detection to verify the directory IS a plugin. If .claude-plugin/plugin.json is missing, the agent MUST refuse to scaffold a plugin around a SKILL.md / single agent / loose commands / unknown folder, and instead ABORT and ask the user whether to "wrap into a NEW plugin" or "ADD to an existing plugin". Hard refusal protocol + detection table in the reference.
The canonical plugin layout, manifest schema, env vars, caching rules, and CLI commands are EMBEDDED verbatim from the official doc at plugins-reference. Always read it BEFORE deciding any plugin shape question.
Overview
Validates Claude Code plugins against 190+ structural and quality rules covering manifests, hooks, skills, MCP servers, marketplace configs, and agents. Produces a severity-graded report with actionable fix guidance.
Prerequisites
- Python 3.12+ with
pyyaml,uvpackage manager - Plugin directory with valid structure (
.claude-plugin/plugin.json— see Phase 0)
Instructions
- Run Phase 0 plugin-shape detection. If NOT a plugin → ABORT and ask the user.
- Run via the launcher (see launcher-invocation — NEVER call
validate_plugin.pydirectly).Why the launcher is mandatory · The one-liner (use this verbatim) · Full alias table · Direct invocation (development only)
- Review compact summary; always use
--reportto save details. - Fix issues CRITICAL > MAJOR > MINOR (
/cpv-fix-validation <report_path>). - Re-run until exit code 0.
Output
- Exit codes: 0 (pass), 1 (CRITICAL), 2 (MAJOR), 3 (MINOR), 4 (NIT, --strict). WARNING never blocks.
- Report at
$MAIN_ROOT/reports/validate_plugin/<TS>-<slug>.md. - For A-F semantic grades use
/cpv-semantic-validation.
What ships with it
17 files 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.
- README.md 2.1 KB
- references/hook-validation.md 19 KB
- references/launcher-invocation.md 3.9 KB
- references/marketplace-validation.md 27 KB
- references/mcp-validation.md 14 KB
- references/official-docs-urls.md 6.1 KB
- references/pipeline-validation.md 7.0 KB
- references/plugin-structure.md 14 KB
- references/plugins-reference.md 62 KB
- references/pre-push-hook.py 3.5 KB runs code
- references/security-validator-contract.md 4.4 KB
- references/shape-detection.md 13 KB
- references/skill-validation.md 10 KB
- references/skills-reference.md 46 KB
- references/troubleshooting-python-scripts.md 10 KB
- references/validation-checklist.md 20 KB
- references/validation-procedures.md 10 KB
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.
- today First seen · 73 lines · 63 tokens per session scan A 572e6de226a9
cpv-plugin-validation-skill is a skill published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 1,152 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 2026-09-03.
Other skills, from other repositories
skill-teilen
Reicht einen Skill, ein Plugin oder eine Vorlage (CLAUDE.md, settings.json, Prompt) in die SKAILE Community Skill-Library ein. Nutzen wenn der User sagt "teile meinen Skill", "teile meine CLAUDE.md", "teile meine Vorlage", "lade meinen Skill in die Community hoch", "reiche meinen Skill ein", "skill teilen" oder "in…
show-and-share
Schreibt einen fertigen Show-&-Share-Post für die SKAILE Community. Nutzen wenn der User sagt "schreib mir einen Show & Share Post", "stelle meinen Skill vor", "Post für meinen Skill/meine Vorlage", "schreib einen Post zu dem was ich gebaut habe", oder direkt nachdem ein Skill mit skill-teilen eingereicht wurde.
readme-pro
Schreibt oder verbessert ein README für das aktuelle Projekt. Nutzen wenn der User "schreib mir ein README", "dokumentier das Projekt" oder "readme-pro" sagt.
exec
数十秒を超えて走るプログラム・スクリプト（学習・評価・データ処理・サーバ等）をログを残す形で起動し，異常の早期検知と完了報告まで担う．「実行して」「動かして」「学習を回して」など，明示の有無に関わらず自動適用する．数十秒で終わる実行（テスト・ビルド・lint 等）は対象外．既に動いているものの状況を知りたいだけなら /ops:progress，UI を見た目で確かめたいだけなら組み込みの run スキルを使う．.
survey
プロジェクト文脈を把握し .claude/context.md を作成する．新しいプロジェクトを始めるときに使う．context.md が既にある場合は /groundwork:theory を使う．.
release
リリース単位（単一パッケージか monorepo か）を判定し，SemVer でバージョンを上げ（マニフェストと全参照箇所を整合），bump コミット・タグ・push・About 欄・GitHub Release までの文面を提案．承認後に一気に実行する．「リリースして」「公開して」「バージョンを上げて」など版を公にすることを求められたときに使う．記録するだけなら /capstone:commit を使う．.