agentmods.dev

cc-plugin-eval

cc-plugin-eval is a skill for Claude Code from ANcpLua/ancplua-claude-plugins. It costs 73 tokens per session (1,604 once invoked), scanned A, original, MIT.

A skill that routes requests to cc-plugin-eval, a local checker for Claude Code plugins and skills. It analyzes files, validates configuration, explains scores, and ranks recommended fixes.

In plain words
What is it for?
Use it to audit plugins or skills, validate manifests and hooks, investigate scores, prioritize fixes, and measure token usage.
Why use it?
It turns natural requests such as auditing an add-on or checking a manifest into the appropriate local evaluation command.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cc-plugin-eval plugin — 5 skills shipped together

not rated 6repo 2d ago A scan 73 tokens original MIT

Good fit Use it to audit plugins or skills, validate manifests and hooks, investigate scores, prioritize fixes, and measure token usage.

Compare 6 skills from other repositories ↓
View source ↗ ANcpLua/ancplua-claude-plugins
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ANcpLua/ancplua-claude-plugins
Claude Code
/plugin install cc-plugin-eval

Made for: Claude Code.

Or install cc-plugin-eval, the plugin that ships this one along with the rest of its 5 skills.

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 cc-plugin-eval

README.md
[![agentmods](https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/cc-plugin-eval/github.svg)](https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/cc-plugin-eval)
Your own site
<a href="https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/cc-plugin-eval"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/cc-plugin-eval/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cc-plugin-eval

Your own site · 80×15
<a href="https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/cc-plugin-eval"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/cc-plugin-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,604 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00073 $0.01604
Opus 5.5 $0.00029 $0.00642
Sonnet 5.5 $0.00015 $0.00321
Haiku 4.5 $0.00007 $0.00160

Measured 2mo ago against content hash 812e9bf6f26a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cc-plugin-eval 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 2mo 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.

plugins/cc-plugin-eval/skills/cc-plugin-eval/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cc-plugin-eval

Use this as the umbrella entrypoint for local Claude Code plugin and skill evaluation. cc-plugin-eval is deterministic, local-first, and zero-dependency.

The runnable command blocks below invoke the shipped script through the plugin root, which works in any checkout: node "${CLAUDE_PLUGIN_ROOT}/scripts/cc-plugin-eval.js" <command> <args>. Inline mentions of cc-plugin-eval <command> are shorthand for that same invocation; the bare cc-plugin-eval alias only exists if you ran npm link in the plugin directory.

Start Here

  1. Resolve whether the target path is a skill (contains SKILL.md), a plugin (contains .claude-plugin/plugin.json), or another local folder.
  2. If the user spoke naturally, prefer the chat-first router so they see the routed local command:
node "${CLAUDE_PLUGIN_ROOT}/scripts/cc-plugin-eval.js" start <path> --request "<user request>" --format markdown
  1. Map natural chat requests to workflows:
    • "Evaluate this plugin." -> cc-plugin-eval analyze <path> --format markdown
    • "Evaluate this skill." -> cc-plugin-eval analyze <path> --format markdown (or evaluate-skill alias)
    • "Why did this score that way?" -> cc-plugin-eval analyze <path> --format markdown
    • "What should I fix first?" -> cc-plugin-eval analyze <path> --format markdown
    • "Explain the token budget for this plugin." -> cc-plugin-eval explain-budget <path> --format markdown
    • "Validate the manifest." / "Lint this plugin." -> cc-plugin-eval validate <path> --format markdown
    • "Inspect the hooks." / "Inspect the mcp servers." -> cc-plugin-eval inspect <path> --component <name> --format markdown
    • "Measure the real token usage of this skill." -> init-benchmark then benchmark, then analyze --observed-usage, then measurement-plan
    • "Help me benchmark this plugin." -> starter benchmark flow
    • "What should I run next?" -> cc-plugin-eval start <path> --request "What should I run next?" --format markdown
  2. If the user wants a rewrite plan, route to ../improve-skill/SKILL.md. That skill produces a brief and then hands the brief to skill-creator for the actual rewrite pass.
  3. If the user wants a custom rubric, route to ../metric-pack-designer/SKILL.md.
  4. If the user names a plugin or skill instead of giving a path, resolve it locally before running commands. Prefer ~/.claude/plugins/cache/<plugin-id> for installed plugins, then any repo-local plugins/<name> or skills/<name> directory. If still ambiguous, ask one short clarifying question.
  5. When the request sounds like "give me a full analysis" rather than just "evaluate", do the fuller path:
    • run analyze
    • initialize .cc-plugin-eval/benchmark.json
    • surface the setup questions that refine the starter scenarios
    • preview the first benchmark command the user can execute next

Read the full file on GitHub · 98 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. 2mo ago First seen · 98 lines · 73 tokens per session scan A 812e9bf6f26a

Subscribe to this mod's changes

cc-plugin-eval is a skill published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 1,604 once invoked, about $0.0003 per session on Opus 5.5. 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.

Building agentsancplua-fleet
Related

cc-plugin-eval compared with skills from other repositories

cc-plugin-eval next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cc-plugin-evalANcpLua/ancplua-claude-pluginsSkill62d agoMITA73Claude Code
imagegenopenai/codexSkill135ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill316k7d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code