What is cc-plugin-eval CLAUDE.md?

A project instruction file for Claude Code describing the cc-plugin-eval project, its commands, development setup, checks, and tests. Claude Code is a coding assistant that follows repository instructions while working.

Use it when working on the evaluation framework for testing whether Claude Code components such as skills, agents, commands, hooks, and external tool servers activate correctly.

It gives the assistant the project context and the correct commands for building, checking, and testing the code.

cc-plugin-eval CLAUDE.md — Instructions file by imbflool

Install

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.

agentmods

npx agentmods add instructions/imbflool/cc-plugin-eval/claude-md

Clone the repo

git clone --depth 1 https://github.com/imbflool/cc-plugin-eval

Per session 3,802 This file is loaded in full into every session.

When invoked 3,802 The same file — it is already loaded in full.

Security scan A 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.

Model	Per session	Once invoked
Fable 5	$0.03802	$0.03802
Opus 5	$0.01901	$0.01901
Sonnet 5	$0.00760	$0.00760
Haiku 4.5	$0.00380	$0.00380

Measured yesterday against content hash 759576fd692c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cc-plugin-eval CLAUDE.md scanned grade A 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

const response = await fetch(url, {

CLAUDE.md · 384 lines

How it starts

The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

cc-plugin-eval is a 4-stage evaluation framework for testing Claude Code plugin component triggering. It evaluates whether skills, agents, commands, hooks, and MCP servers correctly activate when expected.

Requirements: Node.js >= 20.0.0, Anthropic API key (in .env as ANTHROPIC_API_KEY)

Commands

# Build & Dev
npm run build          # Compile TypeScript to dist/
npm run dev            # Watch mode

# Lint & Type Check
npm run lint           # ESLint
npm run lint:fix       # Auto-fix
npm run format         # Prettier auto-fix
npm run format:check   # Prettier check only
npm run typecheck      # tsc --noEmit

# Test
npm run test           # All tests (Vitest)
npm run test:watch     # Watch mode
npm run test:coverage  # With coverage
npm run test:ui        # Visual test UI (opens browser)

# Single test file
npx vitest run tests/unit/stages/1-analysis/skill-analyzer.test.ts

# Tests matching pattern
npx vitest run -t "SkillAnalyzer"

# E2E tests (requires API key, costs money)
RUN_E2E_TESTS=true npm test -- tests/e2e/
RUN_E2E_TESTS=true E2E_MAX_COST_USD=2.00 npm test -- tests/e2e/

Test behavior: Parallel execution, randomized order, 30s timeout. CI retries failed tests twice.

Additional Linters

npx prettier --check "src/**/*.ts" "*.json" "*.md"
markdownlint "*.md"
uvx yamllint -c .yamllint.yml config.yaml .yamllint.yml
actionlint .github/workflows/*.yml

CLI Usage

cc-plugin-eval run -p ./plugin           # Full pipeline
cc-plugin-eval analyze -p ./plugin       # Stage 1 only
cc-plugin-eval generate -p ./plugin      # Stages 1-2
cc-plugin-eval execute -p ./plugin       # Stages 1-3
cc-plugin-eval run -p ./plugin --dry-run # Cost estimation only
cc-plugin-eval resume -r <run-id>        # Resume interrupted run
cc-plugin-eval run -p ./plugin --fast    # Re-run failed scenarios only

Read the full file on GitHub · 384 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.

yesterday First seen · 384 lines · 3,802 tokens per session scan A 759576fd692c

Subscribe to this mod's changes

cc-plugin-eval CLAUDE.md is an instructions file published in the GitHub repository imbflool/cc-plugin-eval (2 stars, last pushed 2d ago), licensed MIT. It adds 3,802 tokens to every session, about $0.0190 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review Testing ai-testing anthropic claude claude-agent-sdk claude-code cli

qaskills AGENTS.md

Instructions for PramodDutta/qaskills, covering agents.md, project overview, common commands, run a single package and run tests in watch mode.

PramodDutta/qaskills · 2,851 tokens

metabot CLAUDE.md

Instructions for xvirobotics/metabot: The canonical project instructions are in AGENTS.md. Follow that file for this repository. This compatibility file exists for Claude Code; MetaBot install/update does not deploy or replace workspace instruction files.

xvirobotics/metabot · 51 tokens

cc-plugin-eval CLAUDE.md