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 instructions/kaldown/ccpm/claude-mdgit clone --depth 1 https://github.com/kaldown/ccpmWrote 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/instructions/kaldown/ccpm/claude-md)<a href="https://agentmods.dev/instructions/kaldown/ccpm/claude-md"><img src="https://agentmods.dev/badge/instructions/kaldown/ccpm/claude-md.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 | $0.03031 | $0.03031 |
| Opus 5 | $0.01515 | $0.01515 |
| Sonnet 5 | $0.00606 | $0.00606 |
| Haiku 4.5 | $0.00303 | $0.00303 |
Grade B, and why
ccpm CLAUDE.md 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 4d 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.
| `Enter` / `l` / `Space` | Toggle plugin in **Local** scope (`./.claude/settings.local.json`) | How it starts
The opening of the file, as written. The whole thing — 259 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.
Documentation Hierarchy
This project maintains structured documentation. Read the appropriate files based on context needed.
Committed Documentation (part of repo)
| File | Purpose | When to Read | When to Update |
|---|---|---|---|
CLAUDE.md |
Primary Claude context, high-to-mid level | Auto-read by Claude Code | After significant changes |
docs/architecture.md |
Detailed architecture, data models, component hierarchy | When making architectural changes or need deep context | After structural/architectural changes |
FEATURE_PLAN.md |
Feature tracking, planned/in-progress/completed | When planning work or checking status | After completing features |
README.md |
User-facing documentation | When updating user-facing features | Only for significant user-visible changes |
Local Documentation (gitignored)
| File | Purpose | When to Read |
|---|---|---|
CLAUDE.local.md |
Low-level details, links, templates, preferences | When need ralph-loop setup, external links, implementation details |
.claude/ralph-wiggum-docs.md |
Ralph-wiggum plugin reference | When running ralph-loops |
.claude/ccpm-task-*.md |
Temporal task files | During active task execution |
Reading Order for Full Context
CLAUDE.md(this file) - Always read first (auto-read)docs/architecture.md- For architectural understandingFEATURE_PLAN.md- For current work statusCLAUDE.local.md- For low-level details and templates
Documentation Update Rules
After every significant change:
-
Architectural changes (new modules, data structures, component changes):
- Update
docs/architecture.mdwith new/modified structures - Update
CLAUDE.mdif it affects high-level understanding
- Update
-
Feature completion:
- Update
FEATURE_PLAN.md- move to completed section - Update
CLAUDE.md- remove from in-progress, add to completed if relevant - Update
CLAUDE.local.md- add implementation details - Update
docs/architecture.md- if new components/patterns added - Bump
Cargo.tomlversion - patch-level (0.x.y→0.x.(y+1)) for typical additive features; minor for visible behavior changes that warrant a release marker; major for breaking changes. The bump goes in the same commit as the docs sweep so the version always tracks completed features.
- Update
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.
- 4d ago First seen · 259 lines · 3,031 tokens per session scan B 2798902a8e3c
ccpm CLAUDE.md is an instructions file published in the GitHub repository kaldown/ccpm (51 stars, last pushed 4mo ago), licensed MIT. It adds 3,031 tokens to every session, about $0.0152 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.