cpm: Instructions file for Claude Code

CLAUDE.md

cpm CLAUDE.md is an instructions file for Claude Code from open-cli-collective/cpm. It costs 1,012 tokens per session, scanned A, original, MIT.

A set of project instructions for cpm, a terminal application that manages Claude Code plugins.

In plain words
What is it for?
Use it when developing cpm to format, test, lint, inspect, build, or run its Go terminal interface.
Why use it?
It records the project’s layout, architecture, required tools, and standard commands so contributors can work consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is open-cli-collective/cpm's own configuration. It tells Claude Code how to work on cpm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cpm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to open-cli-collective/cpm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/open-cli-collective/cpm/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/open-cli-collective/cpm

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 cpm CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/open-cli-collective/cpm/claude-md/github.svg)](https://agentmods.dev/instructions/open-cli-collective/cpm/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/open-cli-collective/cpm/claude-md"><img src="https://agentmods.dev/badge/instructions/open-cli-collective/cpm/claude-md/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 cpm CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/open-cli-collective/cpm/claude-md"><img src="https://agentmods.dev/badge/instructions/open-cli-collective/cpm/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,012 This file is loaded in full into every session.
When invoked 1,012 The same file — it is already loaded in full.
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 $0.01012 $0.01012
Opus 5.5 $0.00405 $0.00405
Sonnet 5.5 $0.00202 $0.00202
Haiku 4.5 $0.00101 $0.00101

Measured 2mo ago against content hash bc6095cbfe56, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cpm CLAUDE.md 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.

CLAUDE.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cpm - Claude Plugin Manager

Last verified: 2026-02-27

A TUI application for managing Claude Code plugins with clear visibility into installation scopes.

Quick Start

mise install        # Install tools (Go, golangci-lint, gofumpt, lefthook)
lefthook install    # Set up git hooks
mise run build      # Build the application
./cpm               # Run the application

Project Structure

cmd/cpm/           # Application entry point
internal/
  claude/          # Claude CLI client (see internal/claude/CLAUDE.md)
  tui/             # Bubble Tea TUI (see internal/tui/CLAUDE.md)
  version/         # Version info (injected at build time)

Development Commands

mise run fmt       # Format code with gofumpt
mise run lint      # Run golangci-lint
mise run vet       # Run go vet
mise run test      # Run tests
mise run build     # Build binary
mise run ci        # Run all checks

Or use Make: make fmt, make lint, make test, make build, make ci

Architecture

  • Flat model architecture: Single Model struct contains all TUI state
  • Bubble Tea: TUI framework using Elm Architecture (Model-Update-View)
  • Lip Gloss: Terminal styling and layout
  • Claude CLI: All plugin operations shell out to claude plugin commands

See docs/architecture.md for detailed diagrams and type definitions.

Maintaining Architecture Documentation

When making structural changes (new types, packages, or significant refactors):

  1. Update docs/architecture.md with any new/changed types or relationships
  2. Update the "Last updated" date at the top
  3. Use LSP documentSymbol operation to extract current type definitions:
    LSP documentSymbol on internal/claude/types.go, client.go, manifest.go
    LSP documentSymbol on internal/tui/model.go, styles.go, keys.go
    
  4. Ensure Mermaid diagrams reflect current structure

Commit Conventions

This project uses Conventional Commits:

Read the full file on GitHub · 113 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 · 113 lines · 1,012 tokens per session scan A bc6095cbfe56

Subscribe to this mod's changes

cpm CLAUDE.md is an instructions file published in the GitHub repository open-cli-collective/cpm (2 stars, last pushed 7d ago), licensed MIT. It adds 1,012 tokens to every session, about $0.0040 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.

Related

cpm CLAUDE.md compared with instructions from other repositories

cpm CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cpm CLAUDE.mdopen-cli-collective/cpmInstructions file27d agoMITA1,012Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode