What is cpal CLAUDE.md?

Project instructions for cpal, a server that lets coding tools ask Claude models for help through the Model Context Protocol, a standard way for AI tools to exchange requests.

Use them when developing, reviewing, or understanding the cpal codebase, including its server, sessions, and model consultation features.

They give the agent the project’s development rules, architecture, and review practices in one place.

How tobert/cpal configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tobert/cpal. 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/tobert/cpal/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tobert/cpal

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tobert/cpal/claude-md/github.svg)](https://agentmods.dev/instructions/tobert/cpal/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tobert/cpal/claude-md"><img src="https://agentmods.dev/badge/instructions/tobert/cpal/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tobert/cpal/claude-md"><img src="https://agentmods.dev/badge/instructions/tobert/cpal/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,438 This file is loaded in full into every session.

When invoked 2,438 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.

Model	Per session	Once invoked
Fable 5.1	$0.02438	$0.02438
Opus 5.5	$0.00975	$0.00975
Sonnet 5.5	$0.00488	$0.00488
Haiku 4.5	$0.00244	$0.00244

Measured 2mo ago against content hash fff9f7ba7834, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cpal 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 · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development Guide

Internal documentation for cpal development.

Dogfooding

Before committing changes to cpal, use cpal to review them:

consult_claude(
    query="Review server.py for bugs, edge cases, and API misuse",
    file_paths=["src/cpal/server.py"],
    extended_thinking=True  # uses Opus by default
)

Architecture

┌─────────────────────────────────────────────────────┐
│              MCP Client                             │
│    (Gemini, Cursor, Claude Code, local models)      │
└─────────────────────┬───────────────────────────────┘
                      │ MCP Protocol
                      ▼
┌─────────────────────────────────────────────────────┐
│                 cpal Server                         │
│                                                     │
│  ┌──────────────────────────────────────────────┐  │
│  │  consult_claude(model="haiku|sonnet|opus")   │  │
│  └──────────────────────┬───────────────────────┘  │
│                         │                          │
│  ┌──────────────────────────────────────────────┐  │
│  │  Session Manager                              │  │
│  │  • Thread-safe with per-session locks         │  │
│  │  • Auto-cleanup after 1 hour TTL              │  │
│  │  • History migrates when switching models     │  │
│  └──────────────────────┬───────────────────────┘  │
│                         │                          │
│  ┌──────────────────────────────────────────────┐  │
│  │  Security Layer                               │  │
│  │  • Path traversal protection                  │  │
│  │  • Symlink attack prevention                  │  │
│  │  • Project directory sandboxing               │  │
│  └──────────────────────┬───────────────────────┘  │
│                         │                          │
│  ┌──────────────────────────────────────────────┐  │
│  │  Agentic Tool Loop                            │  │
│  │  (Claude calls tools autonomously)            │  │
│  └──────────────────────┬───────────────────────┘  │
└──────────────────────────┼──────────────────────────┘
                           ▼
┌─────────────────────────────────────────────────────┐
│              Anthropic API                          │
│                                                     │
│  Claude has internal tools:                         │
│  • list_directory  • read_file  • search_project   │
│                                                     │
│  Agentic loop executes tools until completion       │
└─────────────────────────────────────────────────────┘

Read the full file on GitHub · 262 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.

2mo ago First seen · 262 lines · 2,438 tokens per session scan A fff9f7ba7834

Subscribe to this mod's changes

cpal CLAUDE.md is an instructions file published in the GitHub repository tobert/cpal (5 stars, last pushed 5mo ago), licensed MIT. It adds 2,438 tokens to every session, about $0.0098 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 agents

cpal CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cpal CLAUDE.mdtobert/cpal	Instructions file	5	5mo ago	MIT	A	2,438	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

cpal: Instructions file for Claude Code