What is cl-mcp CLAUDE.md?

A project guide for cl-mcp, a server that lets AI agents work with Common Lisp through standard request formats. It covers the project structure, development rules, self-hosting process, testing, and code checks.

Use it when developing cl-mcp, editing its Common Lisp files, evaluating code in its REPL, updating dependencies, or running tests and lint checks.

It tells agents which project tools and commands to use for reading, editing, evaluating, testing, and checking Lisp code. This reduces the chance of using the wrong workflow or changing the project inconsistently.

How cl-ai-project/cl-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to cl-ai-project/cl-mcp. 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/cl-ai-project/cl-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/cl-ai-project/cl-mcp

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/cl-ai-project/cl-mcp/claude-md.svg)](https://agentmods.dev/instructions/cl-ai-project/cl-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/cl-ai-project/cl-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cl-ai-project/cl-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,085 This file is loaded in full into every session.

When invoked 1,085 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	$0.01085	$0.01085
Opus 5	$0.00543	$0.00543
Sonnet 5	$0.00217	$0.00217
Haiku 4.5	$0.00109	$0.00109

Measured 2d ago against content hash 4367e83c70dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cl-mcp 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 2d 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Agent Guidelines

@prompts/repl-driven-development.md @prompts/common-lisp-expert.md

Project Overview

cl-mcp is a Model Context Protocol (MCP) server for Common Lisp, providing JSON-RPC 2.0 over stdio/TCP/HTTP. It exposes tools for REPL evaluation, file operations, code introspection, and structure-aware Lisp editing to AI agents.

Self-Hosted Development

This project is developed using its own MCP tools. When working on cl-mcp:

Lisp code operations (search, read, edit, eval): Use cl-mcp tools (clgrep-search, lisp-read-file, lisp-edit-form, repl-eval, etc.) per repl-driven-development.md
Shell commands: Only for git, mallet (linting), rove (test fallback), and user-requested commands
Package naming: Uses ASDF package-inferred-system — each file defines package cl-mcp/src/<name>. Add new files by updating cl-mcp.asd dependencies. Exports go in main.lisp

Testing & Linting

Run tests via run-tests tool with system name cl-mcp/tests/<name>-test:

;; Single test via repl-eval (fallback when package conflicts occur)
(rove:run-test 'cl-mcp/tests/integration-test::repl-eval-printlength)

Fallback (stale image / package conflicts): rove cl-mcp.asd from Bash for a clean process.

Pre-PR: (asdf:compile-system :cl-mcp :force :all) to catch warnings, then run full test suite. (:force t recompiles nothing here: cl-mcp is a package-inferred system, so the work is in the per-file subsystems that only :force :all reaches.)

Linting (required before commit; the same globs the Lint CI job runs, tests included):

mallet src/*.lisp src/*/*.lisp tests/*.lisp

Architecture

Protocol (src/protocol.lisp): JSON-RPC 2.0, MCP handshake (2025-06-18, 2025-03-26, 2024-11-05), tools dispatch Transports (src/tcp.lisp, src/http.lisp, src/run.lisp): Stdio, TCP (multi-threaded), HTTP (Streamable HTTP via Hunchentoot) Tools:

Category	Files	Purpose
REPL	`src/repl.lisp`	Form evaluation with package context, print controls, timeout
System Loader	`src/system-loader.lisp`	ASDF loading with force-reload, output suppression
File System	`src/fs.lisp`	Read/write/list with project root guardrails
Lisp Reading	`src/lisp-read-file.lisp`	Collapsed signatures, pattern-based expansion
Lisp Editing	`src/lisp-edit-form.lisp`	CST-based form replace/insert via Eclector
Lisp Patching	`src/lisp-patch-form.lisp`	Token-efficient sub-form text replacement
Code Intel	`src/code.lisp`	Symbol lookup, describe, xref via sb-introspect
Validation	`src/validate.lisp`, `src/parinfer.lisp`	Paren checking, auto-repair
Pool Mgmt	`src/tools/pool-status.lisp`, `src/tools/pool-kill-worker.lisp`	Worker diagnostics and lifecycle

Read the full file on GitHub · 85 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.

2d ago Changed · +2 lines · +65 tokens per session 4367e83c70dd
8d ago First seen · 83 lines · 1,020 tokens per session scan A a7fcbfa59ce0

Subscribe to this mod's changes

cl-mcp CLAUDE.md is an instructions file published in the GitHub repository cl-ai-project/cl-mcp (84 stars, last pushed 2d ago), licensed MIT. It adds 1,085 tokens to every session, about $0.0054 per session on Opus 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 2026-08-30.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

cl-mcp: Instructions file for Claude Code