What is claudecode-mcp AGENTS.md?

Repository instructions for AI agents and contributors working on claudecode-mcp, a stateless MCP server that wraps Claude’s command-line tool. They describe the project, commands, tests, formatting, and architecture.

Use them to install dependencies, build the server, run offline or live tests, check formatting, and understand how the MCP tools start Claude processes.

They give an agent the project context and expected checks, reducing mistakes when changing or testing the repository.

How trevoraspencer/claudecode-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to trevoraspencer/claudecode-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/trevoraspencer/claudecode-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/trevoraspencer/claudecode-mcp

Made for: Codex, OpenCode.

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/trevoraspencer/claudecode-mcp/agents-md.svg)](https://agentmods.dev/instructions/trevoraspencer/claudecode-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/trevoraspencer/claudecode-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/trevoraspencer/claudecode-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,618 This file is loaded in full into every session.

When invoked 1,618 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	$0.01618	$0.01618
Opus 5	$0.00809	$0.00809
Sonnet 5	$0.00324	$0.00324
Haiku 4.5	$0.00162	$0.00162

Measured 7d ago against content hash 8492e0d499d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claudecode-mcp AGENTS.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 7d 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.

AGENTS.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Canonical public guide for AI agents and contributors working in this repository.

Project purpose

claudecode-mcp is a stateless stdio MCP server that wraps the headless claude CLI. It exposes one-shot MCP tools for prompts, prompts with local file context, and schema-constrained structured output.

The server is intentionally narrow: every tool call spawns a fresh claude subprocess, uses the server process's current working directory, and avoids session tracking or resume behavior.

Core commands

npm install - install dependencies.
npm run build - compile TypeScript into dist/ and make dist/server.js executable.
npm test - run the offline test suite. The pretest hook builds first.
npm run test:live - run tests with CLAUDECODE_MCP_LIVE=1; requires a real authenticated claude CLI on PATH.
npm run format:check - check Prettier formatting for src/**/*.ts and test/**/*.mjs.
npm run format - format src/**/*.ts and test/**/*.mjs.

Single tests can be run with Node's test runner after building, for example:

npm run build
node --test --test-name-pattern='<regex>' test/<file>.test.mjs

CI expectations

GitHub Actions validates pushes and pull requests on Node 20 and 22. The required CI workflow runs:

npm ci
npm run format:check
npx tsc --noEmit -p tsconfig.json
npm run build
npm test
npm audit --omit=dev --audit-level=high (blocking)
npm audit --audit-level=high (advisory for development-only transitives)

Manual compatibility coverage can be run on demand. Release validation follows the required checks on Node 20 and 22 and also runs npm pack --dry-run.

Architecture map

src/server.ts - MCP server wiring, tool schemas, request dispatch, baseClaudeArgs(), and compatibility exports used by tests.
src/invoke.ts - child process spawning, explicit environment allowlist, timeout and output caps, JSON parsing, and structured debug logging.
src/path-guard.ts - path containment and file reads for claude_prompt_with_context.
src/validators.ts - MCP tool input validation and lightweight schema sanity checks.
src/redaction.ts - secret redaction, client-safe error formatting, and Claude exit error classification.
src/flag-probe.ts - lazy claude --help probing for --json-schema support, with a short per-binary cache.
src/env.ts - shared environment-variable parsing helpers.

Read the full file on GitHub · 145 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.

7d ago First seen · 145 lines · 1,618 tokens per session scan A 8492e0d499d9

Subscribe to this mod's changes

claudecode-mcp AGENTS.md is an instructions file published in the GitHub repository trevoraspencer/claudecode-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,618 tokens to every session, about $0.0081 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 2026-08-31.

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 · 5,182 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

claudecode-mcp: Instructions file for Codex