mcp-debugger: Instructions file for Codex

AGENTS.md

mcp-debugger AGENTS.md is an instructions file for Codex, OpenCode from debugmcp/mcp-debugger. It costs 1,479 tokens per session, scanned A, original, MIT.

Repository instructions for a TypeScript debugging server and its related packages. The project is a monorepo, meaning one repository contains several connected packages, each with its own source code.

In plain words
What is it for?
Working on debugger adapters, building packages, running development mode, executing targeted tests, and running the full test suite.
Why use it?
They explain the package layout and the commands needed to install, build, develop, and test the whole project or selected parts.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is debugmcp/mcp-debugger's own configuration. It tells Codex and OpenCode how to work on mcp-debugger 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 mcp-debugger configures →

Reuse

Borrowing it

Nothing to install: this file belongs to debugmcp/mcp-debugger. 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/debugmcp/mcp-debugger/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/debugmcp/mcp-debugger

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.

agentmods badge for mcp-debugger AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/debugmcp/mcp-debugger/agents-md/github.svg)](https://agentmods.dev/instructions/debugmcp/mcp-debugger/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/debugmcp/mcp-debugger/agents-md"><img src="https://agentmods.dev/badge/instructions/debugmcp/mcp-debugger/agents-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 mcp-debugger AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/debugmcp/mcp-debugger/agents-md"><img src="https://agentmods.dev/badge/instructions/debugmcp/mcp-debugger/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,479 This file is loaded in full into every session.
When invoked 1,479 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 $0.01479 $0.01479
Opus 5.5 $0.00592 $0.00592
Sonnet 5.5 $0.00296 $0.00296
Haiku 4.5 $0.00148 $0.00148

Measured 15d ago against content hash 8fd0d2d9dcfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-debugger 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 15d 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 · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

  • src/ contains the TypeScript CLI and server core that power the Debug MCP runtime.
  • packages/ hosts 19 workspace modules. Fourteen carry their own src/ trees (@debugmcp/shared, adapter-mock, adapter-python, adapter-ruby, adapter-javascript, adapter-rust, adapter-go, adapter-java, adapter-dotnet, adapter-cpp, adapter-cobol, adapter-dart, codelldb-common, mcp-debugger); the other five — codelldb-win32-x64, codelldb-linux-x64, codelldb-linux-arm64, codelldb-darwin-x64, codelldb-darwin-arm64 — are prebuilt CodeLLDB payloads with no TypeScript in them. A packages/logs/ may linger in a checkout that ran pre-#637 builds (server logs now default to os.tmpdir()/debug-mcp-server/); it is not a package and not in the repository — .gitignore's logs/ rule covers it.
  • tests/ is grouped by scope: unit/, core/unit/, adapters/*/, integration/, e2e/, plus shared utilities in tests/test-utils/ and fixtures under tests/fixtures/.
  • docs/ covers design notes; examples/ hosts adapter recipes; scripts/ stores CI helpers.
  • Build artifacts land in dist/; recorded assets and Docker helpers live in assets/ and docker/.

Build, Test, and Development Commands

  • pnpm install sets up the monorepo (respect the generated pnpm-lock.yaml).
  • pnpm build compiles every package and emits the aggregated dist/index.js.
  • pnpm dev launches the TypeScript entry point via ts-node for quick feedback.
  • pnpm test performs a full build, ensures Docker images are ready, and runs Vitest across all suites.
  • Targeted runs: pnpm test:unit, pnpm test:integration, pnpm test:e2e, pnpm test:coverage.
  • pnpm lint runs ESLint over src/**/*.ts, packages/*/src/**/*.ts, scripts/**/*.{js,mjs,cjs}, and tools/**/*.{js,mjs,cjs} (the dev-proxy supervisor is production tooling; experimental probes go in scripts/experiments/, which is ignored). pnpm lint:fix runs the same globs with --fix.
  • pnpm typecheck type-checks the shipped sources via tsconfig.typecheck.json (no build needed; the root tsc -p tsconfig.json checks nothing). pnpm typecheck:tests runs the per-file ratchet over the test trees against tests/typecheck-baseline.json; pnpm typecheck:tests:update re-records that baseline and pnpm typecheck:tests:raw emits unfiltered tsc output. pnpm typecheck:all runs both, and is the exact command pre-push and CI run.
  • Run the whole dev-loop gate before pushing. It is lint -> baseline committed -> typecheck:all -> clean build -> test:unit + test:integration, and both .husky/pre-push and CI enforce it; typecheck:all is the step most likely to block a push. It is documented once, canonically, in CONTRIBUTING.md — Dev-Loop Gate. Follow that section rather than any restatement of it.

Read the full file on GitHub · 37 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. 15d ago Changed · +5 tokens per session 8fd0d2d9dcfa
  2. 1mo ago Changed · +7 tokens per session 71b347d3c16c
  3. 1mo ago Changed · -5 tokens per session 70f5bac9a365
  4. 1mo ago Changed · +2 lines · +681 tokens per session 50acd31317af
  5. 1mo ago First seen · 35 lines · 791 tokens per session scan A 31594ba8c7f6

Subscribe to this mod's changes

mcp-debugger AGENTS.md is an instructions file published in the GitHub repository debugmcp/mcp-debugger (180 stars, last pushed today), licensed MIT. It adds 1,479 tokens to every session, about $0.0059 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 2026-08-30.

Related

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).

microsoft/vscode · 9,715 tokens

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 · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens