mcp-servers: Instructions file for Codex

AGENTS.md

mcp-servers AGENTS.md is an instructions file for Codex, OpenCode from pulsemcp/mcp-servers. It costs 6,669 tokens per session, scanned C, original, MIT.

Repository instructions for working on PulseMCP's monorepo, a single repository containing multiple MCP servers and shared libraries.

In plain words
What is it for?
Use them when changing a production or experimental MCP server, following the repository's Git workflow, adding test coverage, or writing a pull-request description.
Why use it?
They explain the repository layout, contribution context, branch naming, testing expectations, and required pull-request format.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd ../local && npm install @modelcontextprotocol/sdk@^1.13.2 --save.

Reuse

Borrowing it

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

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-servers AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pulsemcp/mcp-servers/agents-md"><img src="https://agentmods.dev/badge/instructions/pulsemcp/mcp-servers/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,669 This file is loaded in full into every session.
When invoked 6,669 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.06669 $0.06669
Opus 5.5 $0.02668 $0.02668
Sonnet 5.5 $0.01334 $0.01334
Haiku 4.5 $0.00667 $0.00667

Measured 2mo ago against content hash 97e6e609722f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

mcp-servers AGENTS.md scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf node_modules
AGENTS.md · 521 lines

How it starts

The opening of the file, as written. The whole thing — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Also review CONTRIBUTING.md for context.

Repository Overview

This is a monorepo containing Model Context Protocol (MCP) servers built by PulseMCP. Each subfolder represents a standalone MCP server with its own functionality.

Repository Structure

  • productionized/: Directory for production-ready MCP servers
  • experimental/: Directory for experimental MCP servers in development
  • libs/mcp-server-template/: Template structure for creating new MCP servers

Git Workflow

  • Repository: https://github.com/pulsemcp/mcp-servers
  • Branch naming: <github-username>/<feature-description> (e.g., tadasant/fix-bug)
  • Main branch has CI/CD
  • Always include test coverage for changes
  • PRs should have concise titles and detailed descriptions using this format:

PR Description Format

This overrides the default Claude Code PR template. Do NOT use a ## Test plan section with unchecked checkboxes. Instead, use this format:

## Summary
<what changed and why>

## Verification
- [x] <what you actually did to verify this works>
- [x] <proof: concrete evidence it works — not just an assertion>

The ## Verification section documents how you closed the loop — what you actually did, not what should be done. Every checkbox must be checked before the PR is opened. If you can't verify something, explain why instead of leaving an unchecked box.

Proof: Show, Don't Tell

Every verification item should include proof — concrete evidence that the change works. "Tested it and it works" is NOT proof. A screenshot, a test output, or a confirmation receipt IS proof.

Proof types and when to use them:

  1. E2E test report — For backend/logic changes. Describe what you tested end-to-end and what happened. This is the most common type.
  2. Screenshot — For UI changes. UI changes MUST include screenshots. No exceptions.
  3. External confirmation — For tasks with external side effects (API calls, emails sent, deployments). Show the confirmation or response.

Read the full file on GitHub · 521 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 · 521 lines · 6,669 tokens per session scan C 97e6e609722f

Subscribe to this mod's changes

mcp-servers AGENTS.md is an instructions file published in the GitHub repository pulsemcp/mcp-servers (81 stars, last pushed 28d ago), licensed MIT. It adds 6,669 tokens to every session, about $0.0267 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

mcp-servers AGENTS.md compared with instructions from other repositories

mcp-servers AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-servers AGENTS.mdpulsemcp/mcp-serversInstructions file8128d agoMITC6,669Codex, OpenCode
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