mcp-github-projects: Instructions file for Codex

AGENTS.md

mcp-github-projects AGENTS.md is an instructions file for Codex, OpenCode from jersonmartinez/mcp-github-projects. It costs 2,691 tokens per session, scanned A, original, MIT.

A set of AGENTS.md instructions for working on an MCP server that manages GitHub Projects V2. AGENTS.md is a repository guide that tells coding agents and developers how to build, test, and change the project.

In plain words
What is it for?
It helps with repository orientation, Docker-based builds and tests, and adding tools that manage GitHub project boards, issues, milestones, labels, and related work.
Why use it?
It gives one source of truth for project rules, avoiding conflicting instructions in different agent configuration files. It also documents that the project must be built and tested with Docker.

Instructions file for CodexOpenCode

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

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

Reuse

Borrowing it

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

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-github-projects AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jersonmartinez/mcp-github-projects/agents-md"><img src="https://agentmods.dev/badge/instructions/jersonmartinez/mcp-github-projects/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,691 This file is loaded in full into every session.
When invoked 2,691 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 $0.02691 $0.02691
Opus 5.5 $0.01076 $0.01076
Sonnet 5 $0.00538 $0.00538
Haiku 4.5 $0.00269 $0.00269

Measured today against content hash c3f97d0159d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-28, from the pricing page.

Security

Grade A, and why

mcp-github-projects 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 today.

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 · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Vendor-neutral guide for AI coding agents (and humans) working in this repository. This file is the single source of truth for how to build, test, extend, and contribute to the project. If an MCP client needs its own pointer file (for example .cursor/rules/*.mdc or .github/copilot-instructions.md), it must only point here — when they disagree, AGENTS.md wins. This repository intentionally does not create or maintain CLAUDE.md.


1. Project Overview

This repository is a Model Context Protocol (MCP) server for GitHub Projects V2. It exposes 100+ tools for managing issues, project-board fields, milestones, labels, sub-issues, sprints, epics, and PR/issue lifecycle automation. It is built on FastMCP, communicates over the stdio transport, and runs as a Docker container.

  • Language: Python 3.12+, fully type-hinted.
  • Transport: FastMCP over stdio (server.py → mcp.run(transport="stdio")).
  • Data access: GitHub GraphQL API v4 (Projects V2) with a gh CLI fallback for REST-only operations.
  • Runtime: Docker only — there are no supported host-Python workflows.
  • Maintainership: single maintainer, public OSS (MIT).

2. Flat Repository Layout

The project uses a flat package layout (no nested src/ or vendor prefix). Imports are top-level (from tools.close import close_issue, from models.responses import ToolSuccess).

.
├── server.py            # FastMCP entry point; registers every tool
├── config.py            # Settings (env-driven): org/repo/project, timeouts, scopes
├── auth.py              # Token resolution + scope validation
├── capabilities.py      # Capability enum + profile capability enforcement
├── profiles.py          # Multi-target profile registry (user vs org projects)
├── error_handling.py    # build_error_response(), handle_tool_error()
├── exceptions.py        # Typed exceptions
├── hardening.py         # Input/rate-limit hardening helpers
├── tools/               # One module per tool (or tool family) — see §4
│   ├── __init__.py      # Re-exports the core tool subset
│   ├── comment_issue.py # Canonical single-tool example
│   ├── capability_suite.py  # Extended 60-tool suite (dynamic registration)
│   └── ...
├── services/            # Domain services (issue_service, project_service, ...)
├── clients/             # graphql_client, gh_cli_client, cache_manager
├── graphql/             # queries.py, mutations.py (GraphQL documents)
├── models/              # Pydantic models — responses.py, context.py, items.py
├── scripts/             # Docker-invoked CI/validation scripts (Python + bash)
├── tests/               # pytest suite
├── docs/                # SETUP, USAGE, PARAMETERS, CAPABILITIES, TROUBLESHOOTING
├── compose.yaml         # Single `mcp` service
├── Dockerfile
└── Makefile             # The ONLY supported command surface (Docker-backed)

Read the full file on GitHub · 263 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. today Changed · +2 lines · +36 tokens per session c3f97d0159d3
  2. 2d ago First seen · 261 lines · 2,655 tokens per session scan A dcbda28fe6bc

Subscribe to this mod's changes

mcp-github-projects AGENTS.md is an instructions file published in the GitHub repository jersonmartinez/mcp-github-projects (0 stars, last pushed today), licensed MIT. It adds 2,691 tokens to every session, about $0.0108 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 2026-09-25.

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 · 9,406 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 · 6,985 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 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

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 · 3,980 tokens