github-pr-review-mcp: Instructions file for Codex

AGENTS.md

github-pr-review-mcp AGENTS.md is an instructions file for Codex, OpenCode from jamesjfoong/github-pr-review-mcp. It costs 419 tokens per session, scanned A, original, MIT.

A set of project instructions for building a GitHub pull-request review server. It explains where code belongs, how tools are added, and which coding rules to follow.

In plain words
What is it for?
Use it when adding or changing review tools, GitHub API calls, data schemas, or static-analysis code in this TypeScript project.
Why use it?
It gives coding agents a shared guide to the project, reducing inconsistent changes and repeated questions about structure and style.

Instructions file for CodexOpenCode

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

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

Reuse

Borrowing it

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

agentmods badge for github-pr-review-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jamesjfoong/github-pr-review-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jamesjfoong/github-pr-review-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 419 This file is loaded in full into every session.
When invoked 419 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 $0.00419 $0.00419
Opus 5.5 $0.00168 $0.00168
Sonnet 5.5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured 2mo ago against content hash f3e78934e20f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-pr-review-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 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.

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 · 59 lines

What it actually says

GitHub PR Review MCP - Agent Instructions

MCP server providing GitHub PR review capabilities. Built with TypeScript, FastMCP, and GitHub API.

Quick Reference

File Purpose
src/index.ts Register MCP tools
src/github-service.ts GitHub API calls (use this.octokit)
src/code-analyzer.ts Static analysis (pure functions)
src/types.ts Zod schemas + TypeScript types

Core Rules

  • All GitHub API calls go through GitHubService
  • All tool parameters need Zod schemas in types.ts
  • Strong typing - avoid any, use explicit interface or type definitions
  • Use ? for optional - don't use | null | undefined, use ? instead
  • Run npm run validate before committing

Adding Tools (3 Steps)

  1. Schema in types.ts
  2. Service method in github-service.ts
  3. Register in index.ts

Code Style

  • 2 spaces, double quotes, semicolons
  • kebab-case files, PascalCase classes, camelCase functions
  • 80 char max line length

Commands

npm run validate  # Type-check + lint + format
npm run dev       # Development mode
npm run build     # Production build

Error Handling

try {
  const result = await this.octokit.pulls.get({...});
  return result.data;
} catch (error) {
  const message = error instanceof Error ? error.message : String(error);
  console.error("Error fetching PR:", message);
  throw new Error(`Failed to fetch PR: ${message}`);
}

Documentation

  • README.md - Update tool table when adding tools
  • README.md - Full project documentation
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 · 59 lines · 419 tokens per session scan A f3e78934e20f

Subscribe to this mod's changes

github-pr-review-mcp AGENTS.md is an instructions file published in the GitHub repository jamesjfoong/github-pr-review-mcp (1 stars, last pushed 9mo ago), licensed MIT. It adds 419 tokens to every session, about $0.0017 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 2026-08-31.

Related

github-pr-review-mcp AGENTS.md compared with instructions from other repositories

github-pr-review-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
github-pr-review-mcp AGENTS.mdjamesjfoong/github-pr-review-mcpInstructions file19mo agoMITA419Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, 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