Borrowing it
Nothing to install: this file belongs to mhaviv/pr-narrator-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.
curl -O https://raw.githubusercontent.com/mhaviv/pr-narrator-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/mhaviv/pr-narrator-mcpWrote 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.
[](https://agentmods.dev/instructions/mhaviv/pr-narrator-mcp/agents-md)<a href="https://agentmods.dev/instructions/mhaviv/pr-narrator-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mhaviv/pr-narrator-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.
<a href="https://agentmods.dev/instructions/mhaviv/pr-narrator-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mhaviv/pr-narrator-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02472 | $0.02472 |
| Opus 5 | $0.01236 | $0.01236 |
| Sonnet 5 | $0.00494 | $0.00494 |
| Haiku 4.5 | $0.00247 | $0.00247 |
Grade A, and why
pr-narrator-mcp AGENTS.md scanned grade A 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 9d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **No shell exec**: All git operations use `simple-git` — never `child_process` or `exec`. How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Coding Agent Instructions for pr-narrator-mcp
Project Summary
pr-narrator-mcp is an MCP (Model Context Protocol) server that generates commit messages, PR titles, PR descriptions, and related content from git repository state. It is published to npm as pr-narrator-mcp and runs as a CLI tool via npx pr-narrator-mcp.
- Runtime: Node.js >=18, TypeScript 5.3+, ESM (
"type": "module") - Dependencies:
@modelcontextprotocol/sdk^1.26.0,simple-git^3.22.0,zod^3.22.4 - Build: tsup (ESM output, single entry
src/index.ts, target node18) - Test: Vitest with globals, v8 coverage, Node environment
- Lint: ESLint with
@typescript-eslint/recommended-requiring-type-checking+ Prettier - CI: GitHub Actions on Node 18/20/22 matrix
Build & Test Commands
npm install # Install dependencies
npm run typecheck # tsc --noEmit (run FIRST — must pass before test/build)
npm run test:run # vitest run (single pass)
npm test # vitest (watch mode)
npm run test:coverage # vitest with v8 coverage
npm run build # tsup → dist/
npm run lint # eslint src/ test/
npm run lint:fix # eslint --fix
npm run format # prettier --write
npm run format:check # prettier --check
Validation order: npm run typecheck → npm run test:run → npm run build → npm run lint
CI runs this matrix on Node 18, 20, and 22. Always verify your changes pass on Node 18 (the minimum).
Project Layout
src/
├── index.ts # MCP server entry, tool registration, stdio transport
├── config/
│ ├── schema.ts # Zod config schemas, defaults, type exports
│ └── loader.ts # Config loading from MCP env vars
├── tools/ # One file per MCP tool (10 tools total)
│ ├── get-config.ts
│ ├── analyze-git-changes.ts
│ ├── generate-commit-message.ts
│ ├── validate-commit-message.ts
│ ├── extract-tickets.ts
│ ├── generate-pr-title.ts
│ ├── generate-pr-description.ts
│ ├── generate-pr.ts
│ ├── get-pr-template.ts
│ └── generate-changelog.ts
└── utils/
├── git.ts # Git operations via simple-git, path validation, branch detection
└── formatters.ts # String formatting, prefix handling, file categorization
test/ # Mirrors src/ structure
├── config/
│ └── loader.test.ts
├── tools/
│ └── *.test.ts # One test file per tool
└── utils/
├── formatters.test.ts
└── git.test.ts
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.
- 9d ago First seen · 237 lines · 2,472 tokens per session scan A 0065d1d781f7
pr-narrator-mcp AGENTS.md is an instructions file published in the GitHub repository mhaviv/pr-narrator-mcp (1 stars, last pushed 6mo ago), licensed MIT. It adds 2,472 tokens to every session, about $0.0124 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
skill-doctor git-workflow.instructions.md
Instructions for evilstar2016/skill-doctor, covering git-workflow, description, when to use and instructions.
skill-doctor github-automation.instructions.md
Instructions for evilstar2016/skill-doctor, covering github-automation, description, when to use and instructions.
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.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).