Borrowing it
Nothing to install: this file belongs to thebtf/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.
curl -O https://raw.githubusercontent.com/thebtf/pr-review-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/thebtf/pr-review-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/thebtf/pr-review-mcp/agents-md)<a href="https://agentmods.dev/instructions/thebtf/pr-review-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/thebtf/pr-review-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.02891 | $0.02891 |
| Opus 5 | $0.01445 | $0.01445 |
| Sonnet 5 | $0.00578 | $0.00578 |
| Haiku 4.5 | $0.00289 | $0.00289 |
Grade A, and why
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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — PR Review MCP Server
PURPOSE
Plugin-first MCP package for orchestrating AI-driven PR reviews with 7 agent sources, 20 tools, and parallel multi-agent coordination.
Features:
- GraphQL-based GitHub integration with cursor pagination
- Multi-source comment detection and severity extraction
- AI prompt extraction from review comments
- Agent invocation + server-side review await (
pr_invoke→pr_await_reviews) - Parallel worker orchestration for comment processing
- Built-in prompt/command wrappers (
/pr:review,/pr:review-background,/pr:setup) - Built-in background
pr-revieweragent and canonicalpr-reviewskill
LANGUAGE
- Communication with user: RUSSIAN
- Code, commits, docs: ENGLISH
PROJECT STRUCTURE
pr-review-mcp/
├── src/
│ ├── server.ts # MCP server entry point
│ ├── logging.ts # MCP logging utility
│ ├── index.ts # CLI entry point
│ ├── session/
│ │ ├── types.ts # MuxMeta, MuxSessionContext interfaces
│ │ ├── meta.ts # extractMuxMeta() from extra._meta
│ │ ├── context.ts # createSessionContext() factory
│ │ └── manager.ts # MuxSessionManager (per-session state)
│ ├── github/
│ │ ├── client.ts # GitHub GraphQL/REST client
│ │ ├── octokit.ts # Octokit instance management
│ │ ├── queries.ts # GraphQL queries
│ │ ├── types.ts # TypeScript types
│ │ └── state-comment.ts # State comment persistence
│ ├── git/
│ │ └── detect.ts # Git repo/branch detection
│ ├── tools/
│ │ ├── summary.ts # pr_summary
│ │ ├── list.ts # pr_list
│ │ ├── list-prs.ts # pr_list_prs
│ │ ├── get.ts # pr_get
│ │ ├── changes.ts # pr_changes
│ │ ├── poll.ts # pr_poll_updates
│ │ ├── await-reviews.ts # pr_await_reviews
│ │ ├── invoke.ts # pr_invoke
│ │ ├── resolve.ts # pr_resolve
│ │ ├── labels.ts # pr_labels
│ │ ├── reviewers.ts # pr_reviewers
│ │ ├── create.ts # pr_create
│ │ ├── merge.ts # pr_merge
│ │ ├── coordination.ts # pr_claim_work, pr_report_progress, etc.
│ │ ├── sessions.ts # pr_sessions
│ │ ├── cancel.ts # pr_cancel
│ │ ├── wait-state.ts # WaitState classification (shared)
│ │ └── shared.ts # Shared utilities
│ ├── persistence/
│ │ ├── database.ts # SQLite database init (openDatabase)
│ │ ├── invocation-store.ts # InvocationStore (CRUD + gc + reap)
│ │ └── types.ts # StoredInvocation, StoredAgentStatus
│ ├── adapters/
│ │ ├── qodo.ts # Qodo issue comment adapter
│ │ └── greptile.ts # Greptile issue comment adapter
│ ├── agents/
│ │ ├── registry.ts # Agent configs + CompletionStrategy
│ │ ├── completion-detector.ts # Unified completion detection engine
│ │ ├── invoker.ts # Agent invocation logic
│ │ └── detector.ts # Smart detection (delegates to completion-detector)
│ ├── extractors/
│ │ ├── severity.ts # Severity extraction
│ │ ├── prompt.ts # AI prompt extraction
│ │ ├── coderabbit-nitpicks.ts
│ │ └── multi-issue.ts # Multi-issue splitting
│ ├── prompts/
│ │ ├── review.ts # Review orchestrator prompt
│ │ └── setup.ts # Setup wizard prompt
│ ├── resources/
│ │ └── pr.ts # PR resource (pr://{owner}/{repo}/{pr})
│ └── coordination/
│ ├── state.ts # In-memory coordination state (CoordinationStateManager)
│ ├── sqlite-state.ts # SQLite-backed coordination state
│ └── types.ts # Coordination types
├── agents/
│ └── pr-reviewer.md # Built-in background PR reviewer agent
├── skills/
│ ├── review/
│ │ └── SKILL.md # MCP-prompt-oriented review skill
│ └── pr-review/
│ └── SKILL.md # Canonical consumer-facing PR review skill
├── commands/
│ ├── review.md # Prompt wrapper for /pr:review
│ ├── review-background.md # Prompt wrapper for /pr:review-background
│ └── setup.md # Prompt wrapper for /pr:setup
└── dist/ # Compiled output
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.
- 7d ago First seen · 266 lines · 2,891 tokens per session scan A 4c7792aa3022
pr-review-mcp AGENTS.md is an instructions file published in the GitHub repository thebtf/pr-review-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 2,891 tokens to every session, about $0.0145 per session on Opus 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.
Other instructions, from other repositories
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).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.