Borrowing it
Nothing to install: this file belongs to JigeeshaJain/ReviewQueueMcp. 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/JigeeshaJain/ReviewQueueMcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/JigeeshaJain/ReviewQueueMcpWrote 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/jigeeshajain/reviewqueuemcp/claude-md)<a href="https://agentmods.dev/instructions/jigeeshajain/reviewqueuemcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jigeeshajain/reviewqueuemcp/claude-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/jigeeshajain/reviewqueuemcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jigeeshajain/reviewqueuemcp/claude-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 | $0.02129 | $0.02129 |
| Opus 5 | $0.01064 | $0.01064 |
| Sonnet 5 | $0.00426 | $0.00426 |
| Haiku 4.5 | $0.00213 | $0.00213 |
Grade A, and why
ReviewQueueMcp CLAUDE.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 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.
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 — 171 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.
Project Overview
gh-review-queue-mcp is an MCP server that exposes exactly one tool,
get_review_queue: a ranked, deduped view of the viewer's GitHub pull request review
queue. Resisting the urge to add a second tool is a design constraint, not an oversight.
Commands
Dependencies are managed with uv against uv.lock. uv run syncs automatically, so
there is no separate install step.
uv run pytest # all tests
uv run pytest tests/test_queue.py::test_diff_size_sums_both_sides # one test
uv run pytest -k "rank or score" # by name
uv run ruff check . # lint
uv run ruff format . # format
uv run mypy # typecheck
mypy takes its targets from [tool.mypy] files in pyproject.toml, so run it bare —
passing a path checks less than CI would. It runs strict, and tests/ is exempted only
from disallow_untyped_defs. Ruff's ignore list drops ANN for tests/* and scripts/*.
asyncio_mode = "auto", so async tests need no decorator.
Architecture
Four layers, and the boundaries are the point:
models.py— frozen pydantic value objects (PullRequest,QueueItem,QueueSnapshot,Reason). No network types live here.PullRequest.from_node()is the only place GitHub's nested GraphQL shape gets flattened.queue.py— the entire ranking pipeline as pure functions:merge→apply_filters→rank/score, composed bybuild_queue. It takes aQueueSnapshotand a clock, nothing else, which is why its tests need no mocks. Never let anhttpximport reach this module.github.py— the only module that touches the network. Builds the GraphQL, handles HTTP and GraphQL errors, returns domain objects. It must never rank or filter.server.py— a thin MCP adapter: parse arguments, call the client, hand off to the domain layer, serialize. Its own docstring sets a ~120-line budget; exceeding it means logic leaked into the wrong layer.
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 · 171 lines · 2,129 tokens per session scan A 47f12127c4eb
ReviewQueueMcp CLAUDE.md is an instructions file published in the GitHub repository JigeeshaJain/ReviewQueueMcp (1 stars, last pushed 16d ago), licensed Apache-2.0. It adds 2,129 tokens to every session, about $0.0106 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.
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.