Borrowing it
Nothing to install: this file belongs to rdlugs/roborak. 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/rdlugs/roborak/main/CLAUDE.mdgit clone --depth 1 https://github.com/rdlugs/roborakWrote 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/rdlugs/roborak/claude-md)<a href="https://agentmods.dev/instructions/rdlugs/roborak/claude-md"><img src="https://agentmods.dev/badge/instructions/rdlugs/roborak/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/rdlugs/roborak/claude-md"><img src="https://agentmods.dev/badge/instructions/rdlugs/roborak/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 | $0.02420 | $0.02420 |
| Opus 5 | $0.01210 | $0.01210 |
| Sonnet 5 | $0.00484 | $0.00484 |
| Haiku 4.5 | $0.00242 | $0.00242 |
Grade A, and why
roborak 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 2d 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 — 147 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.
What this is
roborak (CLI aliases roborak and rk) is an AI code-review tool: it turns a local diff,
a GitLab MR, a GitHub PR or a raw directory into severity-graded, line-anchored findings, and
optionally publishes them back to the forge. Python 3.12+, packaged with uv, Typer CLI,
Pydantic models, LiteLLM for any model provider.
AGENTS.md points other agents here, and CONTRIBUTING.md is the human-facing companion.
roborak reads the first of AGENTS.md, CLAUDE.md, .roborak/context.md, CONTRIBUTING.md
it finds as repository context, so keep the three in step when conventions change.
Commands
uv sync --dev # set up; there is no venv to activate, everything is `uv run`
# The checks. These are exactly what CI runs, on 3 OSes x Python 3.12/3.13/3.14.
uv run ruff check src tests evals .github/scripts
uv run ruff format src tests evals .github/scripts # CI runs --check; format before committing
uv run mypy src
uv run pytest --cov=src/roborak --cov-fail-under=90 # coverage gate is 90%
uv build
uv run pytest tests/test_render.py # one file
uv run pytest tests/test_render.py::test_name # one test
uv run pytest -k anchor # by name
uv run roborak review --no-llm # exercise the whole pipeline with no API key (static only)
uv run roborak review --base main # dogfood on your own branch before asking for review
uv run python evals/run.py # 30 labeled cases; real model calls, out of PR CI, run nightly
Docs site (docs/, Vite + React Router + Tailwind, Node 20+):
cd docs && npm ci && npm run dev | npm run typecheck | npm run build | npm run serve.
Architecture
One directional pipeline; each stage only knows the stage before it.
Source → ChangeSet → Compressor → Static/supply/verify passes → LLM → Investigate → Validator →
Renderer → Publisher
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.
- 2d ago Changed · +2 lines · +46 tokens per session 2ff1cc4df7b1
- 5d ago Changed · +30 lines · +627 tokens per session f279e2912a91
- 7d ago First seen · 115 lines · 1,747 tokens per session scan A 46051a4fe1e7
roborak CLAUDE.md is an instructions file published in the GitHub repository rdlugs/roborak (2 stars, last pushed 3d ago), licensed MIT. It adds 2,420 tokens to every session, about $0.0121 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 2026-09-05.
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).
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.
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.
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).