roborev is a background code-review system for AI coding agents that checks each Git commit and records findings in a review database. It helps developers catch issues in generated code while they work. Catalogue add-ons connect its findings to agent workflows and can support iterative review and fixing.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/kenn-io/roborev/claude-mdgit clone --depth 1 https://github.com/kenn-io/roborevWrote 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/kenn-io/roborev/claude-md)<a href="https://agentmods.dev/instructions/kenn-io/roborev/claude-md"><img src="https://agentmods.dev/badge/instructions/kenn-io/roborev/claude-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 | $0.05444 | $0.05444 |
| Opus 5 | $0.02722 | $0.02722 |
| Sonnet 5 | $0.01089 | $0.01089 |
| Haiku 4.5 | $0.00544 | $0.00544 |
Grade A, and why
roborev 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 5d 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 — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
roborev is an automatic code review daemon for git commits. It runs locally, triggered by post-commit hooks, and uses AI agents (Codex, Claude Code, Gemini, Copilot, etc.) to review commits in parallel. It also supports background fix jobs, CI integration via GitHub PRs, and PostgreSQL sync for multi-machine setups.
General Workflow
When a task involves multiple steps (e.g., implement + commit + PR), complete ALL steps in sequence without stopping. If creating a branch, committing, and opening a PR, finish the entire chain.
Handling review findings
When the user pastes review findings directly in the conversation (verdicts, severities, file paths, suggested fixes), treat them as direct instructions and fix the code normally. Do NOT invoke the /roborev-fix skill — that skill is only for discovering and fetching open reviews from the daemon, not for processing findings already present in the prompt.
Go Development
After making any Go code changes, always run go fmt ./... and go vet ./... before committing. Stage ALL resulting changes, including formatting-only files.
Git Workflow
Always commit after completing each piece of work — do not wait to be asked. When committing changes, always stage ALL modified files (including formatting, generated files, and ancillary changes). Run git diff and git status before committing to ensure nothing is left unstaged.
Architecture
CLI (roborev) → HTTP API → Daemon (roborev daemon run) → Worker Pool → Agents
↓ ↓
SQLite DB ←──sync──→ PostgreSQL (optional)
↓
CI Poller → GitHub PRs
- Daemon: HTTP server on port 7373 (auto-finds available port if busy)
- Workers: Pool of 4 (configurable) parallel review workers
- Storage: SQLite at
~/.roborev/reviews.dbwith WAL mode - Config: Global at
~/.roborev/config.toml, per-repo at.roborev.toml - Data dir: Set
ROBOREV_DATA_DIRenv var to override~/.roborev - Color mode:
ROBOREV_COLOR_MODE=auto|dark|light|nonecontrols TUI color theme;NO_COLOR=1strips all colors - Runtime info: Daemon writes PID/addr/version to
~/.roborev/runtime/daemon.<pid>.json(kit runtime store); pre-v0.57 daemons wrote~/.roborev/daemon.json, still read for upgrade-time stop/cleanup
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.
- 5d ago First seen · 405 lines · 5,444 tokens per session scan A a68cc837ba7b
roborev CLAUDE.md is an instructions file published in the GitHub repository kenn-io/roborev (1,691 stars, last pushed today), licensed MIT. It adds 5,444 tokens to every session, about $0.0272 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 2026-08-30.
Other instructions, from other repositories
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.
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 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.