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 skills add kenn-io/roborev --skill roborev-respondgit 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/skills/kenn-io/roborev/roborev-respond)<a href="https://agentmods.dev/skills/kenn-io/roborev/roborev-respond"><img src="https://agentmods.dev/badge/skills/kenn-io/roborev/roborev-respond.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00019 | $0.00859 |
| Opus 5 | $0.00010 | $0.00430 |
| Sonnet 5 | $0.00004 | $0.00172 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade A, and why
roborev-respond 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 8d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
roborev-respond
Record a comment on a roborev code review and close it.
Usage
/roborev-respond <job_id> [message]
Explicit invocation only
Invocation must be explicit: literal personal /roborev-respond, or structured
Claude Code skill selection.
Requests such as “respond to this review” without one of these explicit mechanisms must use
native behavior and must not run roborev.
Sandbox access
roborev uses a local daemon. If a command fails with permission denied, the sandbox may be
blocking access to its loopback port or Unix socket. Retry the same Bash command with
dangerouslyDisableSandbox: true. Do not start or restart the daemon because a
sandboxed status probe cannot reach it.
IMPORTANT
This skill requires you to execute bash commands to record the comment and close the review. The task is not complete until you run both commands and see confirmation output.
These instructions are guidelines, not a rigid script. Use the conversation context. Skip steps that are already satisfied. Defer to project-level CLAUDE.md instructions when they conflict with these steps.
Instructions
When the user invokes /roborev-respond <job_id> [message]:
1. Validate input
If no job_id is provided, inform the user that a job ID is required. Suggest roborev status or roborev fix --list to find job IDs. Discovery surfaces synthesis parents (and non-panel reviews), never individual panel members, so the job ID you comment on and close is the parent.
If a job_id is provided, inspect it before closing:
roborev show --job <job_id> --json
If job.panel_role is "member", do not comment on or close that job.
Resolve the synthesis parent for the same job.panel_run_uuid if it is already
known from the conversation or discovery output; otherwise ask the user for the
synthesis parent ID. Only continue once the resolved job ID is a synthesis
parent or a non-panel review.
2. Record the comment and close the review
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.
- 8d ago First seen · 111 lines · 19 tokens per session scan A 3a3380317a47
roborev-respond is a skill published in the GitHub repository kenn-io/roborev (1,692 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 859 once invoked, about $0.0001 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…