roborev-refine

roborev-refine is a skill for Claude Code from kenn-io/roborev. It costs 19 tokens per session (2,421 once invoked), scanned A, original, MIT.

An iterative code-review workflow that reviews a branch or commit range, fixes the findings, and reviews the changes again. A commit range is a selected set of changes in a version-control history.

In plain words
What is it for?
It is for repeatedly reviewing and repairing code changes until reviews pass or the allowed number of cycles is reached.
Why use it?
It closes the loop between finding problems and checking the fixes, reducing the chance that review issues remain unresolved.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; mentions Claude Code.

Part of the roborev plugin — 10 skills shipped together

Good fit It is for repeatedly reviewing and repairing code changes until reviews pass or the allowed number of cycles is reached.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kenn-io/roborev/roborev-refine
About the project

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.

kenn-io/roborev · 1,692 stars · on GitHub · roborev.io

Install

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.

Any agent
npx skills add kenn-io/roborev --skill roborev-refine
Clone the repo
git clone --depth 1 https://github.com/kenn-io/roborev

Made for: Claude Code.

Or install roborev, the plugin that ships this one along with the rest of its 10 skills.

Wrote 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.

agentmods badge for roborev-refine

README.md
[![agentmods](https://agentmods.dev/badge/skills/kenn-io/roborev/roborev-refine.svg)](https://agentmods.dev/skills/kenn-io/roborev/roborev-refine)
Your own site
<a href="https://agentmods.dev/skills/kenn-io/roborev/roborev-refine"><img src="https://agentmods.dev/badge/skills/kenn-io/roborev/roborev-refine.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,421 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.02421
Opus 5 $0.00010 $0.01210
Sonnet 5 $0.00004 $0.00484
Haiku 4.5 $0.00002 $0.00242

Measured 8d ago against content hash b0904b7bc48b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

roborev-refine 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.

internal/skills/claude/roborev-refine/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

roborev-refine

Iterative review-fix loop: review the current branch or commit range, fix findings, commit, re-review, and repeat until all reviews pass or the iteration limit is reached.

Unlike /roborev-fix (single-pass fix without re-review), refine closes the loop by re-reviewing after each fix to verify the findings are resolved.

This skill should perform the refine workflow inside the current coding agent CLI. Do not simply shell out to roborev refine.

Usage

/roborev-refine [--since <commit>] [--branch <name>] [--max-iterations <n>]

Explicit invocation only

Invocation must be explicit: literal personal /roborev-refine, or structured Claude Code skill selection. Requests such as “refine this change” without one of these explicit mechanisms must use native behavior and must not run roborev.

  • --since <commit>: refine commits after this commit (exclusive); required on the default branch
  • --branch <name>: validate that the current branch matches before refining
  • --max-iterations <n>: maximum fix-review cycles (default: 10)

This skill intentionally focuses on the current branch flow. It does not expose roborev refine --all-branches or roborev refine --list.

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.

When NOT to invoke this skill

Do NOT invoke this skill when the user is presenting or pasting existing review results, or when they only want a single review without fixing. Use /roborev-review-branch for review-only and /roborev-fix for fix-only.

IMPORTANT

This skill requires you to execute bash commands to validate inputs, launch reviews, and wait for re-review. The task is not complete until the refine loop finishes and you present the result to the user.

Read the full file on GitHub · 274 lines

Changes

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.

  1. 8d ago First seen · 274 lines · 19 tokens per session scan A b0904b7bc48b

Subscribe to this mod's changes

roborev-refine is a skill published in the GitHub repository kenn-io/roborev (1,692 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 2,421 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.