review-sweep

review-sweep is a skill for Claude Code from rlaope/oh-my-hermes. It costs 58 tokens per session (377 once invoked), scanned A, original, MIT.

A procedure for reviewing open GitHub pull requests that have not been checked at their current commit. A pull request is a proposed code change awaiting review.

In plain words
What is it for?
Use it to review one pull request or sweep a backlog, including draft or author-specific requests. The apply option posts findings as a GitHub review with inline comments.
Why use it?
It checks the full repository and its review rules instead of judging only the changed lines, and its default dry run avoids posting a review without confirmation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions AGENTS.md; mentions Codex.

Good fit Use it to review one pull request or sweep a backlog, including draft or author-specific requests. The apply option posts findings as a GitHub review with inline comments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rlaope/oh-my-hermes/review-sweep
About the project

oh-my-hermes is an operating layer for Hermes Agent that organizes requests into workflows for planning, research, creation, coding handoffs, operations, and project memory. Hermes users run these workflows through the desktop app, CLI, or messenger app, while the catalogue add-ons extend its native capabilities.

rlaope/oh-my-hermes · 1,677 stars · on GitHub · rlaope.github.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 rlaope/oh-my-hermes --skill review-sweep
Clone the repo
git clone --depth 1 https://github.com/rlaope/oh-my-hermes

Made for: Claude Code.

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 review-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/review-sweep/github.svg)](https://agentmods.dev/skills/rlaope/oh-my-hermes/review-sweep)
Your own site
<a href="https://agentmods.dev/skills/rlaope/oh-my-hermes/review-sweep"><img src="https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/review-sweep/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.

agentmods 80×15 button for review-sweep

Your own site · 80×15
<a href="https://agentmods.dev/skills/rlaope/oh-my-hermes/review-sweep"><img src="https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/review-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 377 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 $0.00058 $0.00377
Opus 5 $0.00029 $0.00188
Sonnet 5 $0.00012 $0.00075
Haiku 4.5 $0.00006 $0.00038

Measured 13d ago against content hash 1adb0a360c24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-sweep 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 13d 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.

.claude/skills/review-sweep/SKILL.md · 41 lines

What it actually says

Review sweep

The procedure lives in docs/REVIEW-SWEEP.md. Read that file and follow it.

It is kept there rather than here because Codex, Hermes handoffs, and generic executor profiles run the same sweep, and AGENTS.md requires that no single executor own a shared surface. This file exists so the procedure is reachable as /review-sweep; it deliberately holds no rules of its own, so there is nothing here to drift out of sync with the real one.

Start by reading, in this order:

cat docs/REVIEW-SWEEP.md
cat REVIEW.md

Two things worth knowing before you open the procedure, because they are what the sweep gets wrong most often:

  • Never review from the diff alone. This repo's defects are about consistency with code that is not in the diff, so the procedure checks the PR out into a worktree and runs the gates.
  • The default is a dry run. A review is a public, notifying write to someone else's work; print the findings and stop for confirmation unless the invocation carried --apply.

Arguments pass through verbatim: a bare number reviews one PR, --drafts and --mine widen the sweep, --apply posts.

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. 13d ago First seen · 41 lines · 58 tokens per session scan A 1adb0a360c24

Subscribe to this mod's changes

review-sweep is a skill published in the GitHub repository rlaope/oh-my-hermes (1,677 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 377 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

reviewing-changes

Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.

JetBrains/thinkrail · 59 tokens

reflecting-findings

Use when a reflection package hands you another agent's review findings to verify (before they become a fix request): you are the REFLECTOR, an independent skeptic. Judge each finding against the real code and settle it with reflectfinding — kept or refuted.

JetBrains/thinkrail · 58 tokens

nlpm-audit

Audit SKILL.md, AGENTS.md, prompts, hooks, and plugin manifests for instruction conflicts, quality, broken references, and manifest-to-disk drift.

seaworld008/Commonly-used-high-value-skills · 37 tokens

api-design-reviewer

Use when reviewing API designs for consistency, usability, versioning, error semantics, security, backward compatibility, and developer experience before implementation or release.

seaworld008/Commonly-used-high-value-skills · 34 tokens

pr-review-expert

Review GitHub PRs or GitLab MRs for correctness, security, compatibility, and affected test coverage, with actionable evidence tied to the diff.

seaworld008/Commonly-used-high-value-skills · 35 tokens

gh-address-comments

Use when addressing GitHub PR review comments or issue comments on the current branch with gh CLI, including auth checks, comment triage, edits, verification, and replies.

seaworld008/Commonly-used-high-value-skills · 38 tokens