agentmods.dev

review-loop

review-loop is a skill for Claude Code, Codex from YoungjaeDev/my-claude-plugins. It costs 206 tokens per session (10,119 once invoked), scanned A, original, MIT.

A workflow for handling review comments on an open pull request (PR), a proposed code change awaiting review. It retrieves CodeRabbit and Codex findings, decides whether to apply, defer, or skip each one, then commits and pushes changes in repeated rounds.

In plain words
What is it for?
Use it to process outstanding reviewer feedback on the current PR until reviews stop producing new findings, or until the loop stops because of low severity or repeated changes.
Why use it?
It removes the manual work of collecting review comments, judging them, making fixes, and checking again after each push. It also records declined findings for follow-up instead of silently losing them.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also agents/openai.yaml present. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dev plugin — 12 skills, 3 agents shipped together

not rated 2repo changed today A scan 206 tokens original MIT

Good fit Use it to process outstanding reviewer feedback on the current PR until reviews stop producing new findings, or until the loop stops because of low severity or repeated changes.

Compare 6 skills from other repositories ↓
View source ↗ YoungjaeDev/my-claude-plugins
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add YoungjaeDev/my-claude-plugins
Claude Code
/plugin install dev

Made for: Claude Code, Codex.

Or install dev, the plugin that ships this one along with the rest of its 12 skills, 3 agents.

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-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/review-loop/github.svg)](https://agentmods.dev/skills/youngjaedev/my-claude-plugins/review-loop)
Your own site
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/review-loop"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/review-loop/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-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/review-loop"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/review-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 206 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,119 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.
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 $0.00206 $0.10119
Opus 5.5 $0.00082 $0.04048
Sonnet 5.5 $0.00041 $0.02024
Haiku 4.5 $0.00021 $0.01012

Measured today against content hash 9ee9e0b9b1da, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-loop 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 today.

The scan reads SKILL.md. This mod also ships 38 executable files (scripts/auto-merge-gate.sh, scripts/base-push.sh, scripts/churn-scope.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/dev/skills/review-loop/SKILL.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeRabbit + Codex Fix Pipeline

Overview

One turn drives the whole review-resolution loop on an open PR: detect what each reviewer has already said, fetch its findings, judge each finding against the local code, commit, push, and let that push trigger the next review. The loop ends on convergence, on a low-severity floor, or on churn; whatever it declined to apply leaves in a single follow-up issue.

When to use

An open PR on the current branch with reviewer work outstanding — /dev:review-loop (old name "cr-fix"), "리뷰 반영", "process CodeRabbit feedback", "loop until clean".

Not this skill: cleanup after a PR merges (dev:post-merge), splitting a spec into tickets (Matt /to-tickets), or reviewing code that has no PR yet.

Runner

On Claude Code, unless $ARGUMENTS already carries --runner, the main session does not run the steps below itself. It hands the whole run to one background subagent and consumes its final JSON:

  1. Delete .claude/state/review-loop-final-<PR>.json left by an earlier run on this PR, so step 2 never reads its result as this one's. Then dispatch one Agent with run_in_background: true and this prompt: run the review-loop skill by reading this SKILL.md and following it from Step 1 with the arguments $ARGUMENTS --runner, then return the one JSON line Step 16 prints. One runner per PR; never a second one while the first runs.
  2. Wait without polling the runner. When its completion notice arrives, or on any later turn, read .claude/state/review-loop-final-<PR>.json: the runner writes its final line there too, so a lost notice does not leave the result unread. No file yet means it is still running.
  3. A subagent has no AskUserQuestion (Claude Code removes it from every subagent; confirm on the sub-agents page listed in https://code.claude.com/docs/llms.txt), so --runner takes the safe default at both interactive gates and returns the question in pending_decision. The main session asks it: merge is Step 15's "auto-merge 할까요?", after which it runs the "Step 15: merge" block in references/run-blocks.md as that block describes; cr_source is Step 7c's question, after which it dispatches a new runner with the chosen --cr-source.
  4. Write the final report from the JSON (Step 16). After an answered merge question the file predates the merge: take merged and base_push from what the "Step 15: merge" block did, and report no pending_decision.

Read the full file on GitHub · 345 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today Changed 9ee9e0b9b1da
  2. 13d ago Changed · +24 lines 2f2897c20ef8
  3. 23d ago First seen · 321 lines · 206 tokens per session scan A fb2b6980f139

Subscribe to this mod's changes

review-loop is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 206 tokens to every session and 10,119 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-08.

Code reviewCommitsGit and workflow
Related

Other skills, from other repositories

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

github-pr-workflow

Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.

paperclipai/paperclip · 39 tokens

review-delta

Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.

tirth8205/code-review-graph · 24 tokens

github-contributor

A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.

daymade/claude-code-skills · 105 tokens

hero-diff-highlight

A dark code editor reveals a red deletion then a green addition with a soft pulse. Function: PR / code-change explainer.

Unclecheng-li/AI_Animation · 0 tokens

git-pr-workflows-git-workflow

Guide changes through code checks, testing, commits, and pull request preparation. Use when coordinating a complete Git workflow and verifying readiness for collaboration.

rmyndharis/antigravity-skills · 37 tokens