An automated process for repeatedly reviewing a GitHub pull request, applying valid suggestions, answering discussion threads, and simplifying the result.

Use it to process review feedback, resolve comments through code changes or replies, refresh the pull request description, and stop after a fixed number of iterations.

It helps move a pull request toward review readiness while leaving genuinely uncertain issues for human judgment.

review-loop — Skill for Claude Code by mthines/agent-skills

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 mthines/agent-skills --skill review-loop

Clone the repo

git clone --depth 1 https://github.com/mthines/agent-skills

Made for: Claude Code.

Or install mthines-agent-skills, the plugin that ships this one along with the rest of its 49 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mthines/agent-skills/review-loop/github.svg)](https://agentmods.dev/skills/mthines/agent-skills/review-loop)

Your own site

<a href="https://agentmods.dev/skills/mthines/agent-skills/review-loop"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mthines/agent-skills/review-loop"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/review-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,475 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00124	$0.08475
Opus 5.5	$0.00050	$0.03390
Sonnet 5.5	$0.00025	$0.01695
Haiku 4.5	$0.00012	$0.00847

Measured 16d ago against content hash 96e299817cc2, 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 1 finding 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 16d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

if curl -fsSL --max-time 30 -o "$B/agent0-setup.sh" \

skills/quality/review-loop/SKILL.md · 487 lines

How it starts

The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.

review-loop — Bounded Review-Apply-Resolve Convergence

Iterate pr-reviewer → implement-suggestion --resolve-all → polish simplify on a PR until every review thread is resolved and CI is not red, or the cap is reached; then refresh the PR description. A thread is resolved by a fix or an honest reply; only genuine human-judgment flags stay open, and the loop never resolves a live finding to terminate. This skill is an orchestrator with no quality rules of its own. Why it is shaped this way: references/design-rationale.md.

With no PR reference, the same loop runs locally against .agent/{branch}/findings.jsonl with zero GitHub calls: follow rules/local-mode.md instead of the procedure below.

Each iteration runs sub-steps A (pr-reviewer), B (implement-suggestion --resolve-all), C (polish simplify), and D (ci-auto-fix); after the loop come Step 1.6 (preview run), Step 2 (description refresh), Step 2.5 (--merge), and Step 3 (report).

Dispatch mechanics
Modes
Step 0: Resolve the PR and preconditions
Step 1: Loop
Sub-step A — the named dispatch
Iteration 1 — apply first
Sub-step D — CI
Step 1.6 · Step 2 · Step 2.5 · Step 3
Hard rules

Dispatch mechanics — read before invoking

pr-reviewer is an agent, not a skill: dispatch it with the harness's sub-agent dispatch tool (Task(subagent_type="pr-reviewer", prompt="<PR-URL> [--critical]")). Never call Skill("pr-reviewer", …) — it errors with Unknown skill: pr-reviewer. implement-suggestion and polish are skills: invoke them with Skill(...). If Skill("implement-suggestion") is refused (disable-model-invocation: true), apply its contract inline — resolve a worktree at the PR head, apply findings commit-per-comment, push, and reply-to-and-resolve the threads yourself; never skip sub-step B.

Read the full file on GitHub · 487 lines

Files

What ships with it

11 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.

16d ago Changed · -595 lines · -100 tokens per session 96e299817cc2
17d ago Changed · +1 lines ea9e24eadcfe
20d ago Changed · +41 lines · -6 tokens per session 8ac0827595f2
1mo ago Changed · +46 lines · +8 tokens per session 4407eab688b3
1mo ago Changed · +87 lines 6b858ef95691
1mo ago Changed · +48 lines f303b511cd0b
1mo ago Changed · +17 lines d065798f31bf
1mo ago Changed · -18 lines · -321 tokens per session af0a766fe615
1mo ago Changed · +1 tokens per session 8cf9c9fc6176
1mo ago First seen · 860 lines · 542 tokens per session scan A 7de416eb7d04

Subscribe to this mod's changes

review-loop is a skill published in the GitHub repository mthines/agent-skills (20 stars, last pushed 2d ago), licensed MIT. It adds 124 tokens to every session and 8,475 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Code review Git and workflow ai claude skills skills-sh

review-loop next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
review-loopmthines/agent-skills	Skill	20	2d ago	MIT	A	124	Claude Code
local-pr-reviewPubx-ai/skills	Skill	6	1mo ago	none	A	170	Claude Code, Codex
local-reviewPubx-ai/skills	Skill	6	1mo ago	none	A	158	Claude Code, Codex
raise-prPubx-ai/skills	Skill	6	1mo ago	none	A	117	Claude Code, Codex
checktw93/Waza	Skill	7.5k	4d ago	MIT	A	41	Claude Code
ego-lite-simplifycitrolabs/ego-lite	Skill	22k	yesterday	MIT	A	68	Codex
antfu-create-prantfu/skills	Skill	6.0k	yesterday	MIT	A	54	Claude Code, Codex

review-loop