loop-review

loop-review is a skill for Claude Code, Codex from 0xagentkitchen/kitchenloop. It costs 0 tokens per session (2,759 once invoked), scanned A, original, MIT.

A periodic quality audit for KitchenLoop, an automated software-development cycle. It reviews recent work, merged changes, and reports, then writes a lasting summary of problems by severity.

In plain words
What is it for?
It helps inspect a range of iterations, review pull requests and code, optionally ask other AI auditors for input, and record actionable findings.
Why use it?
It reveals repeated or important issues that may be missed when reviewing one change or one cycle at a time.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit It helps inspect a range of iterations, review pull requests and code, optionally ask other AI auditors for input, and record actionable findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/0xagentkitchen/kitchenloop/loop-review
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 0xagentkitchen/kitchenloop --skill loop-review
Clone the repo
git clone --depth 1 https://github.com/0xagentkitchen/kitchenloop

Made for: Claude Code, Codex.

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 loop-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/0xagentkitchen/kitchenloop/loop-review/github.svg)](https://agentmods.dev/skills/0xagentkitchen/kitchenloop/loop-review)
Your own site
<a href="https://agentmods.dev/skills/0xagentkitchen/kitchenloop/loop-review"><img src="https://agentmods.dev/badge/skills/0xagentkitchen/kitchenloop/loop-review/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 loop-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/0xagentkitchen/kitchenloop/loop-review"><img src="https://agentmods.dev/badge/skills/0xagentkitchen/kitchenloop/loop-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,759 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 $0.00000 $0.02759
Opus 5.5 $0.00000 $0.01104
Sonnet 5.5 $0.00000 $0.00552
Haiku 4.5 $0.00000 $0.00276

Measured 2mo ago against content hash 87a13a206d38, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

loop-review 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 2mo 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.

skills/loop-review/SKILL.md · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loop Review

Review N iterations -- read logs, inspect PRs and code, run external auditors, write a synthesis report with actionable findings.

Triggers

  • loop review
  • review the loop
  • review iterations

Overview

Loop Review is a periodic quality audit of the KitchenLoop's recent output. It reads experience reports, inspects merged PRs and their code changes, optionally runs external auditors (Codex, Gemini), and produces a durable synthesis report with findings categorized by severity.

This phase runs every runtime.review_interval iterations automatically, or on demand.


Inputs

  • Iteration range: Either specified explicitly ("review iterations 10-15") or inferred from loop state (last N iterations since the previous review).
  • Configuration: kitchenloop.yaml -- paths, reviewers, repo, runtime.

Procedure

Step 1: Determine Scope

  1. Load kitchenloop.yaml.
  2. Read loop state at paths.loop_state to find:
    • The current iteration number.
    • The last iteration that was reviewed.
  3. Determine the review range:
    • If called with explicit range (e.g., "iterations 10-15"), use that.
    • Otherwise, review from (last_reviewed + 1) to current iteration.
  4. If the range is empty (no new iterations), report "Nothing to review" and exit.

Step 2: Gather Artifacts

For each iteration in the range, collect:

2a. Experience Reports

Read all reports matching {paths.reports}/experience-report-iter-{N}.md for each N in the range. Extract:

  • Scenario description and tier
  • Pass/fail status
  • Friction log items (count and severity breakdown)
2b. Regression Results

Read loop state entries for each iteration's regression results:

  • Pass rate trend
  • Test count trend
  • Any PAUSED or FLAGGED iterations
2c. PRs and Code Changes

List all PRs merged during the review period:

# Get merge commits in the date range
git log --merges --oneline --after="{start_date}" --before="{end_date}" {repo.base_branch}

# Or list PRs by merge date
gh pr list --state merged --limit 50 --json number,title,mergedAt,additions,deletions,files,body

Read the full file on GitHub · 382 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. 2mo ago First seen · 382 lines · 0 tokens per session scan A 87a13a206d38

Subscribe to this mod's changes

loop-review is a skill published in the GitHub repository 0xagentkitchen/kitchenloop (23 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,759 tokens. 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

loop-review compared with skills from other repositories

loop-review next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
loop-review0xagentkitchen/kitchenloopSkill237mo agoMITA0Claude Code, Codex
autoreviewopenclaw/clawhubSkill9.5kyesterdayMITA17Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skillsSkill2.2k6d agoMITA115Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermesSkill5.2kyesterdayMITA48Claude Code, Codex
revdiff-planumputun/revdiffSkill945yesterdayMITA84Claude Code
explore-unknownsdzhng/skillsSkill1.4k2d agoMITA162Claude Code, Codex
re0-mergeLilMGenius/paperthinSkill1.4k4d agoMITA70Claude Code