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.
npx agentmods add skills/0xagentkitchen/kitchenloop/loop-reviewnpx skills add 0xagentkitchen/kitchenloop --skill loop-reviewgit clone --depth 1 https://github.com/0xagentkitchen/kitchenloopWhat 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 | $0.00000 | $0.02759 |
| Opus 5 | $0.00000 | $0.01380 |
| Sonnet 5 | $0.00000 | $0.00552 |
| Haiku 4.5 | $0.00000 | $0.00276 |
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 2d 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.
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 reviewreview the loopreview 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
- Load
kitchenloop.yaml. - Read loop state at
paths.loop_stateto find:- The current iteration number.
- The last iteration that was reviewed.
- 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.
- 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
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.
- 2d ago First seen · 382 lines · 0 tokens per session scan A 87a13a206d38
loop-review is a skill published in the GitHub repository 0xagentkitchen/kitchenloop (23 stars, last pushed 5mo 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…