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/kitchenloop-executenpx skills add 0xagentkitchen/kitchenloop --skill kitchenloop-executegit 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 | $0.01537 |
| Opus 5 | $0.00000 | $0.00768 |
| Sonnet 5 | $0.00000 | $0.00307 |
| Haiku 4.5 | $0.00000 | $0.00154 |
Grade A, and why
kitchenloop-execute 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KitchenLoop: Execute
Phase 3 -- Query top unblocked tickets, implement them sequentially, ship PRs.
Triggers
kitchenloop executeloop executework on tickets
Overview
The Execute phase takes tickets from the todo queue and turns them into merged code. Each ticket follows a strict workflow: branch, implement, lint, test, commit, PR, transition state. The goal is steady throughput -- 3 to 5 tickets per iteration.
Procedure
Step 0: Pre-Flight
- Load
kitchenloop.yaml-- readpaths,verification,ticketing, andrepo. - Read loop state at
paths.loop_statefor current iteration context. - Check environment variables listed in
verification.preflight_env_vars. If any are missing, STOP and report which are absent.
Step 1: Check PR Backpressure
Before starting new work, check for open PRs from previous iterations:
gh pr list --author "@me" --state open --json number,title,mergeable,reviewDecision,statusCheckRollup
Backpressure rules:
- If there are 5+ open PRs, STOP. Focus on getting existing PRs merged (address review comments, fix failing CI, ping reviewers).
- If there are 3-4 open PRs, limit this iteration to 2 tickets max.
- If there are 0-2 open PRs, proceed normally (3-5 tickets).
Step 2: Recover Stale Tickets
Check for tickets marked as in-progress that have no active branch or PR. These are artifacts of interrupted previous iterations.
For GitHub Issues ticketing:
gh issue list --label "{ticketing.github.state_labels.in_progress}" --json number,title
For each stale ticket:
- If a branch exists with changes, pick up where it left off.
- If no branch exists, transition back to todo state.
Step 3: Select Tickets
- Query the todo queue, ordered by priority:
gh issue list --label "{ticketing.github.state_labels.todo}" --json number,title,labels,body --limit 10 - Filter out tickets that are blocked (check for "blocked" label or dependencies mentioned in the ticket body).
- Select the top 3-5 unblocked tickets (adjusted by backpressure from Step 1).
- Prefer a mix of categories (bugs, features, improvements) over all-of-one-type.
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 · 203 lines · 0 tokens per session scan A b6b2d6195607
kitchenloop-execute 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 1,537 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…