kitchenloop-ideate

The idea-generation stage of KitchenLoop, an automated software-development cycle. It acts like a project user, tries realistic tasks through the project's public tools, and records what works or fails.

In plain words
What is it for?
It helps test simple features, combined workflows, and boundary cases, then creates an experience report that can be turned into work items.
Why use it?
It exposes missing features, broken workflows, and integration problems by testing the project as someone would actually use it.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/0xagentkitchen/kitchenloop/kitchenloop-ideate
Any agent
npx skills add 0xagentkitchen/kitchenloop --skill kitchenloop-ideate
Clone the repo
git clone --depth 1 https://github.com/0xagentkitchen/kitchenloop

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,949 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01949
Opus 5 $0.00000 $0.00975
Sonnet 5 $0.00000 $0.00390
Haiku 4.5 $0.00000 $0.00195

Measured 2d ago against content hash 0dd2a91d920d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kitchenloop-ideate 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.

skills/kitchenloop-ideate/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KitchenLoop: Ideate

Phase 1 -- Brainstorm a usage scenario, implement it, test it, write an experience report.

Triggers

  • kitchenloop ideate
  • loop ideate
  • brainstorm scenario

Overview

The Ideate phase is where the loop generates new work. You act as a synthetic user of the project: pick a realistic scenario, try to implement it using the project's public API and tooling, document what works and what doesn't, and produce a structured experience report that the Triage phase will later convert into tickets.


Scenario Tiers

T1 -- Foundation (single feature, happy path)

  • Exercise ONE feature from the spec.dimensions section of kitchenloop.yaml
  • Follow the documented happy path exactly
  • Goal: verify basics still work, catch regressions early
  • Example: "Use the auth module to register a user and log in"

T2 -- Composition (combine features)

  • Exercise TWO OR MORE features together in a realistic workflow
  • Goal: catch integration seams, data-flow mismatches, missing error handling
  • Example: "Register a user, create a payment, then generate a report"

T3 -- Frontier (push boundaries)

  • Attempt something the project does not explicitly support yet
  • Goal: discover missing capabilities, poor error messages, edge cases
  • Example: "Use the reports API with a date range that spans a timezone change"

Tier selection rule: If the last 3 iterations were all T1, escalate to T2. If T2 scenarios have high pass rates (>90%), try T3. If T3 keeps failing on the same root cause, file a blocker ticket and drop back to T2.


Procedure

Step 1: Read Context

  1. Load kitchenloop.yaml -- read spec.dimensions, spec.blocked, paths, and verification.
  2. Read loop state at the path specified by paths.loop_state:
    • What iteration number is this?
    • What scenarios were tried in recent iterations?
    • What tiers have been used recently?
  3. Read the spec docs listed in spec.docs to understand project capabilities.
  4. If paths.patterns exists, read it for known codebase patterns and pitfalls.

Read the full file on GitHub · 224 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. 2d ago First seen · 224 lines · 0 tokens per session scan A 0dd2a91d920d

Subscribe to this mod's changes

kitchenloop-ideate 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 1,949 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

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens