0xagentkitchen

12 mods across 1 repository, 23 stars between them.

uat-evaluator

02

0xagentkitchen/kitchenloop

Agent Claude Code

Read-only adversarial user acceptance tester. Executes a sealed test card without implementation context. Cannot modify product code. Collects raw evidence only.

23 5mo ago A 32 tokens original MIT

0xagentkitchen/kitchenloop

Skill Claude CodeCodex

Orchestrate a structured multi-AI discussion. Gemini and Codex debate via CLI, Claude debates via an isolated subagent, and you are the impartial moderator.

23 5mo ago A 0 tokens original MIT

0xagentkitchen/kitchenloop

Instructions file CodexOpenCode

Instructions for 0xagentkitchen/kitchenloop, covering kitchenloop, key concepts, architecture, worktree model and configuration.

23 5mo ago A 1,113 tokens original MIT

0xagentkitchen/kitchenloop

Instructions file

Instructions for 0xagentkitchen/kitchenloop, a project described as: The Kitchen Loop — autonomous self-evolving codebase framework.

23 5mo ago A 3 tokens copy · 100% MIT

kitchenloop-backlog

06

0xagentkitchen/kitchenloop

Skill Claude CodeCodex

The Backlog phase keeps the todo queue healthy. It scans all open tickets, scores them on urgency/accessibility/impact, promotes the best candidates to the todo queue, and retires stale tickets. The goal is to maintain a todo queue of 5-8 tickets with good category balance.

23 5mo ago A 0 tokens original MIT

kitchenloop-execute

07

0xagentkitchen/kitchenloop

Skill Claude CodeCodex

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.

23 5mo ago A 0 tokens original MIT

kitchenloop-ideate

08

0xagentkitchen/kitchenloop

Skill Claude CodeCodex

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…

23 5mo ago A 0 tokens original MIT

kitchenloop-regress

09

0xagentkitchen/kitchenloop

Skill Claude CodeCodex

The Regress phase is the loop's quality gate. It runs the full test suite, evaluates whether the codebase is healthy enough to continue looping, and consolidates patterns learned during the iteration. If stop conditions are triggered, the loop pauses until a human intervenes.

23 5mo ago A 0 tokens original MIT

kitchenloop-triage

10

0xagentkitchen/kitchenloop

Skill Claude CodeCodex

The Triage phase converts the raw friction log from an experience report into actionable, well-labeled tickets. Every finding becomes exactly one ticket -- no more, no less. Deduplication against existing tickets prevents the backlog from filling with clones.

23 5mo ago A 0 tokens original MIT

loop-review-meta

11

0xagentkitchen/kitchenloop

Skill Claude CodeCodex

Loop Review Meta is a higher-order analysis that reads ALL loop review reports and identifies patterns that span multiple review periods. While individual loop reviews catch per-iteration issues, the meta review catches systemic trends: recurring themes that never get fixed, drift in loop behavior, effectiveness of…

23 5mo ago A 0 tokens original MIT

loop-review

12

0xagentkitchen/kitchenloop

Skill Claude CodeCodex

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.

23 5mo ago A 0 tokens original MIT