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 skills add 0xagentkitchen/kitchenloop --skill loop-review-metagit clone --depth 1 https://github.com/0xagentkitchen/kitchenloopWrote 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.
[](https://agentmods.dev/skills/0xagentkitchen/kitchenloop/loop-review-meta)<a href="https://agentmods.dev/skills/0xagentkitchen/kitchenloop/loop-review-meta"><img src="https://agentmods.dev/badge/skills/0xagentkitchen/kitchenloop/loop-review-meta/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.
<a href="https://agentmods.dev/skills/0xagentkitchen/kitchenloop/loop-review-meta"><img src="https://agentmods.dev/badge/skills/0xagentkitchen/kitchenloop/loop-review-meta.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01898 |
| Opus 5.5 | $0.00000 | $0.00759 |
| Sonnet 5.5 | $0.00000 | $0.00380 |
| Haiku 4.5 | $0.00000 | $0.00190 |
Grade A, and why
loop-review-meta 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.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loop Review Meta
Macro analysis across all loop review reports -- trends, recurring themes, systemic recommendations.
Triggers
loop review metameta analysis
Overview
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 self-improvement over time.
Procedure
Step 1: Gather All Review Reports
-
Load
kitchenloop.yaml-- readpaths. -
List all review reports in
{paths.reports}/:ls {paths.reports}/loop-review-iter-*.md -
Read each report. Extract structured data:
- Iteration range covered
- Metrics (pass rate, test count, backlog, PRs merged)
- Finding counts by severity (Blocker, Important, Observation)
- Recommendations made
- External auditor results
-
Read loop state at
paths.loop_statefor the full iteration history.
Step 2: Trend Analysis
2a. Quality Trends
Plot (textually) how key metrics have evolved across all review periods:
- Pass rate trajectory: Is it trending up (loop is improving the codebase), flat (loop is maintaining), or down (loop is introducing regressions)?
- Test count trajectory: Growing (good coverage expansion), shrinking (test deletion or skip-creep), or flat?
- Backlog trajectory: Growing (more issues found than fixed), shrinking (good execution velocity), or stable?
2b. Finding Recurrence
Identify findings that appear across multiple review reports:
- Cluster findings by theme (e.g., "test coverage gaps", "error handling", "documentation drift", "convention violations").
- For each theme, count how many review periods it appeared in.
- Flag themes that appear in 3+ reviews as Systemic Issues.
2c. Recommendation Follow-Through
For each recommendation made in previous reviews:
- Was it converted to a ticket?
- Was the ticket resolved?
- Did the issue recur after the fix?
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.
- 2mo ago First seen · 272 lines · 0 tokens per session scan A 4a1058da3539
loop-review-meta 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 1,898 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.
loop-review-meta compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| loop-review-meta0xagentkitchen/kitchenloop | Skill | 23 | 7mo ago | MIT | A | 0 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |