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 rordi-ai/loopbreaker --skill review-planninggit clone --depth 1 https://github.com/rordi-ai/loopbreakerWrote 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/rordi-ai/loopbreaker/review-planning)<a href="https://agentmods.dev/skills/rordi-ai/loopbreaker/review-planning"><img src="https://agentmods.dev/badge/skills/rordi-ai/loopbreaker/review-planning/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/rordi-ai/loopbreaker/review-planning"><img src="https://agentmods.dev/badge/skills/rordi-ai/loopbreaker/review-planning.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 | $0.00063 | $0.00913 |
| Opus 5 | $0.00032 | $0.00456 |
| Sonnet 5 | $0.00013 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
review-planning 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 12d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Planning
Decide whether an authored shape and implementation plan cohere well enough to admit coding. This is an independent review: inspect and record, but do not edit the shape, behavior contract, or planning profile while acting as reviewer.
Read references/decision-rules.md completely before reviewing.
State authority
See state authority for the full discipline. This skill's header emits four lines:
Shape: <exact persisted disposition and readiness>
Planning: <exact persisted score and readiness>
Planning review: <exact persisted disposition and next action>
Implementation: <admitted or held>
Call delivery_readiness, then review_substrate to populate it. If shape is absent,
incomplete, or not proceed, stop at the shape gate. If planning health is not ready,
return its named structural blockers. Do not begin a semantic pass until both gates
are ready.
Review protocol
Use planning_review.next_action; never select a pass from intuition.
- Pass 1, comprehensive: test semantic alignment from problem and smallest slice through enforced behaviors, work-unit ownership, proportionate proof, production wiring, rollback, migration, and named risks. Enumerate material root causes once.
- Pass 2, repair verification: inspect only admitted repairs and regressions caused by those repairs. Preserve finding IDs. Do not reopen accepted design choices.
- Pass 3, decision only: conduct no new audit. Choose
approved,rescope, orreturn_to_shapingfrom the decision packet. There is no pass 4.
Record stable concerns with planning_review_upsert_finding. Open P0/P1 findings
must include reachability, impact, and smallest fix; they prevent approval. Record the
completed pass with planning_review_record_pass. Passes 1 and 2 allow only
approved or changes_required; pass 3 is terminal and decision-only.
Boundaries
- The issue's enforced behavior children are the acceptance surface. Narrative parents interpret it but cannot add requirements.
- Planning health proves structural completeness; this review judges coherence.
- The authoring agent must not approve its own work.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 87 lines · 63 tokens per session scan A 821e8ca0defd
review-planning is a skill published in the GitHub repository rordi-ai/loopbreaker (3 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 913 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…