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-invariantsgit 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-invariants)<a href="https://agentmods.dev/skills/rordi-ai/loopbreaker/review-invariants"><img src="https://agentmods.dev/badge/skills/rordi-ai/loopbreaker/review-invariants/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-invariants"><img src="https://agentmods.dev/badge/skills/rordi-ai/loopbreaker/review-invariants.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 | $0.00075 | $0.01113 |
| Opus 5 | $0.00037 | $0.00557 |
| Sonnet 5 | $0.00015 | $0.00223 |
| Haiku 4.5 | $0.00007 | $0.00111 |
Grade A, and why
review-invariants 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 11d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Invariants
Determine whether the frozen behavior contract is true in production. Produce one comprehensive pass, one repair-verification pass when needed, and at most one decision-only pass. Review evidence supports behavior state; it is not a hidden ship gate.
Non-negotiable state authority
See state authority for the full discipline; it applies here without exception. This skill's header emits five separate lines:
Shape: <exact persisted disposition and readiness>
Planning review: <exact persisted disposition>
Planning: <exact persisted score and readiness>
Review: <current or proposed review result>
Shipping: <exact persisted disposition> [state unchanged when not persisted]
Read references/decision-rules.md completely before reviewing.
Preflight
- Resolve the issue and exact artifact: working diff, commit range, or PR.
- Call
delivery_readiness, thenreview_substrate, before reading the change. Do not start pass one unless implementation is admitted by shape, planning health, and planning-review approval; return the exact active gate instead. - Treat behavior children as the frozen acceptance surface. Parent context may interpret them but cannot add requirements.
- Read
review.next_action; never choose a pass from intuition.
Review is read-only with respect to source code, remote reviews, and waivers unless the user separately requests changes. Recording review passes, evidence, and findings in Loopbreaker is part of this skill.
Pass protocol
Pass 1 — comprehensive
Trace every enforced behavior through implementation, active production wiring, and proportionate proof. Enumerate all material root causes now. Collapse symptoms with the same cause. Check candidate invariants only when their declared scope intersects the changed or required-wiring paths.
Pass 2 — repair verification
Check every admitted repair against its named closing proof, then inspect only the repair delta for regressions caused by that repair. Do not reopen allowed designs or scan untouched pre-existing code for additional improvements.
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.
- 11d ago First seen · 111 lines · 75 tokens per session scan A 87573fc5723e
review-invariants is a skill published in the GitHub repository rordi-ai/loopbreaker (3 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,113 once invoked, about $0.0004 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…