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.
git clone --depth 1 https://github.com/wahidyankf/ose-publicWrote 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/agents/wahidyankf/ose-public/rules-checker)<a href="https://agentmods.dev/agents/wahidyankf/ose-public/rules-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/rules-checker/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/agents/wahidyankf/ose-public/rules-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/rules-checker.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 | $0.00041 | $0.01191 |
| Opus 5.5 | $0.00016 | $0.00476 |
| Sonnet 5.5 | $0.00008 | $0.00238 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
rules-checker 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rules Checker
Finds where a repository's rules disagree with each other, with the repository, or with the level above them. It changes nothing.
Normal Workload
It reads rules across every rule-bearing location, traces each to the level above it, and compares the statements that
speak to one subject. Two rules can contradict without sharing a word, so its core loop is reading for meaning across
documents and levels, which
Portable Tiers places at plan.
A missed contradiction also costs more than one finding: every rule built on the wrong statement inherits it.
Scope
Rules sit wherever Rule Definition finds them: governance prose, root instruction files, agent and skill definitions, and gate declarations with the hooks and pipeline jobs that enforce them. A check confined to one directory is reported as partial.
It is the checker of Rules Quality Gate: each cycle it audits the subject that gate froze, with its uses, the authority above it, and overlapping guidance. Run alone, it judges the whole corpus's consistency, as Validating Governance Rules describes, while Rules Grooming sweeps for reductions.
What It Checks
- Contradictions. Two statements that cannot both be followed, within a level or across levels, with the level that governs under Governance Layers named in the finding.
- Inaccuracies. A path, agent, skill, workflow, command, or gate that a rule names but that does not exist, or exists and does something else, and a gate declaration its implementation no longer matches.
- Inconsistencies. One obligation stated at two strengths, as Rule Definition reads wording; one term used for two things; an index that disagrees with its directory; a summary that disagrees with the document it summarizes.
- Traceability. A convention or development standard with no recorded principle, or a trace to a principle it no longer serves, per Principle Traceability.
- Duplicated bodies. Two capabilities carrying one body, per Capability Forms, with a merge recommended only as conservatively as the skill allows.
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.
- 2d ago First seen · 98 lines · 41 tokens per session scan A b835f813cba5
rules-checker is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,191 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.
Other agents, from other repositories
reviewer
Code review specialist for quality/security analysis.
workflow-quality
Use this agent when you need expert guidance on Output SDK implementation patterns, code quality, and best practices. Invoke when writing or reviewing workflow code, troubleshooting implementation issues, or ensuring code follows SDK conventions.
ts-enforcer
TypeScript strict mode enforcement — no any types, schema-first at trust boundaries, type vs interface discipline, strict tsconfig audit.
angular-reviewer
Angular 22 and TypeScript code review specialist — Signals, Signal Forms (stable), standalone components, RxJS, performance, zoneless change detection, httpResource.
typescript-software-architect-review
Expert TypeScript software architect that provides Clean Architecture, Domain-Driven Design (DDD), Node.js patterns, and modern TypeScript frameworks guidance. Reviews TypeScript codebases for architectural integrity, proper separation of concerns, and best practices across Express, Fastify, NestJS, and other…
logic-design
Decide where new application logic belongs — component shape, logic layer, store variant — and return a recommendation with the schematic to run and what to verify. Use the logic-review agent for existing code.