Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gonzalezpazmonica/savianpx agentmods add commands/gonzalezpazmonica/savia/compliance-checkWrote 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/commands/gonzalezpazmonica/savia/compliance-check)<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/compliance-check"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/compliance-check/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/commands/gonzalezpazmonica/savia/compliance-check"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/compliance-check.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 | $0.00015 | $0.00460 |
| Opus 5.5 | $0.00006 | $0.00184 |
| Sonnet 5.5 | $0.00003 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
compliance-check 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 20d 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.
This is a copy
100% identical to compliance-check — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
/compliance-check — Verificación de compliance de reglas
Ejecuta el sistema de verificación automática de reglas de pm-workspace.
Qué verifica
- Links de comparación en CHANGELOG — Cada
## [X.Y.Z]debe tener su[X.Y.Z]: URLal final - Tamaño de ficheros — Commands, rules, skills ≤ 150 líneas
- Frontmatter YAML — Comandos nuevos deben tener frontmatter
- READMEs — Máximo 150 líneas, sincronización ES/EN
Parámetros
- Sin parámetros: verifica ficheros staged
--all: verifica todo el repositorio
Ejecución
bash .claude/compliance/runner.sh --all
Si hay violaciones
- Lee el mensaje de error — indica qué regla se ha violado
- Localiza la regla en
docs/rules/domain/para entender el contexto - Corrige la violación
- Vuelve a ejecutar
/compliance-checkpara verificar
Cómo funciona
El sistema traduce reglas de prosa (docs/rules/domain/*.md) a verificaciones ejecutables
(.claude/compliance/checks/*.sh). Así, aunque el LLM pierda contexto en conversaciones largas,
los scripts garantizan que las reglas objetivas se cumplen.
Reglas cubiertas automáticamente:
| Regla | Check | Tipo |
|---|---|---|
changelog-enforcement.md |
validate-changelog-links.sh |
Bloqueante |
| File size conventions | check-file-size.sh |
Bloqueante |
| Command validation | check-command-frontmatter.sh |
Warning |
| README conventions | check-readme-sync.sh |
Bloqueante |
Las reglas conversacionales (tone, workflow, inclusive-review) no son verificables por script y siguen dependiendo del contexto cargado en las rules de Claude Code.
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.
- 20d ago Changed 89d84a8b075e
- 1mo ago First seen · 56 lines · 15 tokens per session scan A a53583020535
compliance-check is a command published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 460 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to compliance-check, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
asset-audit
Audit assets for compliance with standards.
review-policy
Review a policy document for structure, coverage, and language quality.
listing-reviewer
Reviews a listing description for quality, factual accuracy, and Fair Housing compliance. Use after drafting listing/MLS copy, and inside /list-it.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.