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 marcoguillermaz/Tierward --skill compliance-auditgit clone --depth 1 https://github.com/marcoguillermaz/TierwardWrote 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/marcoguillermaz/tierward/compliance-audit)<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/compliance-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/compliance-audit/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/marcoguillermaz/tierward/compliance-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/compliance-audit.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 | $0.00062 | $0.03509 |
| Opus 5 | $0.00031 | $0.01754 |
| Sonnet 5 | $0.00012 | $0.00702 |
| Haiku 4.5 | $0.00006 | $0.00351 |
Grade A, and why
compliance-audit 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope for v1
- Static analysis only. Grep, filesystem reads, configuration parsing. Does not run tests, does not connect to databases, does not validate live policy enforcement.
- Regulatory scope, not legal advice. This skill flags mechanical gaps between common regulatory expectations and the codebase. It does not produce legal-grade compliance attestation - that requires human counsel review.
- Active profile: GDPR only. SOC 2 and HIPAA are scaffolded in
PROFILES.mdwith check-ID placeholders and will be enabled once real enterprise feedback validates the patterns. Enabling before validation risks false confidence.
Configuration (adapt before first run)
Replace these placeholders:
[APP_SOURCE_PATH]- application source root (e.g.src/,app/,lib/)[API_ROUTES_PATH]- API route handlers (e.g.src/routes/,app/api/)[SCHEMA_PATH]- DB schema or ORM model files (e.g.prisma/schema.prisma,src/models/,app/models.py)[PRIVACY_DOC_PATH]- privacy policy and data-handling docs (e.g.docs/privacy/,PRIVACY.md). Leave empty if none.
Step 0 - Target and profile resolution
Parse $ARGUMENTS for target: or profile: tokens.
| Pattern | Meaning |
|---|---|
target:path:<dir> |
Audit only files under a specific directory |
profile:gdpr |
Run only the GDPR profile (default in v1) |
mode:all / no argument |
Full GDPR audit. SOC 2 and HIPAA findings reported as FUTURE - profile scaffolded for v1.15+. |
Announce: Running compliance-audit - scope: [FULL | target: <resolved>] - profile: gdpr.
Add caveat on first line of output: This audit produces mechanical findings. Legal compliance attestation requires human counsel review.
Step 1 - Profile loading
Read ${CLAUDE_SKILL_DIR}/PROFILES.md. Three profiles defined: GDPR (active), SOC 2 (future), HIPAA (future).
For v1, only GDPR checks execute. SOC 2 and HIPAA sections in the report are emitted with a single row: Profile scaffolded for v1.15+. No checks run. This keeps the report shape stable for future releases.
What ships with it
1 file 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 · 286 lines · 62 tokens per session scan A 72e0765f1569
compliance-audit is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 3,509 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
harness-engineering
Use when the user asks to improve, fix, or build their repository's AI harness — AGENTS.md, rules, skills, commands, hooks, guardrails, CI sensors — or to act on harness-score audit findings and raise their maturity level.
dispute-respond
Prepare and explicitly file an evidence-bound payment dispute response using native receipt proof, approval, provider execution, and independent readback.
sign-receipt
Bind an off-runtime action claim to opaque evidence references in a signed Runx receipt without pretending Runx verified the external action.
vuln-disclosure
Prepare an evidence-bound vulnerability publication and publish the exact approved advisory through any compatible provider binding with independent readback.
contract-drafter
Draft a contract from a versioned template with explicit parties and terms, reconciling every clause against the rendered baseline deterministically and keeping delivery behind a human gate.
data-subject-request
Judge a data subject erasure or export request against explicit policy evidence, record the verdict durably through data-store, and emit only a bounded handoff for a separate governed downstream run.