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 agentmods add skills/lukedj78/dev-flow/compliance-auditnpx skills add lukedj78/dev-flow --skill compliance-auditgit clone --depth 1 https://github.com/lukedj78/dev-flowWrote 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/lukedj78/dev-flow/compliance-audit)<a href="https://agentmods.dev/skills/lukedj78/dev-flow/compliance-audit"><img src="https://agentmods.dev/badge/skills/lukedj78/dev-flow/compliance-audit.svg" alt="Measured on agentmods" 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 | $0.00215 | $0.02367 |
| Opus 5 | $0.00108 | $0.01184 |
| Sonnet 5 | $0.00043 | $0.00473 |
| Haiku 4.5 | $0.00021 | $0.00237 |
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 4d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
compliance-audit — GDPR + EU AI Act audit & remediation for existing projects
Runs on a project that already exists (any dev-flow stack — Next.js web, Expo mobile, or an eve agent). It reads the codebase and .workflow/meta.json#stack, scores it against a fixed risk register, writes a report, and — on request — applies the safe mitigations while flagging the ones that need a human decision.
Not legal advice. This produces engineering findings and remediations. A DPO / qualified counsel confirms materiality, legal basis, and high-risk classification per deployment. Every generated artifact carries that caveat.
The 10-point risk register (canonical)
Full checklist + article mapping + remediation recipes in references/gdpr-ai-act-checklist.md. In short:
| ID | Risk | GDPR / AI Act |
|---|---|---|
| R1 | No DSAR: data export / erasure (also Apple 5.1.1(v) + Play in-app account deletion) | Art. 15/17/20 |
| R2 | No consent capture / cookie-consent banner | Art. 6/7, ePrivacy |
| R3 | International transfer / EU data residency not addressed | Art. 44+ |
| R4 | No retention/TTL + no PII-scrubbing (logs, event log, caches) | Art. 5(1)(e) |
| R5 | No AI-transparency disclosure; synthetic voice unlabeled | AI Act Art. 50 |
| R6 | High-risk use case never classified (DPIA) | AI Act Annex III; GDPR Art. 35 |
| R7 | PII in server/app logs | Art. 32 |
| R8 | Sub-processors not disclosed / no DPA register | Art. 28 |
| R9 | Special-category data unguarded | Art. 9 |
| R10 | Memory/personalization not screened for manipulation | AI Act Art. 5 |
Art. 32 also covers keeping the software patched — that part lives in
vercel-deploy. "Security of processing" is not only R7 (PII in logs): running a framework version with known, published CVEs is the same article. Since 2026-07 Next.js ships pre-announced monthly security releases with two maintained lines whose labels move (2026-08-25: 16.3.x Active LTS, 15.5.x Maintenance LTS — 16.2 stopped receiving patches), and the deploy gate checks the project against that floor — seereferences/contracts.md§nextjs_version. Don't duplicate the check here; when auditing a web project, readmeta.json#historyfor a recentvercel-deployrun and say so if the floor has never been verified. Note for the report: a platform WAF rule is a mitigation, not a patch — Vercel says so itself.
What ships with it
4 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.
- 4d ago First seen · 109 lines · 215 tokens per session scan A 44a3acdf5f8c
compliance-audit is a skill published in the GitHub repository lukedj78/dev-flow (6 stars, last pushed yesterday), licensed MIT. It adds 215 tokens to every session and 2,367 once invoked, about $0.0011 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
extendr-bindings
extendr conventions for exposing a Rust core to R: extendr macros and module registration, Robj type mapping, NA handling, rextendr builds, R package scaffolding, and CRAN compliance. Load when generating or reviewing extendr R bindings for a Rust library.
r-conventions
R code conventions covering R 4.1+, tidyverse/base style, styler/lintr, roxygen2, testthat, error handling, input validation, C/C++/Rust interop, and CRAN compliance. Load when writing or reviewing R code.
procurement-audit
Review procurement contracts and purchase packages against uploaded compliance rules (招标/采购制度). Use for 采购审核, contract compliance checklists, or procurement statistics rollups.
travel-expense-audit
Audit travel / 差旅报销 claims against uploaded policy handbooks and rate tables (lodging caps, transport, per diem). Use for 差旅费审核, travel expense review, or lodging over-limit checks.
tcx-order-approve
Approve or reject a checked OrderTicket without executing it after risk review, policy review, restricted-list checks, and creator-versus-approver separation.
tcx-policy
Review workspace policy readiness before approval, including restricted lists, adapter eligibility, notional limits, approval readiness, information barriers, and audit gaps.