compliance-audit

compliance-audit is a skill for Claude Code, Codex from lukedj78/dev-flow. It costs 215 tokens per session (2,367 once invoked), scanned A, original, MIT.

A code review for privacy and artificial-intelligence regulations in the European Union, mainly the GDPR and EU AI Act. It checks an existing web, mobile, or agent project against a set of engineering risks and can apply some fixes.

In plain words
What is it for?
Use it to inspect an existing project, produce a compliance report, and implement safe technical mitigations where appropriate.
Why use it?
It helps find missing data export and deletion, consent, retention, data-location, privacy, and AI-transparency safeguards before release. Legal professionals still need to confirm the legal interpretation.

Skill for Claude CodeCodex

Part of the dev-flow plugin — 46 skills shipped together

Install

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.

agentmods
npx agentmods add skills/lukedj78/dev-flow/compliance-audit
Any agent
npx skills add lukedj78/dev-flow --skill compliance-audit
Clone the repo
git clone --depth 1 https://github.com/lukedj78/dev-flow

Made for: Claude Code, Codex.

Or install dev-flow, the plugin that ships this one along with the rest of its 46 skills.

Wrote 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.

agentmods badge for compliance-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/lukedj78/dev-flow/compliance-audit.svg)](https://agentmods.dev/skills/lukedj78/dev-flow/compliance-audit)
Your own site
<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>
Per session 215 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash 44a3acdf5f8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/scan.py, scripts/test_scan.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

compliance-audit/SKILL.md · 109 lines

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 — see references/contracts.md § nextjs_version. Don't duplicate the check here; when auditing a web project, read meta.json#history for a recent vercel-deploy run 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.

Read the full file on GitHub · 109 lines

Files

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.

Changes

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.

  1. 4d ago First seen · 109 lines · 215 tokens per session scan A 44a3acdf5f8c

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories