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/fmflurry/settings-opencode/gdpr-compliancenpx skills add fmflurry/settings-opencode --skill gdpr-compliancegit clone --depth 1 https://github.com/fmflurry/settings-opencodeWhat 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 | $0.00088 | $0.10096 |
| Opus 5 | $0.00044 | $0.05048 |
| Sonnet 5 | $0.00018 | $0.02019 |
| Haiku 4.5 | $0.00009 | $0.01010 |
Grade A, and why
gdpr-compliance 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 — 656 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GDPR Compliance Reference & Code Audit Checklist
FRANCE / CNIL-Focused Edition
This skill provides foundational GDPR knowledge, actionable CNIL compliance requirements, and a concrete code-audit checklist for auditing data-protection compliance in French companies. Reference this alongside the gdpr-specialist agent when reviewing code or building data-processing features.
Jurisdiction: France (EU member state); primary authority = CNIL (Commission Nationale de l'Informatique et des Libertés). Supplementary French law: Loi n°2018-493 (Code de la Protection des Données Personnelles); French Penal Code (Art. 226-16 to 226-24).
Legal Disclaimer: This is informational guidance, not legal advice. For jurisdiction-specific requirements or contested interpretations, consult a DPO, legal counsel, or CNIL (Phone: +33 1 53 73 22 22; Web: https://www.cnil.fr/).
1. Applicability
GDPR applies to:
- Any organization (any size, any industry) established in France/EU OR targeting EU residents
- Processing of both computerized AND paper data
- Any personal data (Art. 4(1)): any information relating to an identified or identifiable natural person
French Supplementary Law:
- Loi Informatique et Libertés (Art. 82 onwards): cookie/tracker consent rules (stricter than GDPR baseline)
- French Penal Code (Art. 226-16 to 226-24): criminal penalties for unauthorized processing, failure to inform, misuse of personal data
2. Six Core GDPR Principles (Art. 5) + Accountability (Art. 5(2))
| Principle | Requirement | Code Implication | Citation |
|---|---|---|---|
| Lawfulness (Art. 5(1)(a)) | One of 6 legal bases required (Art. 6) | Document which basis applies to each processing; enforce authorization checks in code | gdpr-info.eu/art-5-gdpr |
| Fairness (Art. 5(1)(a)) | Processing not deceptive/discriminatory | Audit ML models for bias; transparent data use | gdpr-info.eu/art-5-gdpr |
| Transparency (Art. 5(1)(a)) | Inform data subjects of collection, purpose, rights | Implement privacy notices, consent dialogs, data-subject-rights endpoints | gdpr-info.eu/art-5-gdpr |
| Purpose Limitation (Art. 5(1)(b)) | Data used only for stated purpose; repurposing needs fresh legal basis | Enforce audit logging; segregate use-case logic; don't share data across purposes without reconsent | gdpr-info.eu/art-5-gdpr |
| Data Minimization (Art. 5(1)(c)) | Collect only strictly necessary data | Remove unused fields; set default to minimal; challenge every PII field added | gdpr-info.eu/art-5-gdpr |
| Accuracy (Art. 5(1)(d)) | Keep data accurate & up-to-date | Provide rectification endpoint (PATCH /api/subject/data/{field}); flag stale data for user review | gdpr-info.eu/art-5-gdpr |
| Storage Limitation (Art. 5(1)(e)) | Define retention periods upfront; delete when objective met | Implement TTL/retention schema in database; automated deletion jobs; cleanup migrations | gdpr-info.eu/art-5-gdpr |
| Integrity & Confidentiality (Art. 5(1)(f)) | Proportional technical + organizational security measures | Encryption (TLS, at-rest), access control, logging, incident response, staff training | gdpr-info.eu/art-5-gdpr |
| Accountability (Art. 5(2)) | Demonstrate compliance with all principles above | Maintain Register of Processing Activities (RoPA); conduct DPIAs; document legal bases; keep audit trails (code-enforceable via logging, retention schema comments, consent records) | gdpr-info.eu/art-5-gdpr |
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 · 656 lines · 88 tokens per session scan A 0d7557958ebc
gdpr-compliance is a skill published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed 20d ago), licensed MIT. It adds 88 tokens to every session and 10,096 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
advogado-criminal
Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.
mod-actions
Comprehensive moderation toolkit: user actions (ban/mute/DM), strike system, image moderation, report handling, generation moderation, content/training moderation, and NCMEC/CSAM reporting. All via Civitai tRPC API.
auditing-part11-trails
Generates and verifies 21 CFR Part 11-style audit trails — who/what/when, electronic signatures, and tamper-evidence — for OpenMed pipelines in GxP and clinical-trial (GCP) settings. Use when the user runs OpenMed in a regulated/validated environment and needs an attributable, time-stamped, tamper-evident record of…
2026-legal-research-agent
Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape. Activate on "find expungement data", "scrape state laws", "legal research", "court URLs", "statute sources", "Clean Slate laws", "automatic…
amazon-suspension-appeal
Account suspension prevention and appeal — policy violations, Plan of Action writing, reinstatement process.
build-audit-logs
Build or review audit trails in TypeScript/JavaScript apps using evlog (pipelines, typed actions, denials, retention, compliance-style reviews). For application code, not for extending the evlog package.