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/tradebaas/groundwork/complynpx skills add Tradebaas/Groundwork --skill complygit clone --depth 1 https://github.com/Tradebaas/GroundworkWhat 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 | $0.00076 | $0.01255 |
| Opus 5 | $0.00038 | $0.00628 |
| Sonnet 5 | $0.00015 | $0.00251 |
| Haiku 4.5 | $0.00008 | $0.00126 |
Grade A, and why
comply 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
comply: legal is a gate, not a vibe
docs/compliance/COMPLIANCE.md holds the regimes and when they bite, the same in every project.
docs/compliance/REGISTER.md is this project's register: which of them apply here, status per
obligation, evidence per row. This skill fills and re-verifies both.
1. Determine what applies (per project, honestly)
Walk that trigger table against BRIEF.md and the actual system: personal data? (almost always yes: an email address is enough) → GDPR/AVG. AI features → AI Act, at minimum Art 50 transparency. Consumer-facing digital service/e-commerce → European Accessibility Act. Product with digital elements sold in the EU → CRA. Software placed on the EU market, which is virtually every shipped product → Product Liability Directive. Essential/important sector or supplier to one → NIS2. The client is a financial entity → DORA. Connected product, or a cloud/SaaS service a customer can switch away from → Data Act. Every dependency → its license.
2. Verify current state of the law
Regulations shift (every regime row carries its own last-verified date; they age). For each
applicable regime, confirm today's status via authoritative sources (EUR-Lex, the Commission's
pages, the AP (autoriteitpersoonsgegevens.nl) for NL) and update the dates in the regimes table.
Stamp today in Dates verified on the rows you actually checked, and leave the other rows'
stamps alone: a partial pass that stamps the whole table turns a stale row into a fresh-looking
one. Never assert a deadline or obligation from model memory. Deadline horizon: when any date
there falls within the next 60 days, re-verify that regime now instead of waiting for the
quarterly audit - rules move fastest just before they bite.
3. Apply per obligation: build it in, don't bolt it on
- GDPR/AVG: lawful basis named per processing purpose; data minimization in the schema
(collect nothing "for later"); records of processing (Art 30); DPIA if high-risk (Art 35);
data-subject rights executable (export, delete: actually implemented, not promised); the
retention periods recorded here honored to the end, the product's own retirement included
(
maintainowns that step); processor agreements for every third-party service touching personal data; EU data residency checked per service; breach path known (72h to the AP). - AI Act: users told they're interacting with AI; AI-generated content marked
machine-readably (Art 50, binding from 2026-08-02); high-risk uses (Annex III) identified
early. Obligations land 2027-12-02, design for them now, not then. Art 4 AI literacy:
docs/compliance/AI-LITERACY.mdis the evidence note; keep the register's literacy line true for this team and re-check the note at the quarterly audit. - Accessibility: EN 301 549 / WCAG 2.1 AA as the working floor (design-guard checks it per delivery; this skill checks the claim holds product-wide).
- CRA: scope before duties, because both the CRA and the PLD turn on the same test: supply in
the course of a commercial activity. Free and open-source software its maintainer does not
monetise is outside it, and paid services alongside a freely downloadable product or donations
that do not gate access do not change that; a paid edition, updates behind a payment, or other
services monetised through it do. A legal person sustaining such an unmarketed project intended
for commercial use is an open-source software steward instead (Art 24). Inside scope:
secure-by-default posture, and the vulnerability intake channel plus the support period
published in the root
SECURITY.md(ships as a working template; fill its marked TBD fields); actively exploited vulnerability → reporting duty via ENISA platform (from 2026-09-11). The regimes table's CRA row carries that scope test in full: settle it before writing a duty. - PLD: software is a product with no-fault liability; defectiveness includes cybersecurity
vulnerabilities, and damage covers users' destroyed or corrupted data. The CRA posture above
plus a proven restore path (
docs/operations/backup-restore.md) are the working defense. - DORA: the obligations arrive through the financial client's contract (Art 30: security measures, incident support, audit and access rights, exit strategy); check those clauses against what the product actually delivers and record any gap in the register.
- Data Act: a connected product is designed so its data reaches the user by default, not bolted on as an export later; a cloud/SaaS offering carries no switching barriers and an exit the customer can actually walk, contract terms and egress included.
- Licensing: every dependency's license compatible with the product's use and distribution; copyleft obligations honored; the register lists anything non-trivial.
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 · 77 lines · 0 tokens per session scan A 4408a4a335b3
comply is a skill published in the GitHub repository Tradebaas/Groundwork (2 stars, last pushed 7d ago), licensed MIT. It adds 76 tokens to every session and 1,255 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 2026-08-31.
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.