check-compliance

check-compliance is a skill for Claude Code, Codex from stunt-double/stuntdouble-mcp. It costs 43 tokens per session (833 once invoked), scanned A, original, MIT.

A review of a product against specified legal and regulatory requirements, such as cookie consent, privacy access, disclosures, and unsubscribe processes. It collects observations and evidence for a lawyer or compliance team.

In plain words
What is it for?
Use it to check a live product against requirements for the jurisdictions and rules you specify, then prepare findings for counsel to review.
Why use it?
It helps find missing or broken compliance-related flows before release. It does not decide what the law means or provide legal advice.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to check a live product against requirements for the jurisdictions and rules you specify, then prepare findings for counsel to review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stunt-double/stuntdouble-mcp/check-compliance
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.

Any agent
npx skills add stunt-double/stuntdouble-mcp --skill check-compliance
Clone the repo
git clone --depth 1 https://github.com/stunt-double/stuntdouble-mcp

Made for: Claude Code, Codex.

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 check-compliance

README.md
[![agentmods](https://agentmods.dev/badge/skills/stunt-double/stuntdouble-mcp/check-compliance/github.svg)](https://agentmods.dev/skills/stunt-double/stuntdouble-mcp/check-compliance)
Your own site
<a href="https://agentmods.dev/skills/stunt-double/stuntdouble-mcp/check-compliance"><img src="https://agentmods.dev/badge/skills/stunt-double/stuntdouble-mcp/check-compliance/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.

agentmods 80×15 button for check-compliance

Your own site · 80×15
<a href="https://agentmods.dev/skills/stunt-double/stuntdouble-mcp/check-compliance"><img src="https://agentmods.dev/badge/skills/stunt-double/stuntdouble-mcp/check-compliance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 833 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00043 $0.00833
Opus 5 $0.00022 $0.00417
Sonnet 5 $0.00009 $0.00167
Haiku 4.5 $0.00004 $0.00083

Measured 12d ago against content hash 9d53504d825e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

check-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 12d 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.

skills/check-compliance/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Check compliance

When to use

  • You need evidence of whether a product meets stated legal or regulatory requirements
  • A release or content change may have affected consent, disclosures, or required flows
  • You want compliance regressions caught continuously, not discovered in an audit

Important framing

This produces evidence for the team and their counsel to review. It is not legal advice. Present findings as observations against the stated requirements, never as legal conclusions. Do not guess which jurisdictions or regimes apply — ask.

Instructions

  1. Resolve context:

    • list_workspaces() → pick the workspace
    • list_projects(workspace_id) → match the URL to a project, or let create_checklist find/create it
  2. Confirm the requirements in scope:

    • If none were supplied, ask which regimes apply (e.g. GDPR cookie consent, AU Consumer Law pricing, financial-services disclaimers) before running
  3. Set up a compliance-reviewer actor and record the requirements:

    • list_actors(workspace_id), else create_actor(...)
    • add_project_guideline(project_id, category: "compliance", content, title), one obligation per guideline so a finding can name the requirement it breaks. Check list_workspace_guidelines(workspace_id) first: an obligation that applies to several products is one rule attached to each with set_project_guideline
  4. Create a checklist that exercises behaviour, not just presence:

    • "A cookie banner appears before any non-essential tracking and the reject option works"
    • "Privacy policy and terms are reachable from every page footer"
    • "Prices include mandatory taxes or state clearly that they do not"
    • "Required disclaimers appear adjacent to the claims they qualify"
    • "The signup flow states how personal data will be used"
    • If email flows are in scope, actors have their own inboxes: include "Marketing emails contain a working unsubscribe link"
  5. Run and keep the evidence:

    • run_checklist(checklist_id) → poll get_checklist_run(run_id) until terminal
    • On anything ambiguous, quote exactly what the page showed

Read the full file on GitHub · 68 lines

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. 12d ago First seen · 68 lines · 43 tokens per session scan A 9d53504d825e

Subscribe to this mod's changes

check-compliance is a skill published in the GitHub repository stunt-double/stuntdouble-mcp (1 stars, last pushed 27d ago), licensed MIT. It adds 43 tokens to every session and 833 once invoked, about $0.0002 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

yuwen-publish-precheck

A Chinese-language review workflow for checking content before publishing it on Douyin, Xiaohongshu, or WeChat Channels.

yuwen-cool/yuwen-publish-precheck · 206 tokens

lov-china-website-filing

A workflow for preparing and launching websites in mainland China, including ICP filing and public-security filing. ICP filing is the registration required for many mainland websites, while public-security filing is a separate police registration.

lovstudio/skills · 75 tokens

contract-review-pro

Professional-grade contract review skill that adds comment-based issue annotations without changing original text. Enforces a four-layer review (entity verification, basic, business, legal), writes structured comments (issue type, risk reason, revision suggestion) with risk level encoded via reviewer name, and…

lovstudio/skills · 85 tokens

telnyx-email-suppressions-curl

Manage email suppressions (blocks), import and export suppression lists, and manage unsubscribe groups. Use for deliverability compliance and bounce handling.

team-telnyx/ai · 37 tokens

healthcare-providers-verify

Validates practitioner credentials and license status against the NPI registry. Cross-references specialties, credentials, and practice addresses against official records. Returns Verified / Partially Verified / Unverified / Flagged per practitioner with mismatch details and source URLs. Triggers: "verify these…

Nimbleway/agent-skills · 186 tokens

python-packaging-license-finder

Use this skill to deterministically find license information for Python packages by checking PyPI metadata first, then falling back to Git repository LICENSE files using shallow cloning.

opendatahub-io/ai-helpers · 38 tokens