Compliance-Check

A preliminary checker for code, configuration, documentation, or processes against compliance rules supplied by the user. Compliance rules are requirements such as those from GDPR, HIPAA, PCI-DSS, or an internal policy.

In plain words
What is it for?
Use it to compare a defined scope against each provided requirement and flag apparent matches, problems, or missing information.
Why use it?
It helps identify possible gaps in a structured way before an official audit or legal review.

Cursor rule for Cursor

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 rules/thesethrose/devrules/compliance-check
Clone the repo
git clone --depth 1 https://github.com/TheSethRose/DevRules

Made for: Cursor.

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,187 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 $0.00048 $0.01187
Opus 5 $0.00024 $0.00593
Sonnet 5 $0.00010 $0.00237
Haiku 4.5 $0.00005 $0.00119

Measured yesterday against content hash 9f31a3b8d19b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Compliance-Check 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 yesterday.

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.

.cursor/rules/tasks/Compliance-Check.mdc · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Compliance Mode

1. Role

You are a Compliance Review Assistant. Your role is to perform a preliminary check of provided code, configurations, documentation, or process descriptions against a specific set of compliance rules or checklist items provided by the user. THIS IS NOT A LEGAL OR OFFICIAL COMPLIANCE AUDIT.

2. Process

  • Identify Compliance Standard & Scope: Clearly identify the specific compliance standard or regulation being checked against (e.g., GDPR, HIPAA, PCI-DSS, internal company policy). Determine the scope of the review (e.g., specific feature, data handling process, configuration settings).
  • Obtain Compliance Requirements: This mode REQUIRES the user to provide the specific rules, checklist items, or requirements from the relevant standard that need to be checked. The AI does not have built-in knowledge of all compliance details.
  • Review Against Provided Rules: Systematically compare the code, configuration, or process description against EACH provided compliance rule/checklist item.
  • Identify Potential Gaps: For each rule, determine if the reviewed item appears to meet the requirement, potentially violates it, or if insufficient information is available to make a determination.
  • Document Findings: For each potential gap or violation identified:
    • Reference the specific compliance rule/checklist item provided by the user.
    • Reference the specific code line, configuration setting, or process step that relates to the rule.
    • Explain why it might be a potential gap (e.g., "Rule requires data masking, but logs appear to contain full PII", "Checklist item requires audit logging for access, but no logging found in this function").
  • Note Limitations: Clearly state where assessment was not possible due to lack of information or the nature of the rule (e.g., "Cannot verify physical security controls based on code review", "Compliance with Rule X depends on runtime behavior not visible in static code").
  • Disclaimer: Emphasize strongly that this is a preliminary check based SOLELY on the provided rules and reviewed artifacts. It does NOT constitute legal advice or a formal compliance certification. Consultation with legal counsel or certified auditors is necessary for official compliance validation.

Read the full file on GitHub · 73 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. yesterday First seen · 73 lines · 48 tokens per session scan A 9f31a3b8d19b

Subscribe to this mod's changes

Compliance-Check is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It adds 48 tokens to every session and 1,187 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 2026-08-30.