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 rules/thesethrose/devrules/compliance-checkgit clone --depth 1 https://github.com/TheSethRose/DevRulesWhat 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 | $0.00048 | $0.01187 |
| Opus 5 | $0.00024 | $0.00593 |
| Sonnet 5 | $0.00010 | $0.00237 |
| Haiku 4.5 | $0.00005 | $0.00119 |
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.
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.
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.
- yesterday First seen · 73 lines · 48 tokens per session scan A 9f31a3b8d19b
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.
Other cursor rules, from other repositories
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, and multi-package management.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
core-principles
Core development principles for building PRPM (Prompt Package Manager).
creating-kiro-agents
Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.