Borrowing it
Nothing to install: this file belongs to vaquarkhan/compliance-agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vaquarkhan/compliance-agent-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/vaquarkhan/compliance-agent-skillsWrote 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.
[](https://agentmods.dev/instructions/vaquarkhan/compliance-agent-skills/agents-md)<a href="https://agentmods.dev/instructions/vaquarkhan/compliance-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/vaquarkhan/compliance-agent-skills/agents-md/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.
<a href="https://agentmods.dev/instructions/vaquarkhan/compliance-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/vaquarkhan/compliance-agent-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01565 | $0.01565 |
| Opus 5 | $0.00783 | $0.00783 |
| Sonnet 5 | $0.00313 | $0.00313 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade A, and why
compliance-agent-skills AGENTS.md 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 9d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Compliance Agent Entry Point
This file is the primary routing document for AI coding agents working in this repository. Read it before loading any skill.
Mission
Execute deterministic USA compliance audits across HIPAA, HITECH, PCI-DSS v4.0, SOC 2, ISO 27001, NIST CSF 2.0, NIST AI RMF, FERPA, COPPA, CCPA/CPRA, US state privacy laws, GDPR, FedRAMP, SOX, CMMC, and GLBA/FFIEC without inventing regulatory requirements. All user-provided text passes through PHI redaction (redaction.py) before LLM reasoning.
Mandatory rules
- Load skills progressively — use
using-compliance-agent-skillsfor routing; then load exactly one primary framework skill per audit thread. - Never reconstruct redacted tokens (
<PERSON_1>,<US_SSN_1>) unless using the authorizeddeanonymize_responsetool inagent.py. - Cite authoritative sources — CFR, PCI-DSS v4.0, AICPA TSC. Do not fabricate requirement numbers.
- Emit auditable artifacts — scope JSON, evidence manifests with SHA-256 hashes, remediation trackers.
- Respect lifecycle order when possible:
/scope→/audit→/evidence→/remediate→/report.
Skill routing
| Signal in user request | Primary skill |
|---|---|
| Broad / unclear framework | using-compliance-agent-skills |
| PHI, ePHI, BAA, Security Rule | hipaa-technical-safeguards, hipaa-phi-redaction-pipeline, or hipaa-baa-vendor-assessment |
| Payment scripts, checkout, Req 6.4.3 | pci-dss-script-audit |
| CDE, firewall, segmentation | pci-dss-network-segmentation |
| TSC mapping, SOC 2 scope | soc2-trust-services-criteria |
| Audit binder, screenshots | soc2-evidence-collection |
| Continuous monitoring | soc2-ccm-continuous-monitoring |
| IAM, MFA, RBAC | access-control-identity-audit |
| Logs, SIEM, Req 10 | audit-logging-integrity |
| Breach, incident notification | breach-incident-response |
| HITECH breach / OCR portal | hitech-breach-notification |
| US state privacy (VCDPA, CPA, TDPSA) | us-state-privacy-laws |
| GDPR / EU transfers (US multinational) | gdpr-us-multinational |
| Vendor SOC reports | vendor-third-party-risk |
| OPA, Terraform, policy-as-code | compliance-as-code-governance |
| MCP server hardening | mcp-compliance-integration |
| ISO 27001 Annex A / SoA | iso27001-annex-a-controls |
| NIST CSF 2.0 gap assessment | nist-csf-2-assessment |
| CCPA/CPRA, DSAR, California privacy | ccpa-cpra-privacy-rights |
| PCI encryption, PAN, key management | pci-dss-encryption-key-management |
| HIPAA minimum necessary / de-id | hipaa-privacy-minimum-necessary |
| FedRAMP Moderate / NIST 800-53 | fedramp-moderate-baseline |
| SOX ITGC / SOX 404 | sox-itgc-audit |
| CMMC / CUI / NIST 800-171 | cmmc-nist-800-171 |
| GLBA / FFIEC financial privacy | glba-ffiec-financial-privacy |
| NIST AI RMF / trustworthy AI | nist-ai-rmf-governance |
| FERPA / education records / EdTech | ferpa-education-records |
| COPPA / under-13 / child-directed app | coppa-children-privacy |
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.
- 9d ago First seen · 110 lines · 1,565 tokens per session scan A d84b2eb6b54a
compliance-agent-skills AGENTS.md is an instructions file published in the GitHub repository vaquarkhan/compliance-agent-skills (2 stars, last pushed 16d ago), licensed MIT. It adds 1,565 tokens to every session, about $0.0078 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.