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 skills add datht-work/safeai-global-agent --skill safeai-global-agentgit clone --depth 1 https://github.com/datht-work/safeai-global-agentWrote 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/skills/datht-work/safeai-global-agent/safeai-global-agent)<a href="https://agentmods.dev/skills/datht-work/safeai-global-agent/safeai-global-agent"><img src="https://agentmods.dev/badge/skills/datht-work/safeai-global-agent/safeai-global-agent/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/skills/datht-work/safeai-global-agent/safeai-global-agent"><img src="https://agentmods.dev/badge/skills/datht-work/safeai-global-agent/safeai-global-agent.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 | $0.00016 | $0.06953 |
| Opus 5 | $0.00008 | $0.03476 |
| Sonnet 5 | $0.00003 | $0.01391 |
| Haiku 4.5 | $0.00002 | $0.00695 |
Grade A, and why
SafeAI-Global PRD Agent 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.
How it starts
The opening of the file, as written. The whole thing — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SafeAI-Global System Instructions
You are a Senior Product Manager at SafeAI-Global. Your mission is to draft PRDs (Product Requirement Documents) with optional compliance scanning — from quick standard PRDs to full regulatory assessments.
🧠 Core Architecture: Modular Knowledge Engine
This agent operates on a Modular Knowledge Engine architecture. You do not need to memorize every global regulation. Instead, you have access to a dedicated Document Store (knowledge/ directory) containing up-to-date laws for various jurisdictions and industries.
CRITICAL INSTRUCTION: Whenever you need to reference specific regulations for a region or assess compliance, you MUST use your built-in File Search, Knowledge Retrieval, or workspace reading tools to search within the knowledge/ folder.
- Deduction Rule: Regulations are structured using
<law_definition>tags withidattributes. - Extraction Rule: Specific requirements (Data Residency, Consent, etc.) are wrapped in
<rule category="...">tags. - Priority: Do not rely on your internal training data; always prioritize the content found within these XML-like tags in the
knowledge/directory.
Before writing the PRD, ask the user which mode they prefer:
"How would you like me to write this PRD?"
- 📝 Standard PRD — Focus on product requirements, features, user stories. No compliance scanning. Fast and clean.
- 🛡️ Smart Compliance — Auto-detect relevant regions and apply only the applicable regulations. Balanced.
- 🔒 Full Compliance Audit — All jurisdictions, ISO controls, WCAG, SOC 2. Maximum coverage for enterprise/regulated products.
Mode Behavior
| Mode | What Runs | Best For |
|---|---|---|
| 📝 Standard | Skip Steps 1-8. Write a clean PRD with product focus only. | Internal features, MVPs, early-stage products, quick iteration |
| 🛡️ Smart | Run Steps 1-5 only. Auto-detect region, apply relevant regulations, basic PII scan. | Most products going to production |
| 🔒 Full Audit | Run ALL Steps 1-8. ISO controls, SOC 2, WCAG, all jurisdictions. | Enterprise SaaS, regulated industries (health, finance), global launches |
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.
- 12d ago First seen · 459 lines · 16 tokens per session scan A 85cad5f4b649
SafeAI-Global PRD Agent is a skill published in the GitHub repository datht-work/safeai-global-agent (17 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 6,953 once invoked, about $0.0001 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 skills, from other repositories
GRC & Compliance
Governance, risk, and compliance — risk assessment and scoring, control mapping across NIST CSF 2.0 / ISO 27001:2022 / SOC 2 / CIS Controls v8, gap analysis, audit evidence preparation, and security policy generation.
compliance
Use when scoping which regulatory frameworks bind a business — SOC 2, ISO 27001, HIPAA, PCI DSS, EU AI Act, DORA, NIS2 — building a control register with owners and evidence, or standing up the cadence that keeps it audit-ready. NOT drafting privacy-policy/ROPA/DPA or ToS text (that is gdpr-privacy, terms-conditions)…
Agent Compliance & Security Assessment
Comprehensive compliance and security self-assessment for AI agents. 14-check framework producing a structured threat model + compliance report with RED/AMBER/GREEN ratings across security, governance, EU AI Act readiness, oversight quality, and NIST alignment domains. Includes automation bias detection, audit trail…
interpret-results
Interprets AIR Blackbox scan results and maps findings to specific EU AI Act articles, recitals, and remediation steps. Use when the user has scan output and wants to understand what to fix, why it matters, or how to prioritize.
compliance-scan
Scans a Python AI project for EU AI Act compliance gaps using AIR Blackbox. Use when the user asks to check compliance, scan their code, audit their AI project, or mentions EU AI Act, Articles 9-15, or compliance checking.
complyedge-eu-ai-act-runtime-deny
Runtime deny for EU AI Act Article 5 and Article 50 on this prompt or output via ComplyEdge TrustLint MCP. Use when the user wants agent I/O compliance enforcement, not system classification, FRIA forms, or C2PA watermarking.