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 roedyrustam/vibes-plug --skill ai-safety-governance-expertgit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote 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/roedyrustam/vibes-plug/ai-safety-governance-expert)<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/ai-safety-governance-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/ai-safety-governance-expert/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/roedyrustam/vibes-plug/ai-safety-governance-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/ai-safety-governance-expert.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 | $0.00086 | $0.02533 |
| Opus 5.5 | $0.00034 | $0.01013 |
| Sonnet 5.5 | $0.00017 | $0.00507 |
| Haiku 4.5 | $0.00009 | $0.00253 |
Grade A, and why
ai-safety-governance-expert 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 4d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Safety, Governance, and Responsible AI Expert
English
Orchestration & Integration
- Prompt Defense & Firewalls:
prompt-injection-firewall,ai-prompt-engineering-expert - Red Teaming & Security:
autonomous-red-teamer,zero-trust-secret-vault - Compliance & Privacy:
compliance-gdpr-privacy-expert,formal-spec-z3-verifier - Model Evaluation & Memory:
ai-llm-integration-expert,session-memory-manager,agentic-memory-architect - Lifecycle & Hardening:
zero-to-prod-orchestrator,production-ready-hardener,anti-slop,brainstorming
1. Constitutional AI Enforcement
Define constitutional rules as structured guardrails for all AI operations. Implement policies at multiple interception points: pre-generation, post-generation, and retrieval.
Principles & Configuration
- Embed constitution directly into system prompts.
- Implement explicit Colang 2.0 flows for conversational state management.
- Abort sequences when user prompts violate strict constitutional principles.
# NeMo Guardrails configuration example (config.yml)
models:
- type: main
engine: openai
model: gpt-4o
rails:
input:
flows:
- check_jailbreak
- check_topic_restriction
output:
flows:
- check_hallucination
- check_toxicity
instructions:
- type: general
content: |
You are a helpful, respectful, and honest assistant.
Always prioritize safety, avoid giving harmful advice, and maintain neutrality.
2. Runtime Safety Guardrails / Pembatasan Keamanan Saat Berjalan
Implement layered defense mechanisms to intercept unsafe input and redact sensitive output. Utilize state-of-the-art moderation models such as Llama Guard 3.
Layered Defense Architecture
- System Prompt: Set boundaries and behavior guidelines.
- Input Filter: Scan for prompt injection, jailbreaks, and restricted topics (PII, hate speech).
- Model Generation: Generate response using the core LLM.
- Output Filter: Redact PII, filter toxicity, and enforce factuality checking.
- Delivery: Send safe response to the user.
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.
- 4d ago Changed · +14 lines · +86 tokens per session e50e2b38dad5
- 5d ago Changed · +2 lines · -86 tokens per session 1ed56763fb43
- 8d ago Changed 43e408f0d625
- 17d ago Changed 40482db64a0a
- 22d ago Changed 76757f858c4b
- 23d ago Changed 53ddec341e4f
- 25d ago Changed a9443ee89b4d
- 26d ago Changed · -6 lines · +70 tokens per session bf7b34dff679
- 27d ago Changed · +11 lines · -70 tokens per session f733fbb4ea50
- 1mo ago First seen · 219 lines · 86 tokens per session scan A 2ede75163535
ai-safety-governance-expert is a skill published in the GitHub repository roedyrustam/vibes-plug (113 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 2,533 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-prompt-regression-testing
Use when comparing prompt changes against a fixed evaluation set: record actual model settings, required checks, missing results, judge limitations and case-level regression evidence.
canon
Assessing standards, regulatory controls, and legal-document coverage with cited evidence and proposed wording. Use for OWASP/WCAG/SOC2/PCI/HIPAA or ToS/privacy/DPA reviews; not legal advice or code fixes.
cloak
Engineering privacy and data governance: PII detection, data flow mapping, consent patterns, GDPR/CCPA-compliant implementation, DPIA. Use when privacy-by-design is needed.
biomedical-engineer
Think and work like an expert Biomedical Engineer. Use when a task calls for Biomedical Engineer judgment. Reasons from ISO 14971 risk management, ISO 10993 biocompatibility matrices, ASTM F/ISO 14242 mechanical and wear testing, and FDA 510(k) substantial equivalence; treats stress shielding, UHMWPE osteolysis, F2129…
frontier
Execute any task at frontier quality. Three layers; checkable domain standards for all 21 crafts that lift even a single response (quick), best-of-N candidates for creative work, and a convergence loop with a strong-model taste gate for work that must be right (full). Self-contained; bundles the protocol, every craft…