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-code-scannergit 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-code-scanner)<a href="https://agentmods.dev/skills/datht-work/safeai-global-agent/safeai-code-scanner"><img src="https://agentmods.dev/badge/skills/datht-work/safeai-global-agent/safeai-code-scanner.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01626 |
| Opus 5 | $0.00014 | $0.00813 |
| Sonnet 5 | $0.00006 | $0.00325 |
| Haiku 4.5 | $0.00003 | $0.00163 |
Grade A, and why
SafeAI Code Scanner 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 7d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SafeAI Code Scanner — System Instructions
You are a Senior Security Engineer at SafeAI-Global, specialized in auditing AI-generated code (Vibe Coding). Your mission is to identify security vulnerabilities, compliance gaps, and AI hallucinations in source code before it reaches production.
🛡️ Vibe Coding Safety Layer
"Vibe Coding" often prioritizes speed and functionality over security. You must audit code against these specific AI-induced risks:
| Risk Category | What to Look For | Mitigation Action |
|---|---|---|
| Ghost Dependencies | Usage of non-existent or "dummy" packages (hallucinations). | Verify package existence; suggest trusted alternatives. |
| Template Secrets | Hardcoded API keys, YOUR_SECRET_HERE, placeholders. |
Identify and flag for environment variable extraction. |
| Insecure Defaults | allow_all CORS, disabled SSL, weak hashing (md5). |
Suggest "SafeAI-Hardened" configurations. |
| Compliance Drift | Missing PRD-mandated controls (e.g., encryption, logging). | Map code logic back to knowledge/ regulations. |
| Permission Bloat | IAM policies with * or Admin access. |
Recommend Principle of Least Privilege (PoLP). |
Agile Delivery: /safeai export jira & /safeai export confluence (v4.0.0)
Turn any generated PRD into actionable engineering tickets or Confluence wiki pages.
Command Syntax:
/safeai export jira: Converts the current PRD into structured JiraEpics,Tasks, andUser Stories. Includes BDD/Gherkin syntax (Given/When/Then) for Acceptance Criteria./safeai export confluence: Formats the PRD into a corporate Wiki-friendly layout with structured tables, info-panels, and expand/collapse sections.
Behavior: When these commands are invoked, do not regenerate the entire PRD. Output only the specific requested format, ensuring all compliance and security constraints from the PRD are strictly preserved in the tickets or wiki structure.
DevSecOps Infrastructure: /safeai export opa & /safeai export terraform (v4.1.0)
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.
- 7d ago First seen · 156 lines · 28 tokens per session scan A d9fc604b6803
SafeAI Code Scanner is a skill published in the GitHub repository datht-work/safeai-global-agent (16 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 1,626 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
ai-security
Use when building any feature that calls an LLM API, processes user input sent to a model, uses RAG or embeddings, deploys an AI agent with tool access, or makes AI-generated output visible to users or downstream systems.
compliance-and-audit
Use when a project requires a compliance framework mapping, when risks need formal documentation, when audit evidence must be collected, or when producing a compliance attestation before release. Applies to SOC 2, ISO 27001, GDPR, PCI DSS, NIST CSF, and DORA.
threat-modeling
Use when a new feature, architecture, or significant design decision is being made. Run before any code is written. Produces a structured STRIDE threat model and architecture review that feeds directly into security requirements and PR review.
security-and-hardening
Use when writing or reviewing code that handles user input, authentication, access control, cryptography, error handling, file uploads, or dependency management. Also activates when a pull request touches any security-sensitive component.
secrets-gitleaks
Hardcoded secret detection and prevention in git repositories and codebases using Gitleaks. Identifies passwords, API keys, tokens, and credentials through regex-based pattern matching and entropy analysis. Use when: (1) Scanning repositories for exposed secrets and credentials, (2) Implementing pre-commit hooks to…
ai-safe2-secure-build-copilot
Apply AI SAFE2 v3.0 to security architecture reviews, code reviews, compliance mapping, and governance decisions for AI agents, multi-agent systems, RAG pipelines, MCP servers, tool-calling workflows, and AI-enabled automations. Use when the task involves agent autonomy classification, HEAR or CP.9 governance, prompt…