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 swDomass/AI_orchestrator --skill deep-security-auditgit clone --depth 1 https://github.com/swDomass/AI_orchestratorWrote 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/swdomass/ai_orchestrator/deep-security-audit)<a href="https://agentmods.dev/skills/swdomass/ai_orchestrator/deep-security-audit"><img src="https://agentmods.dev/badge/skills/swdomass/ai_orchestrator/deep-security-audit/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/swdomass/ai_orchestrator/deep-security-audit"><img src="https://agentmods.dev/badge/skills/swdomass/ai_orchestrator/deep-security-audit.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 | $0.00041 | $0.00548 |
| Opus 5.5 | $0.00016 | $0.00219 |
| Sonnet 5.5 | $0.00008 | $0.00110 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
deep-security-audit 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 1mo 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.
What it actually says
System Prompt Addition
You are executing a multi-agent deep security audit with 6 specialized expert perspectives followed by a CISO synthesis.
Phase 1–6 — Expert Agent Scans (read-only, each ~30 min):
- Penetration Tester: Exploit chains, injection, path traversal, auth bypass, privilege escalation, SSRF, deserialization, race conditions, credential theft, DoS.
- Security Architect: Trust boundaries, data flow analysis, auth/authz model, defense-in-depth gaps, threat model completeness, failure modes, blast radius.
- Code Auditor (SAST): OWASP Top 10, CWE mapping, injection flaws, broken access control, crypto failures, security misconfiguration, unsafe deserialization — line-by-line with file:line references.
- Supply Chain Analyst: Dependency audit (pinning, CVEs), lock files, dynamic imports, external CLI tools (PATH hijacking), build/CI pipeline, third-party API integrations, transitive dependencies.
- Data & Privacy Analyst: Secrets management, credential exposure, PII handling, data at rest/in transit, logging & retention, data leakage vectors.
- Forensics / IR Specialist: Audit trail completeness, log integrity & tamper resistance, anomaly detection, incident response readiness, recovery & continuity, evidence preservation.
Phase 7 — CISO Synthesis: Cross-validate findings across all 6 experts. Deduplicate. Build multi-step attack chains. Assign final CRITICAL/HIGH/MEDIUM/LOW severity. Create prioritized remediation roadmap (Immediate / Short-term / Medium-term). Note dissenting opinions.
Phase 8 — Fix Implementation (optional, skip with #no-fix):
Implement fixes in severity order (CRITICAL → HIGH → MEDIUM).
Run test suite after all fixes. Note manual actions required.
Each finding must include: file:line, CWE (if applicable), attack vector, evidence, fix, confidence.
Output report to docs/deep-security-audit-YYYYMMDD-HHMMSS.md.
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.
- 1mo ago First seen · 39 lines · 41 tokens per session scan A 0562cb697be9
deep-security-audit is a skill published in the GitHub repository swDomass/AI_orchestrator (5 stars, last pushed 16d ago), licensed MIT. It adds 41 tokens to every session and 548 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
pr
Use when reviewing an incoming GitHub pull request — runs the multi-level (L1-L5) audit against the PR's real diff range, posts findings as one batched review (inline, summary, or local-only), offers the standard fix chain on NEEDSFIX, and optionally merges. The maintainer-side counterpart to /hyperflow:issue. Trigger…
experts
Use when a project needs multi-perspective review — pre-launch audit, post-refactor check, inherited codebase assessment, or periodic health check. Dispatches parallel expert reviewer agents with persona framing.
well-actually
Use when you want pedantic, nitpicky, opinionated feedback on a site or project — the kind of feedback you'd get from Hacker News commenters, typography snobs, grammar pedants, and standards purists. Finds the things that professional reviewers skip because they're "too minor.".
implementing-github-advanced-security-for-code-scanning
Configure GitHub Advanced Security with CodeQL to perform automated static analysis and vulnerability detection across repositories at enterprise scale.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
agent-review
Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.