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 kok-o/contextos-agents --skill security-auditgit clone --depth 1 https://github.com/kok-o/contextos-agentsWrote 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/kok-o/contextos-agents/security-audit)<a href="https://agentmods.dev/skills/kok-o/contextos-agents/security-audit"><img src="https://agentmods.dev/badge/skills/kok-o/contextos-agents/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/kok-o/contextos-agents/security-audit"><img src="https://agentmods.dev/badge/skills/kok-o/contextos-agents/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 | $0.00036 | $0.00994 |
| Opus 5.5 | $0.00014 | $0.00398 |
| Sonnet 5.5 | $0.00007 | $0.00199 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
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 today.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit
Find vulnerabilities that violate a real trust boundary, then give owners source evidence, safe reproduction, priority, and the smallest effective fix. This is a defensive, source-first workflow inspired by Cloudflare's security audit architecture.
Operating Modes
This skill operates in two distinct modes:
- Guidance Mode: For security questions, focused reviews, threat modeling, or triage of specific components, use only the relevant parts of this skill. Do not automatically create audit directories or write audit artifacts.
- Full Audit Mode: Use the complete workflow when explicitly requested to audit, pen-test, or perform an end-to-end security review of a repository. Run all phases and generate structured artifacts.
Adversarial Multi-Agent Audit Protocol
A core invariant of rigorous security auditing is adversarial verification:
- Separation of Hunter and Verifier:
- The agent that discovers a candidate vulnerability (Hunter) must never be the same agent that validates it.
- The verifying agent (Verifier) starts with a fresh context and explicitly attempts to disprove each finding.
- Evidence-Based Standard:
- A candidate vulnerability is confirmed only if it has a complete source trace from untrusted input to a sensitive sink, along with a bounded, observable defect.
- If an issue cannot be definitively reproduced or disproven locally, mark it as
needs_validationrather than creating speculative findings.
┌─────────────────────────────────────────────────────────────┐
│ SECURITY AUDIT PIPELINE │
│ │
│ Phase 1: Reconnaissance (Map trust boundaries & inputs) │
│ ↓ │
│ Phase 2: Coverage Hunting (Hunter agents search surfaces) │
│ ↓ │
│ Phase 3: Candidate Validation (Verifier agents disprove) │
│ ↓ │
│ Phase 4: Structured Output (findings.json & ledger) │
│ ↓ │
│ Phase 5: Record Verification (Final attestation review) │
│ ↓ │
│ Phase 6: Target-Neutral Reporting (REPORT.md) │
└─────────────────────────────────────────────────────────────┘
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 92 lines · 36 tokens per session scan A 84d914c0a3cf
security-audit is a skill published in the GitHub repository kok-o/contextos-agents (10 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 994 once invoked, about $0.0001 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 2026-10-25.
Other skills, from other repositories
ai-engineering-toolkit
6 production-ready 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.
gsap-scrolltrigger
Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…
threejs-geometry
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.
seedance-2-5
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…
comfyui
Use when working with ComfyUI workflows in OpenMontage, including comfyuiimage/comfyuivideo/comfyuimusic, custom workflowjson/workflowpath inputs, outputnode selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.
lyria
Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before calling OpenMontage googlemusic, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-generation failures, or preparing…