Borrowing it
Nothing to install: this file belongs to okuzpe/midas-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/okuzpe/midas-harness/main/.agents/skills/midas-security-audit/SKILL.mdgit clone --depth 1 https://github.com/okuzpe/midas-harnessWrote 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/okuzpe/midas-harness/midas-security-audit)<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-security-audit"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-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/okuzpe/midas-harness/midas-security-audit"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-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 | $0.00073 | $0.01724 |
| Opus 5 | $0.00036 | $0.00862 |
| Sonnet 5 | $0.00015 | $0.00345 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
midas-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 9d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
midas-security-audit — Deep Security Audit
Guard + state:
<paths.engine>/templates/skill-state-ritual.md(+AGENTS.md§ Safety / Path resolution). Readpaths.statefirst. Advanced, non-advancing audit — never auto-run.
Paths: Read
layout+pathsfrompaths.state. Substitute{runs}/→paths.runs,{product}/→paths.product. SeeAGENTS.md§ Path resolution.
Standalone security audit (analog of /midas-tribunal): orchestrate a recognized standard, run real tools for evidence, freeze ranked findings. Complements <paths.engine>/rules/security.md (Phase 8 floor) and /midas-tribunal security (debate lens).
Shared fragments: <paths.engine>/templates/audit-checklists.md (gate semantics, MIDAS_SECURITY_RESULT tally).
Does / Does not
| Does | Does not |
|---|---|
STRIDE + ASVS/Top10/LLM checklist with file:line evidence |
Advance stage or set gate: passed |
| Run installed scanners; recommend exact commands when absent | Block on missing tools |
Freeze {runs}/security/security-NN.md |
Invent severity when critical=0 high=0 |
Bridge findings → sprint tasks / ADR / open-questions.md |
Replace /close-sprint gate decision |
Standards (fetch current — never from memory)
- OWASP ASVS 5.0 — L1 (public/low-risk), L2 (default SaaS), L3 (payments/health/auth providers).
--leveloverrides; else recommend from data sensitivity. - OWASP Top 10 — broken access control, injection, crypto failures, SSRF, etc.
- OWASP LLM Top 10 + Agentic AI Top 10 — when product uses LLM/agent/RAG/tool-use: prompt injection, excessive agency, insecure output, etc.
Inputs
paths.state,{product}/architecture.md,{product}/business-plan.md,<paths.engine>/rules/security.md- Codebase: UI/API/data/auth, manifests, CI,
.mcp.json/ agent config
Procedure
1. Scope + ASVS level (recommend-don't-wall)
--scope default all. If --level absent, recommend L1/L2/L3 from data handled; proceed at recommendation (human may override). Flag AI-bearing products for LLM/Agentic lenses.
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.
- 9d ago First seen · 121 lines · 73 tokens per session scan A b9d420978291
midas-security-audit is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,724 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…