Borrowing it
Nothing to install: this file belongs to miikkij/aimeat-protocol. 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/miikkij/aimeat-protocol/main/.claude/skills/security-audit/SKILL.mdgit clone --depth 1 https://github.com/miikkij/aimeat-protocolWrote 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/miikkij/aimeat-protocol/security-audit)<a href="https://agentmods.dev/skills/miikkij/aimeat-protocol/security-audit"><img src="https://agentmods.dev/badge/skills/miikkij/aimeat-protocol/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/miikkij/aimeat-protocol/security-audit"><img src="https://agentmods.dev/badge/skills/miikkij/aimeat-protocol/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 | $0.00072 | $0.04510 |
| Opus 5.5 | $0.00029 | $0.01804 |
| Sonnet 5.5 | $0.00014 | $0.00902 |
| Haiku 4.5 | $0.00007 | $0.00451 |
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 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.
This is a copy
100% identical to security-audit — 34 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit
AIMEAT: before anything else, read AIMEAT-PURPOSE.md in this folder, and put its path in the brief of every agent you delegate to (hunter, verifier, critic, fix). It applies in both modes: a fix makes a use safe and never removes the use.
Find vulnerabilities that violate a real trust boundary, then give owners the source evidence, safe reproduction, priority, and smallest effective fix. This is a defensive, source-first workflow. A candidate without a concrete affected principal, resource, or security outcome is not a confirmed finding.
Operating modes
This skill is guidance by default. Loading it does not authorize the complete audit workflow or file creation.
- Guidance mode: For security questions, focused reviews, methodology, triage, or investigation of specific findings, use only the relevant parts of this skill. Do not automatically run all six phases, create an output directory, or write audit artifacts. You may launch focused agents when useful; they return results to the current task.
- Full audit mode: Use the complete workflow when the user explicitly asks to audit or pen-test a codebase, asks for a full, comprehensive, or end-to-end security review, or requests report artifacts. Run all six phases and write the files defined below.
If the request could mean either mode, ask one focused question before creating files or starting the complete workflow.
Platform terminology
This skill is agent-neutral:
- Parent is the agent that coordinates the run and owns shared state.
- Task tool is the platform's delegation or sub-agent mechanism.
researchagent is a delegated agent for focused source exploration and factual verification.generalagent is a delegated agent for broad investigation and bounded local execution.subagent_type:in a heading names which of these two delegated agent roles runs that work.
Use equivalent platform capabilities while preserving role, write-isolation, prompt, and independence boundaries.
What ships with it
23 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.
- AI-AND-LLM.md 10 KB
- AIMEAT-PURPOSE.md 7.7 KB
- ATTACK-CLASSES.md 15 KB
- CLIENT-SIDE.md 8.4 KB
- CLOUD-AND-DEPLOYMENT.md 8.1 KB
- DATA-ISOLATION-AND-LIFECYCLE.md 7.6 KB
- DESKTOP-MOBILE-AND-LOCAL-IPC.md 8.5 KB
- HUNTING.md 22 KB
- LICENSE 1.1 KB
- MEMORY-SAFETY-AND-BINARY.md 10 KB
- PROTOCOLS-RPC-AND-MESSAGING.md 7.3 KB
- RECONNAISSANCE.md 16 KB
- report-schema.json 14 KB
- RESOURCE-EXHAUSTION-AND-AVAILABILITY.md 7.3 KB
- SUPPLY-CHAIN-AND-RELEASE.md 7.1 KB
- UPSTREAM.md 3.7 KB
- validate-coverage-ledger.cjs 33 KB runs code
- validate-coverage-ledger.test.cjs 28 KB runs code
- validate-findings.cjs 28 KB runs code
- validate-findings.test.cjs 26 KB runs code
- VALIDATION-AND-REPORTING.md 17 KB
- WEB-PROTOCOL-AND-AUTH.md 12 KB
- windows-validate.cjs 2.7 KB runs code
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 Changed · +2 lines 161d67d1e9df
- 9d ago First seen · 193 lines · 72 tokens per session scan A f13db00a766c
security-audit is a skill published in the GitHub repository miikkij/aimeat-protocol (10 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 4,510 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to security-audit, differing in 34 lines, and is treated as a copy.
Other skills, from other repositories
coordinate-agent-work
Coordinate independent coding or research agents across host sessions and linked Git worktrees through AgentTool Collab's local journal. Use when starting or resuming credential-bound coordination, splitting parallel work, claiming before overlapping edits, polling or acknowledging events, attaching evidence…
capability-conductor
A guide for finding and combining existing agent skills for one task while keeping track of where each skill came from and what limits it has.
nen-math-card
Frame a mathematical challenge as a bounded proof, model, or measurement inquiry and decide whether it can construct, repair, choose, or clarify anything. Use when a user asks whether a math problem is useful, wants to turn a competition or puzzle into reusable understanding, needs to separate formal proof from world…
nen-common-ground
Model several explicitly stated decision boundaries as convex feasible regions and return either shared room, a small conflict witness, or an honest refusal of the model. Use when the user invokes Helly, common-ground geometry, 共域, local-to-global agreement, constraint reconciliation, or a KINGDOM challenge about…
scriptwriter-room
Focused on writers' room operations — creating rooms with a seed prompt, contributing signed scenes/dialogue/stage-directions/twists/chaos-cards/notes, subscribing to the SSE live stream, polling for new contributions. Use when the user wants to actually draft something with peers, draw a chaos card to seed a scene…
scriptwriter-rrr
Focused on the REAL RECOGNISE REAL cascade flow specifically — opening cascades with a peer, escalating depth, verifying chains, surfacing wall refusals with their meaning. Use when the user explicitly references RRR depth, cascade verification, alternation walls, or the "I know you know I know" mutual-recognition…