agent-audit

agent-audit is a skill for Claude Code from majiayu000/claude-skill-registry. It costs 69 tokens per session (3,200 once invoked), scanned A, original, MIT.

A skill for examining an LLM agent—an AI system that uses instructions and tools—to find which parts are actually needed.

In plain words
What is it for?
Use it when reviewing or inheriting an agent, measuring its behavior, reducing its size or cost, improving speed, or refactoring its design.
Why use it?
It helps uncover unused instructions, unnecessary tool calls, slow steps, repeated work, and avoidable model costs before production deployment.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Good fit Use it when reviewing or inheriting an agent, measuring its behavior, reducing its size or cost, improving speed, or refactoring its design.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/agent-audit-elliotjlt-claude-skill-potions
Install

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.

Any agent
npx skills add majiayu000/claude-skill-registry --skill agent-audit-elliotjlt-claude-skill-potions
Clone the repo
git clone --depth 1 https://github.com/majiayu000/claude-skill-registry

Made for: Claude Code.

Wrote 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.

agentmods badge for agent-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-audit-elliotjlt-claude-skill-potions/github.svg)](https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-audit-elliotjlt-claude-skill-potions)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-audit-elliotjlt-claude-skill-potions"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-audit-elliotjlt-claude-skill-potions/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.

agentmods 80×15 button for agent-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-audit-elliotjlt-claude-skill-potions"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-audit-elliotjlt-claude-skill-potions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,200 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.03200
Opus 5 $0.00034 $0.01600
Sonnet 5 $0.00014 $0.00640
Haiku 4.5 $0.00007 $0.00320

Measured 13d ago against content hash 433ca4afb85d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-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 13d 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.

skills/agent/agent-audit-elliotjlt-claude-skill-potions/SKILL.md · 434 lines

How it starts

The opening of the file, as written. The whole thing — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Audit

This skill treats agent optimization like dead code elimination: instrument, measure, identify what's actually used, strip the rest. The goal isn't "what could be useful" but "what's actually necessary."

When To Activate

Trigger when:

  • Inheriting or reviewing an existing agent
  • Agent costs are higher than expected
  • Agent is slower than it should be
  • "Can we make this cheaper/faster without breaking it?"
  • Preparing for production deployment
  • Refactoring agent architecture

The Audit Framework

Instructions

Step 1: Instrument the Agent

Before optimizing, understand current behavior. Add logging for:

INSTRUMENTATION CHECKLIST:

□ Tool calls
  - Which tools are called?
  - How often?
  - What arguments?
  - What's returned?
  - How long do they take?

□ Model usage
  - Which model handles which tasks?
  - Token counts (input/output)
  - Latency per call
  - Cost per call

□ Context composition
  - What's in the system prompt?
  - What's retrieved/injected?
  - What's the token breakdown?

□ Control flow
  - Which branches are taken?
  - How many iterations per task?
  - Where does it loop/retry?

□ Errors and fallbacks
  - Which error paths fire?
  - How often?
  - What triggers fallbacks?

Read the full file on GitHub · 434 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 13d ago First seen · 434 lines · 69 tokens per session scan A 433ca4afb85d

Subscribe to this mod's changes

agent-audit is a skill published in the GitHub repository majiayu000/claude-skill-registry (604 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 3,200 once invoked, about $0.0003 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.