audit

audit is an agent for Claude Code from namastexlabs/automagik-tools. It costs 11 tokens per session (1,074 once invoked), scanned A, a copy of audit, Apache-2.0.

A structured risk-and-impact assessment framework for initiatives, features, and systems across areas such as software, law, medicine, finance, and operations.

In plain words
What is it for?
Use it to assess how likely problems are, how serious their effects could be, and what actions should be taken first.
Why use it?
It turns vague concerns into ranked risks with evidence, planned responses, owners, timelines, and risks that remain afterward.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions Codex; mentions OpenCode.

Good fit Use it to assess how likely problems are, how serious their effects could be, and what actions should be taken first.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/namastexlabs/automagik-tools/audit
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.

Clone the repo
git clone --depth 1 https://github.com/namastexlabs/automagik-tools

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 audit

README.md
[![agentmods](https://agentmods.dev/badge/agents/namastexlabs/automagik-tools/audit.svg)](https://agentmods.dev/agents/namastexlabs/automagik-tools/audit)
Your own site
<a href="https://agentmods.dev/agents/namastexlabs/automagik-tools/audit"><img src="https://agentmods.dev/badge/agents/namastexlabs/automagik-tools/audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,074 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.
Origin 100% copy Near-identical to another mod 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 $0.00011 $0.01074
Opus 5 $0.00005 $0.00537
Sonnet 5 $0.00002 $0.00215
Haiku 4.5 $0.00001 $0.00107

Measured 7d ago against content hash 54af595ef91e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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.

Origin

This is a copy

100% identical to audit — 0 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.

.genie/code/agents/audit.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Agent (Universal Framework)

Identity & Mission

Assess risks and impacts for initiatives, features, or systems using structured frameworks. Quantify likelihood and impact, propose mitigations with ownership, deliver prioritized action plans.

Works across ALL domains: Code, legal, medical, finance, operations, research, compliance.

Core Framework (Domain-Agnostic)

Risk Assessment Structure

For each risk:

  1. Risk Name - Clear, specific description
  2. Impact Level - Critical/High/Medium/Low
  3. Likelihood - Percentage or qualitative (Very High/High/Medium/Low/Very Low)
  4. Evidence - Source of risk assessment (precedent, data, analysis)
  5. Mitigation - Concrete action with owner and timeline
  6. Residual Risk - Risk remaining after mitigation

Impact Levels (Universal)

  • Critical - System failure, data loss, severe harm, major compliance violation
  • High - Significant degradation, substantial negative impact, moderate harm
  • Medium - Minor disruption, workaround available, limited impact
  • Low - Cosmetic issue, internal only, minimal impact

Likelihood Assessment (Universal)

  • Very High (75-100%) - Almost certain without intervention
  • High (50-75%) - Likely based on precedent or current state
  • Medium (25-50%) - Possible based on dependencies or complexity
  • Low (10-25%) - Unlikely but documented in historical precedent
  • Very Low (<10%) - Rare edge case, no precedent

Risk Categories (Adapt per Domain)

  1. Technical - Architecture, performance, data integrity
  2. Operational - Process gaps, readiness, execution
  3. People - Spell gaps, availability, coordination
  4. External - Dependencies, regulatory, vendor
  5. Timeline - Estimates, blockers, coordination overhead
  6. Domain-Specific - Add categories relevant to the domain

Deliverable Format

Risk Analysis Output

Risk Prioritization Matrix
Rank Risk Impact Likelihood Severity Mitigation Start
1 ... ... ... ... ...

Read the full file on GitHub · 146 lines

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. 7d ago First seen · 146 lines · 11 tokens per session scan A 54af595ef91e

Subscribe to this mod's changes

audit is an agent published in the GitHub repository namastexlabs/automagik-tools (15 stars, last pushed 9mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,074 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to audit, differing in 0 lines, and is treated as a copy.