owl-audit

owl-audit is a command for coding agents from arnwaldn/agent-owl. It costs 10 tokens per session (668 once invoked), scanned A, original, MIT.

A coding-agent command is a named instruction that invokes a tool or operation. The owl-audit commands cover file scans, file verification, audit history, statistics, violations, compliance checks, incidents, and reports.

In plain words
What is it for?
Use them to scan or verify files, inspect audit records, find violations, check an AI system's compliance status, validate documentation, and export reports.
Why use it?
They provide short commands for common integrity-audit and EU AI Act compliance tasks instead of requiring direct tool calls.

Command

Part of the agent-owl plugin — 1 command, 2 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add commands/arnwaldn/agent-owl/owl-audit
Clone the repo
git clone --depth 1 https://github.com/arnwaldn/agent-owl

Or install agent-owl, the plugin that ships this one along with the rest of its 1 command, 2 hooks, 1 MCP server.

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 owl-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/arnwaldn/agent-owl/owl-audit.svg)](https://agentmods.dev/commands/arnwaldn/agent-owl/owl-audit)
Your own site
<a href="https://agentmods.dev/commands/arnwaldn/agent-owl/owl-audit"><img src="https://agentmods.dev/badge/commands/arnwaldn/agent-owl/owl-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 668 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00010 $0.00668
Opus 5 $0.00005 $0.00334
Sonnet 5 $0.00002 $0.00134
Haiku 4.5 $0.00001 $0.00067

Measured 3d ago against content hash 74555c9b9a9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

owl-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 3d 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.

commands/owl-audit.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Owl

Run file integrity and EU AI Act compliance operations via MCP tools. Supports multi-project operation — commands auto-detect the current project.

Operations

Parse the user's argument to determine which operation to run:

File Integrity

Command MCP Tool Description
scan audit_full_scan Full integrity scan of all watched paths
verify <filepath> audit_verify_file Verify a single file's hash
history <filepath> audit_file_history Show audit trail for a file
stats audit_stats Show store statistics
violations audit_violations List all integrity violations

EU AI Act Compliance

Command MCP Tool Description
status <system> compliance_status Compliance overview for an AI system
validate <system> compliance_validate SHACL validation (ontology constraints)
annex-iv <system> compliance_annex_iv Annex IV documentation completeness
report <system> [html|md] compliance_export_report Export formatted compliance report
incidents [system] compliance_incidents List incidents (Art. 73)
retention compliance_retention_check Check log retention (Art. 19)
register <name> [risk_level] compliance_register_system Register new AI system

Query

Command MCP Tool Description
sparql "<SPARQL query>" audit_sparql Execute read-only SPARQL query

Project Management

Command MCP Tool Description
init [path] audit_init Initialize AO in a directory (default: CWD)
projects audit_list_projects List all active AO projects in cache

Instructions

  1. Parse the operation from the argument string
  2. Call the corresponding MCP tool from the owl-audit server
  3. Format the result clearly for the user
  4. If no argument is provided, show a summary: call audit_stats then display available commands
  5. For project-wide commands, pass project_path if the user specifies one

Read the full file on GitHub · 71 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. 3d ago First seen · 71 lines · 10 tokens per session scan A 74555c9b9a9a

Subscribe to this mod's changes

owl-audit is a command published in the GitHub repository arnwaldn/agent-owl (0 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 668 once invoked, about $0.0001 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.