cranelisp: Agent for Claude Code

.claude/agents/audit.md

audit is an agent for Claude Code from alilee/cranelisp. It costs 14 tokens per session (228 once invoked), scanned A, original, MIT.

A read-only audit agent role for assessing one defined part of a project. It follows the project's instructions and reports findings without taking ownership of other roles' work.

In plain words
What is it for?
Use it to inspect a bounded project area, record evidence and unresolved handoffs, and report the results to a coordinator.
Why use it?
It provides a focused review without changing the code. Clear boundaries help prevent an assessment from expanding into unrelated implementation.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md.

This is alilee/cranelisp's own configuration. It tells Claude Code how to work on cranelisp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cranelisp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to alilee/cranelisp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/alilee/cranelisp/main/.claude/agents/audit.md
Clone the repo
git clone --depth 1 https://github.com/alilee/cranelisp

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/alilee/cranelisp/audit.svg)](https://agentmods.dev/agents/alilee/cranelisp/audit)
Your own site
<a href="https://agentmods.dev/agents/alilee/cranelisp/audit"><img src="https://agentmods.dev/badge/agents/alilee/cranelisp/audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 228 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 5.1 $0.00014 $0.00228
Opus 5 $0.00007 $0.00114
Sonnet 5 $0.00003 $0.00046
Haiku 4.5 $0.00001 $0.00023

Measured yesterday against content hash ed7401da518a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 yesterday.

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

Copies of this mod

1 near-identical copy found in the catalogue:

  • qa — 88% identical, 10 lines differ
.claude/agents/audit.md · 21 lines

What it actually says

Read and follow, in order: the repository root CLAUDE.md (and every CLAUDE.md applicable to the directories you touch), then sprints/METHOD.md for what cranelisp adds, then your role contract at .agents/skills/audit/SKILL.md — the contract governs your authority, boundaries and handoffs, and takes precedence over habit. Before work, load every support skill listed under always for audit in .agents/skill-composition.toml; when creating or editing a memory or standing document, also load those under standing_documents.

You are acting as the audit role. The dispatching coordinator's brief is your scope: do not silently expand it, and route work owned by other roles back to the coordinator per the contract's handoff rules. Report your results, your evidence, and any unresolved handoffs in your final message.

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. yesterday First seen · 21 lines · 14 tokens per session scan A ed7401da518a

Subscribe to this mod's changes

audit is an agent published in the GitHub repository alilee/cranelisp (7 stars, last pushed 6d ago), licensed MIT. It adds 14 tokens to every session and 228 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 2026-09-04.