carve-harness: Command for Claude Code

.claude/commands/harness-audit.md

harness-audit is a command for Claude Code from claude-code-expert/carve-harness. It costs 30 tokens per session (120 once invoked), scanned A, original, MIT.

A mechanical check of an agent harness, the rules, feedback, and stored state that guide an agent's work.

In plain words
What is it for?
Use it to verify the configuration of an agent workflow and find broken constraints, feedback, or state handling.
Why use it?
It shows whether those controls actually work by reporting PASS or FAIL instead of relying on assumptions.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PROJECT_DIR} variable.

This is claude-code-expert/carve-harness's own configuration. It tells Claude Code how to work on carve-harness 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 carve-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to claude-code-expert/carve-harness. 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/claude-code-expert/carve-harness/main/.claude/commands/harness-audit.md
Clone the repo
git clone --depth 1 https://github.com/claude-code-expert/carve-harness

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 harness-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/claude-code-expert/carve-harness/harness-audit.svg)](https://agentmods.dev/commands/claude-code-expert/carve-harness/harness-audit)
Your own site
<a href="https://agentmods.dev/commands/claude-code-expert/carve-harness/harness-audit"><img src="https://agentmods.dev/badge/commands/claude-code-expert/carve-harness/harness-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 120 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00030 $0.00120
Opus 5 $0.00015 $0.00060
Sonnet 5 $0.00006 $0.00024
Haiku 4.5 $0.00003 $0.00012

Measured 6d ago against content hash 01d940769e2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

harness-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 6d 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.

.claude/commands/harness-audit.md · 10 lines

What it actually says

하네스 게이트를 기계적으로 점검한다. 아래를 실행하고 결과를 그대로 보고하라:

bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/harness-audit.sh

  • exit 0 → 하네스 정상(모든 게이트 존재).
  • non-zero → 게이트 누수. 출력의 FAIL: 항목을 수정한 뒤 재실행하라.
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. 6d ago First seen · 10 lines · 30 tokens per session scan A 01d940769e2e

Subscribe to this mod's changes

harness-audit is a command published in the GitHub repository claude-code-expert/carve-harness (11 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 120 once invoked, about $0.0002 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.