harness-audit

harness-audit is a skill for Claude Code from joymin5655/Agent. It costs 105 tokens per session (2,229 once invoked), scanned A, original, MIT.

A read-only health check for an agent harness, the tools and checks that support agent work. It runs the existing integrity checks once and reports each result, including whether documentation matches reality.

In plain words
What is it for?
Use it to inspect the harness, review pass, fail, and skipped checks, investigate failures, and identify fixes or follow-up work.
Why use it?
It turns low-level check output into a clear diagnosis without changing the harness or repeating its checks in a separate implementation.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash core/tests/verify-all.sh.

Part of the agent-harness plugin — 12 skills, 1 command, 3 agents, 5 hooks shipped together

Good fit Use it to inspect the harness, review pass, fail, and skipped checks…

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/joymin5655/Agent
agentmods
npx agentmods add skills/joymin5655/agent/harness-audit

Made for: Claude Code.

Or install agent-harness, the plugin that ships this one along with the rest of its 12 skills, 1 command, 3 agents, 5 hooks.

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/skills/joymin5655/agent/harness-audit.svg)](https://agentmods.dev/skills/joymin5655/agent/harness-audit)
Your own site
<a href="https://agentmods.dev/skills/joymin5655/agent/harness-audit"><img src="https://agentmods.dev/badge/skills/joymin5655/agent/harness-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,229 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 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 $0.00105 $0.02229
Opus 5 $0.00053 $0.01115
Sonnet 5 $0.00021 $0.00446
Haiku 4.5 $0.00011 $0.00223

Measured 6d ago against content hash 701683c8b989, 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.

skills/harness-audit/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/harness-audit

Goal

Produce one interpreted health report of the harness in a single read-only dry-run. The machine integrity layer (P1-1 doc-reality.sh, the CI jobs, and the verify-all.sh runner) is the enforcement; this skill is the consumer that runs it once, reads off a per-check pass/fail table, and turns each failure into a diagnosis a maintainer can act on.

Concretely the report answers three questions with evidence:

  1. Is the harness passing its own gates right now? — a per-check PASS / FAIL / SKIP table, taken verbatim from verify-all.sh.
  2. What does the doc-reality gate (P1-1) say? — cited explicitly, because it is the gate that catches the harness lying about itself (phantom paths + drifted counts), and it is the one item most easily missed in a wall of green.
  3. For every non-PASS: why, and what next? — the check's purpose, the likely root cause, the recommended fix, and whether it warrants a new backlog row.

This skill supplies the interpretation; it does not re-implement any check. The checks live in core/tests/ and CI; here you run them and read the results.

Why this is a layer, not a duplicate of P1-1

P1-1 (core/tests/doc-reality.sh) is a machine gate: it runs in CI, exits 0/1, and mechanically blocks doc drift. This skill is the agent consumer that sits on top of that gate — it invokes the whole machine layer in one dry-run and interprets the results (root-cause, fix, backlog follow-up) the way a maintainer would. It reads doc-reality's verdict; it never re-derives phantom-path or count logic. Deleting this skill would not weaken any gate (CI still enforces them); deleting doc-reality would. That asymmetry is the layer relationship: the gate enforces, the audit interprets. This mirrors the machine-gate-vs-agent-consumer split the plan draws for H-2.

Steps

1. Run the machine integrity layer (one dry-run)

bash core/tests/verify-all.sh

verify-all.sh is the single-command runner. It dynamically discovers every core/tests/*.sh check (the runner and its own self-test aside, to avoid recursion — that self-test runs as its own CI step) so no harness check is silently omitted, and runs, per check, PASS / FAIL / loud SKIP with a final tally. Its discovered set already includes the machine layer this audit reports on:

Read the full file on GitHub · 170 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. 6d ago First seen · 170 lines · 105 tokens per session scan A 701683c8b989

Subscribe to this mod's changes

harness-audit is a skill published in the GitHub repository joymin5655/Agent (2 stars, last pushed 4d ago), licensed MIT. It adds 105 tokens to every session and 2,229 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

regex-mastery

Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.

alibaba/anolisa · 60 tokens

background-watch-hook

Use vibe watch to run a managed Harness waiter that returns to the same conversation later. Best for reviews, CI, files, logs, and other wait-now-continue-later workflows.

avibe-bot/avibe · 44 tokens

use-avibe-harness

Use Avibe Harness for durable Agent delegation, Sessions, scheduled Tasks, Watches, Runs, queues, and work that must continue beyond the current turn.

avibe-bot/avibe · 36 tokens

use-show-pages

Build, inspect, update, or share an Avibe Show Page when a visual explanation, diagram, dashboard, report, or interactive prototype would materially help.

avibe-bot/avibe · 35 tokens

use-avibe-vault

Use Avibe Vault for API keys, tokens, passwords, protected credentials, authenticated HTTP requests, or digest signing without exposing secret values to the agent.

avibe-bot/avibe · 36 tokens

technocore-chat

Coordinate with other AI agents over plain HTTP GETs — shared rooms, durable notes, long-polling. No POST, no sockets, no client libraries, no account; a fetch tool is enough, and an MCP server fronts the same surface. Use when you need to leave a message for another agent, wait for one, or persist state across your…

flop-labs/technocore-chat · 79 tokens