harness-audit

A command that audits the setup around a coding agent in a repository and produces a scored list of findings and priorities.

In plain words
What is it for?
Use it to review the whole repository or focus on hooks, skills, commands, or agents. It checks related configuration folders and returns category scores, file-specific actions, and suggested next steps.
Why use it?
It shows where the agent setup is missing tools, quality checks, saved knowledge, tests, security protections, or cost controls.

Command

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/zhmxiaowo/opencode-simple/harness-audit
Clone the repo
git clone --depth 1 https://github.com/zhmxiaowo/opencode-simple
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 407 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% 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 $0.00015 $0.00407
Opus 5 $0.00008 $0.00204
Sonnet 5 $0.00003 $0.00081
Haiku 4.5 $0.00002 $0.00041

Measured yesterday against content hash ceaf6b9f5023, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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

This is a copy

86% identical to harness-audit — 5 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.

.opencode/commands/harness-audit.md · 64 lines

What it actually says

Harness Audit Command

Audit the current repository's agent harness setup and return a prioritized scorecard.

Usage

/harness-audit [scope] [--format text|json]

  • scope (optional): repo (default), hooks, skills, commands, agents
  • --format: output style (text default, json for automation)

What to Evaluate

Score each category from 0 to 10:

  1. Tool Coverage
  2. Context Efficiency
  3. Quality Gates
  4. Memory Persistence
  5. Eval Coverage
  6. Security Guardrails
  7. Cost Efficiency

Output Contract

Return:

  1. overall_score out of 70
  2. Category scores and concrete findings
  3. Top 3 actions with exact file paths
  4. Suggested ECC skills to apply next

Checklist

  • Inspect hooks/hooks.json, scripts/hooks/, and hook tests.
  • Inspect skills/, command coverage, and agent coverage.
  • Verify cross-harness parity for .cursor/, .opencode/, .codex/.
  • Flag broken or stale references.

Example Result

Harness Audit (repo): 52/70
- Quality Gates: 9/10
- Eval Coverage: 6/10
- Cost Efficiency: 4/10

Top 3 Actions:
1) Add cost tracking hook in scripts/hooks/cost-tracker.js
2) Add pass@k docs and templates in skills/eval-harness/SKILL.md
3) Add command parity for /harness-audit in .opencode/commands/

Arguments

$ARGUMENTS:

  • repo|hooks|skills|commands|agents (optional scope)
  • --format text|json (optional output format)
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 · 64 lines · 15 tokens per session scan A ceaf6b9f5023

Subscribe to this mod's changes

harness-audit is a command published in the GitHub repository zhmxiaowo/opencode-simple (2 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 407 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to harness-audit, differing in 5 lines, and is treated as a copy.