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.
git clone --depth 1 https://github.com/Intense-Visions/harness-engineeringWrote 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.
[](https://agentmods.dev/commands/intense-visions/harness-engineering/audit)<a href="https://agentmods.dev/commands/intense-visions/harness-engineering/audit"><img src="https://agentmods.dev/badge/commands/intense-visions/harness-engineering/audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/intense-visions/harness-engineering/audit"><img src="https://agentmods.dev/badge/commands/intense-visions/harness-engineering/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.00399 |
| Opus 5.5 | $0.00016 | $0.00160 |
| Sonnet 5.5 | $0.00008 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
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 1mo 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.
What it actually says
Phases:
- classify: Determine repo shape and select applicable audit dimensions
- fanout: Dispatch parallel read-only audit agents, one per dimension, composing existing skills
- verify: Adversarial confirmation of HIGH findings by a second agent
- dedup: Merge cross-dimension duplicates, severity-rank, cross-check against existing issues
- publish: File grouped thematic tracking issues with checkbox action lists (or emit ranked report)
- remediate: Optional fix fan-out — worktree-isolated fix agents, one per theme, gated on human confirmation (optional)
<execution_context> @agents/skills/claude-code/harness-audit/SKILL.md @agents/skills/claude-code/harness-audit/skill.yaml </execution_context>
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.
- 1mo ago First seen · 42 lines · 40 tokens per session scan A d63ea4e31971
harness:audit is a command published in the GitHub repository Intense-Visions/harness-engineering (22 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 399 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other commands, from other repositories
refactor-clean
Refactor provided code for cleanliness, maintainability, and alignment with SOLID principles and modern best practices — no over-engineering.
deep-audit.skeleton
Description: This section is populated by Bootstrap with manifest data. Required manifest fields: project.description, stack.primary, project.structure, project.subprojects, stack.orm, stack.authmethod Example output.
modify
Command "modify" from MartyBonacci/specswarm, covering user input, flag parsing, parse flags from arguments, mode routing and goal.
hotfix
Ship a fast branch-based P0 hotfix — diagnose, implement, open a ready-for-review PR, then verify + review after (deferred by design).
Diagnose
Run a 20-point health check across the plugin install, project config, PM/notification reachability, docs freshness, board consistency, and git state. Read-only — never changes state. Reports each check as PASS/WARN/FAIL/SKIP with an actionable fix. Target under 15 seconds end-to-end. Use before demos, after a plugin…
triage
Triage a bug report (PDF / markdown / text) — extract the issues, prioritize, then run the fix pipeline per issue.