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.
npx agentmods add skills/mifunedev/openharness/auditnpx skills add mifunedev/openharness --skill auditgit clone --depth 1 https://github.com/mifunedev/openharnessWrote 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/skills/mifunedev/openharness/audit)<a href="https://agentmods.dev/skills/mifunedev/openharness/audit"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/audit.svg" alt="Measured on agentmods" 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 | $0.00125 | $0.01634 |
| Opus 5 | $0.00063 | $0.00817 |
| Sonnet 5 | $0.00025 | $0.00327 |
| Haiku 4.5 | $0.00013 | $0.00163 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit — explicit target dispatcher
Usage validation happens before any reference is read, run identity is created, or state changes. The dispatcher never guesses a missing target from prose. Trigger families include: audit this task; audit PR N; triage the PR queue; audit the harness; audit context budget; audit skills; lint evals; check framework drift; and full audit campaign.
Canonical usage
usage: /audit <implementation|pr|prs|harness|context|skills|eval-quality|drift|full> [target options]
| Target | Invocation | Native result |
|---|---|---|
implementation |
/audit implementation <slug> [--pr N --repo O/N] [--base B] [--branch B] |
AUDIT-PASS / AUDIT-FAIL |
pr |
/audit pr <N> [--repo O/N] [--base B] [--deep] [--proof] [--dry-run] |
PR-AUDIT-PROMOTABLE / PR-AUDIT-BLOCKED / PR-AUDIT-UNKNOWN |
prs |
/audit prs [--repo O/N] [filters/actions] |
buckets + PRS-AUDIT-COMPLETE / PRS-AUDIT-PARTIAL |
harness |
`/audit harness [--focus area] [--external URL | path] [actions]` |
context |
`/audit context [all | --baseline]` |
skills |
`/audit skills [all | root |
eval-quality |
`/audit eval-quality [all | probes |
drift |
/audit drift |
per-class OK / aggregate DRIFT: |
full |
/audit full [--repo O/N] [--focus area] [--health-target target] |
AUDIT-CAMPAIGN-COMPLETE / AUDIT-CAMPAIGN-PARTIAL |
For missing/unknown targets or missing required arguments, print the exact usage line and this table, then stop. Exactly these nine cases are public:
| Target | Authoritative route |
|---|---|
| implementation | references/implementation.md |
| pr | references/pr.md |
| prs | references/prs.md |
| harness | references/harness.md |
| context | references/context.md |
| skills | references/skills.md |
| eval-quality | references/eval-quality.md |
| drift | references/drift.md |
| full | references/full.md |
What ships with it
26 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- fixtures/artifact-contract.prd.json 1.5 KB
- fixtures/github-status-rollup.json 631 B
- probes/context/probe-advisor.md 348 B
- probes/context/probe-git-branch.md 287 B
- probes/context/probe-git-pr.md 256 B
- probes/context/probe-readme.md 380 B
- probes/context/probe-recursive.md 402 B
- probes/context/probe-sandbox.md 297 B
- references/context.md 6.8 KB
- references/drift.md 16 KB
- references/eval-quality.md 20 KB
- references/external-proposal-audit.md 991 B
- references/full.md 2.4 KB
- references/harness.md 15 KB
- references/implementation.md 10 KB
- references/pr-classification.md 843 B
- references/pr.md 1.8 KB
- references/prs.md 2.5 KB
- references/reviewer-evidence-doc.md 6.7 KB
- references/skills.md 7.7 KB
- scripts/audit-evidence.sh 1.6 KB runs code
- scripts/audit-run.sh 9.3 KB runs code
- scripts/implementation-gates.sh 4.5 KB runs code
- scripts/pr-acquire.sh 2.3 KB runs code
- scripts/pr-classify.sh 6.6 KB runs code
- scripts/route-driver.sh 2.4 KB runs code
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.
- 4d ago First seen · 109 lines · 125 tokens per session scan A 78a2fddd6d75
audit is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed 4d ago), licensed Apache-2.0. It adds 125 tokens to every session and 1,634 once invoked, about $0.0006 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.
Other skills, from other repositories
data-visualization
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
blog-post
Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.
social-media
Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
textual-screenshot
Capture a Textual terminal UI as an SVG using its headless test harness. Use when asked to make, attach, or preview a screenshot of deepagents-code/dcode or another Textual app, visually verify a TUI state, or render a modal, screen, or widget without a desktop or browser.