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 skills add holon-run/holon --skill code-health-auditgit clone --depth 1 https://github.com/holon-run/holonWrote 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/holon-run/holon/code-health-audit)<a href="https://agentmods.dev/skills/holon-run/holon/code-health-audit"><img src="https://agentmods.dev/badge/skills/holon-run/holon/code-health-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/skills/holon-run/holon/code-health-audit"><img src="https://agentmods.dev/badge/skills/holon-run/holon/code-health-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 | $0.00039 | $0.01051 |
| Opus 5.5 | $0.00016 | $0.00420 |
| Sonnet 5.5 | $0.00008 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
code-health-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 12d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Health Audit Skill
Summary
Use this skill for a read-only repository health audit or for preparing an evidence-backed maintenance plan. Plans may cover a focused cleanup, a multi-phase refactor, or a broad coordinated change when that scale is justified by the repository's maintenance cost. It defines an evidence discipline and an output shape; it does not provide a static analyzer and it does not authorize code changes.
When To Use
- Finding maintainability hotspots across a repository
- Reviewing a technical-debt register for stale or duplicate entries
- Comparing refactoring candidates before implementation
- Drafting a proportionate, behavior-preserving maintenance or refactoring plan
- Preparing verification gates for an approved refactoring
Do Not Use
- As a substitute for reviewing a concrete change set or pull request
- To declare a smell a bug, vulnerability, or performance issue without evidence
- To run a broad rewrite, formatter sweep, or dependency upgrade as an unapproved side effect of an audit
- To infer permission to edit code, merge changes, or publish findings
Evidence Rules
- Name the scope. Record the repository, paths, time window, and read/write authorization.
- Prefer direct evidence. Cite a file and symbol or line range, relevant tests, history, configuration, or measured behavior.
- Separate certainty levels. Use
confirmed,signal,hypothesis, orunknown; explain what would raise confidence. - Avoid metric theater. A large file, high churn count, or duplicated string is a lead. Connect it to coupling, change friction, defect history, testability, or another observed impact before ranking it highly.
- Record counter-evidence. Note stable interfaces, strong tests, low churn, generated code, or other reasons not to refactor now.
- Keep findings atomic. One finding should have one primary location, impact statement, and next step. Link related findings instead of merging unrelated smells.
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.
- 12d ago First seen · 130 lines · 39 tokens per session scan A 70bb7618f733
code-health-audit is a skill published in the GitHub repository holon-run/holon (166 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,051 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 2026-10-04.
Other skills, from other repositories
codex
Delegate coding work to the OpenAI Codex CLI for repository changes, reviews, and focused fixes.
orbit-github
Open Orbit briefing skill — selected by the Orbit pipeline when GitHub is the user's only connected connector, or when the user explicitly scopes their daily digest to GitHub. Pulls the past 24 hours of PRs, review requests, issues, CI runs, and merges from the user's authenticated GitHub connection and renders them…
diff-review
Render the patch-edit run's accumulated changes as a reviewable diff, surface it through a GenUI choice surface, and persist the user's accept / reject decision into the artifact manifest.
patch-edit
Apply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change suffices.
critique-theater
Five-dimension design quality review — score the artifact against craft, brand, accessibility, and copy, then fix what falls short before handing it over.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…