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 shimo4228/claude-harness --skill skill-healthgit clone --depth 1 https://github.com/shimo4228/claude-harnessWrote 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/shimo4228/claude-harness/skill-health)<a href="https://agentmods.dev/skills/shimo4228/claude-harness/skill-health"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/skill-health/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/shimo4228/claude-harness/skill-health"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/skill-health.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 | $0.00168 | $0.03095 |
| Opus 5 | $0.00084 | $0.01548 |
| Sonnet 5 | $0.00034 | $0.00619 |
| Haiku 4.5 | $0.00017 | $0.00310 |
Grade A, and why
skill-health 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 11d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-health — Skill-Library Structural Debt Scan
Detect skill technical debt — library-level defects that do not break a
single skill in isolation but degrade the library over time (SkillOps, Pu/Song/
Zhao 2026, arXiv:2605.13716). This skill
owns the one debt pattern no other harness skill checks: missing artifacts
— a SKILL.md that references a scripts/ module, a bash script, an agent, or
a sibling skill that no longer exists on disk (it silently dangles after a
rename or delete).
This is a structural property — decidable from the literal text plus a
filesystem exists() check — so it is owned by deterministic code at 100%
accuracy (AKC ADR-0008 Code-LLM Layering). The semantic, risk, and validation
dimensions are delegated, never re-implemented here.
Three output categories — only one is a defect claim
The scanner reports three lists, and conflating them is the mistake this section exists to prevent:
- Dangling references (
dangling, exit code 1) — the skill wrote a path, and that path does not exist.exists()is authoritative here. - Unresolved names (
unresolved_names, exit code unaffected) — the skill named a skill/command without a path (See skill: X,`X` skill,`/X`) and no file matches under the skills root. This is an enumeration handed to judgment, not a finding. The name may still be a CLI builtin, a bundled skill, a plugin command, or a project-scoped skill in another repo — none of which live here. - External skills (
external, exit code unaffected) — the skill's directory is a symlink out of the skills root, so this harness does not own the file. Also an enumeration, and it answers a different question from the other two: not "is this skill correct?" but "would a fix applied here survive?" It would not — the owning tree overwrites it on its next upgrade, and the change never reaches version control. Route these upstream (issue / PR); do not hand them a local verdict.
What ships with it
8 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.
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.
- 11d ago First seen · 206 lines · 168 tokens per session scan A d67cf5999a8e
skill-health is a skill published in the GitHub repository shimo4228/claude-harness (3 stars, last pushed 5d ago), licensed MIT. It adds 168 tokens to every session and 3,095 once invoked, about $0.0008 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.
Other skills, from other repositories
iterate
Autonomous multi-cycle problem solver for complex tasks that require diagnosis → fix → test → verify loops. Use when the user says things like "make this work", "test this end-to-end", "fix and verify", "iterate until working", "do cycles", "keep going until it passes", or when a task clearly requires multiple rounds…
troubleshoot-terva
Diagnose terva itself. Symptoms include an extension that will not load, a connector or bot that is down, missing tools, or MCP trouble. A bloated context or session/resume confusion also qualifies. Use when terva misbehaves, or when something that should be available is absent. Also use when the user asks why terva…
agent-adoption-triage
Five-question triage for routing AI work to the right architecture — script, algorithmic search, LLM workflow, or autonomous agentic loop — before any agent is built. Use when someone says "let's build an agent for X", when deciding whether a use case actually needs an autonomous agent, when reviewing an agent…
debug-help
Help debug an issue systematically.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.