Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vasuag09/harness-claudenpx agentmods add skills/vasuag09/harness-claude/healthWrote 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/vasuag09/harness-claude/health)<a href="https://agentmods.dev/skills/vasuag09/harness-claude/health"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/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/vasuag09/harness-claude/health"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/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 | $0.00095 | $0.01019 |
| Opus 5 | $0.00048 | $0.00509 |
| Sonnet 5 | $0.00019 | $0.00204 |
| Haiku 4.5 | $0.00010 | $0.00102 |
Grade A, and why
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/health — is the repo green right now?
Goal: one command that runs the repo's checks (test, lint, typecheck, …) and tells you
PASS or FAIL — on any project, with a secret-free record. This is a green/red pulse,
not a coverage gate (the pipeline /harness-claude:test skill owns the 80% floor).
Opt-in. No default-pipeline skill or hook invokes
/health. It shell-executes the repo's own check commands with your privileges — run it deliberately. Git boundary: it only reads and runs; it never commits, pushes, or branches.
When to run
- Before
/harness-claude:ship, or after a major change, to confirm the repo is still green. - On a fresh checkout / unfamiliar repo, to see what passes with one command.
- As the
--scorehalf of a/benchmarkrun, or any time you want a quick health check.
Secret-safety (hard invariant)
Each check's output streams live to your terminal (same as running the command yourself)
but is never captured — it cannot reach the summary, the JSON artifact, or any log. The
artifact records only name / command / pass / durationMs + the gate. A secret printed by a
check stays on your tty and out of every persisted file.
Discovery
With no --cmd, the runner auto-detects checks:
- package.json
scripts—test,lint,typecheck(run as<pm> run <name>; the package manager is detected from the lockfile — pnpm / yarn / npm). Non-standard scripts (e.g.build) are ignored. - else Makefile —
testandlinttargets (make test/make lint).
--cmd '<shell>' (repeatable) replaces the detected set when present.
Do this
- Inspect (optional): see what will run without running it.
node scripts/eval/continuous.js --list - Run the pulse:
Exit 0 = all checks PASS · 1 = any check FAIL · 2 = nothing to run (nonode scripts/eval/continuous.js # auto-detect node scripts/eval/continuous.js --cmd 'pytest -q' --cmd 'ruff check .' # explicit--cmdand nothing detectable). Per-check timeout defaults to 300s (--timeout-msoverrides); a timed-out check counts as FAIL and the run continues. - Read the result. The summary lists each check (
PASS|FAIL <name> <dur>, with a→ re-run: <command>hint on failure) and a gate line. The full machine record is written to.claude/eval/continuous/<timestamp>.json(andlatest.json) — metrics only, no output. - Act on it. On FAIL, re-run the named command yourself to see the captured output (it was
streamed live, never stored), fix, and re-run
/health.
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 · 70 lines · 95 tokens per session scan A ea2d02448208
health is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 1,019 once invoked, about $0.0005 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
ci-tests
Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test).
git-worktree
Create isolated git worktrees for feature development without switching branches.
git-worktree-status
Check status of background verification tasks running in a git worktree.
python-providers
Create, modify, test, or package Python provider adapters under python/providers, including framework-specific dependencies, public imports, type inference, and provider metadata. Use for Python provider work only; use python-sdk for core SDK changes.
python-sdk
Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.
typescript-providers
Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.