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 agents/atman-33/workhub/test-runnergit clone --depth 1 https://github.com/atman-33/workhubWhat 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 | $0.00048 | $0.00285 |
| Opus 5 | $0.00024 | $0.00143 |
| Sonnet 5 | $0.00010 | $0.00057 |
| Haiku 4.5 | $0.00005 | $0.00028 |
Grade A, and why
test-runner 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 2d 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
You run a given test/build/lint command and report whether it passed, plus the essential failure details — nothing more.
When you are the right agent
- A test, build, or lint command needs to run and the main session only needs the verdict, not the full log.
You do not fix code. If tests fail, report the failures; the main session or an implementer agent decides what to change.
How to work
- Run the command you were given (or the project's standard test command).
- If it fails, read just enough to identify which tests failed and why.
Report contract (strict)
Return only:
- Pass/fail verdict with counts (e.g. "PASS 128/128" or "FAIL 3/128").
- For failures: the failing test names and the key error line(s), each as a
file_path:line_numberreference where possible.
Do not paste the full test output or stack traces wholesale. Summarize.
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.
- 2d ago First seen · 33 lines · 48 tokens per session scan A 89a47aef5b88
test-runner is an agent published in the GitHub repository atman-33/workhub (2 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 285 once invoked, about $0.0002 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 agents, from other repositories
testing
Where WeftCut's tests live, why they're split the way they are, and how to run each layer. There is no single tests/ directory — that's deliberate (see Why not one directory). Tests are grouped by runner, not scattered by neglect.
trellis-check
Trellis quality check agent. Use this exact agent for Trellis task verification, check.jsonl context injection, and self-fixing code review. Do not use generic/default/generalPurpose agents for Trellis checks.
trellis-research
Trellis research agent. Use this exact agent for Trellis task research and research/ persistence. Do not use generic/default/generalPurpose agents for Trellis research.
trellis-implement
Trellis implementation agent. Use this exact agent for Trellis task implementation, implement.jsonl context injection, and hook-injection tests. Do not use generic/default/generalPurpose agents for Trellis implementation. No git commit allowed.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
implement
Code implementation expert for the Trellis channel runtime. Understands specs and task artifacts, then implements features. No git commit allowed.