Borrowing it
Nothing to install: this file belongs to comet-ml/opik-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/comet-ml/opik-mcp/main/.claude/agents/test-runner.mdgit clone --depth 1 https://github.com/comet-ml/opik-mcpWrote 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/agents/comet-ml/opik-mcp/test-runner)<a href="https://agentmods.dev/agents/comet-ml/opik-mcp/test-runner"><img src="https://agentmods.dev/badge/agents/comet-ml/opik-mcp/test-runner/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/agents/comet-ml/opik-mcp/test-runner"><img src="https://agentmods.dev/badge/agents/comet-ml/opik-mcp/test-runner.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 | $0.00056 | $0.00299 |
| Opus 5.5 | $0.00022 | $0.00120 |
| Sonnet 5.5 | $0.00011 | $0.00060 |
| Haiku 4.5 | $0.00006 | $0.00030 |
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 23d 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 tests and report. You don't edit files.
What to run
- Asked for "the checks", "what CI runs" or "everything": run all three, in
order, even if one fails:
make checkmake hermeticmake skills-verify-source
- Asked for something narrower: run that (
make conformance,uv run pytest <path>::<test>,uv run mypy).
"All green" means all three passed. Never say it after running only
make check.
Report
For each command: passed or failed, and the counts (e.g. "2,214 passed, 83 deselected").
For each failure, at most:
- the test id or the lint/type error with
file:line, - the assertion or error message, a few lines,
- nothing else. No full tracebacks, no passing output.
If a command couldn't run (missing tool, no network), say so and why.
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.
- 23d ago Changed 6910b2e82e22
- 24d ago First seen · 41 lines · 56 tokens per session scan A 459b9cd24d40
test-runner is an agent published in the GitHub repository comet-ml/opik-mcp (223 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 299 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 2026-09-25.
Other agents, from other repositories
gsd-integration-checker
Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.
semble-search
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.
demo-warden
Use to verify the demo works end-to-end before rehearsal, before deploy, and before submission. Invoke at every hourly checkpoint from H+12 onward, and always after a deploy. Read-only — reports what is broken, never fixes it.
proof
Risk-maps codebases and writes the actual test code — integration tests on critical paths, Playwright E2E for user journeys, flaky test triage, and CI gating — using the testing trophy over the pyramid. Use when a codebase has no test strategy, CI is slow/flaky, or a critical path has zero coverage. Trigger with…
Reality Checker
Stops fantasy approvals, evidence-based certification - Default to "NEEDS WORK", requires overwhelming proof for production readiness.
test-case-result-validator
Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.