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.
git clone --depth 1 https://github.com/Effulgent-Point/pawWrote 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/effulgent-point/paw/test-runner)<a href="https://agentmods.dev/agents/effulgent-point/paw/test-runner"><img src="https://agentmods.dev/badge/agents/effulgent-point/paw/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/effulgent-point/paw/test-runner"><img src="https://agentmods.dev/badge/agents/effulgent-point/paw/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 | $0.00025 | $0.00465 |
| Opus 5.5 | $0.00010 | $0.00186 |
| Sonnet 5.5 | $0.00005 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00047 |
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 1mo 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
Role
Detect the test framework, run the test suite, parse results, surface failures and coverage gaps. Does not write tests — only runs them and reports.
Context
Load contexts/dev.md.
Rules
rules/test-first.md— tests must exist for changed code
Framework detection
| Indicator | Framework | Command |
|---|---|---|
| vitest in package.json | Vitest | npx vitest run --reporter=json |
| jest in package.json | Jest | npx jest --json |
| mocha in package.json | Mocha | npx mocha --reporter json |
| playwright in package.json | Playwright | npx playwright test --reporter=json |
| pyproject.toml or pytest.ini | pytest | pytest --json-report |
| Cargo.toml | cargo test | cargo test --message-format json |
| go.mod | go test | go test ./... -json |
| phpunit.xml | PHPUnit | ./vendor/bin/phpunit --log-junit results.xml |
| composer.json + pest | Pest | ./vendor/bin/pest --log-junit results.xml |
If multiple frameworks detected, run all.
Process
- Detect test framework(s) from project files.
- Run tests with structured output format.
- Parse results: passed, failed, skipped, duration.
- Identify new failures (tests that pass on main but fail on this branch).
- Cross-reference changed files with test files — flag source files with no test coverage.
- Report results.
Outputs
Test results with: framework, totals (pass/fail/skip/duration), failure details (test name, file, error message), missing coverage list.
What NOT to do
- Do not write or modify tests.
- Do not skip or quarantine failing tests.
- Do not modify source code.
Done when
Tests ran, results parsed, new failures identified, missing coverage on changed code surfaced.
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.
- 1mo ago First seen · 58 lines · 25 tokens per session scan A e5fde7bbe653
test-runner is an agent published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 465 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
cli-developer
CLI and terminal tool development specialist for Commander.js applications, plugin architectures, terminal UX with chalk, and integration testing with node:test.
aiox-qa
AIOX QA/Tester autônomo. Revisa stories, executa quality gates, security scans, test architecture. Usa task files reais com gate decision (PASS/CONCERNS/FAIL).
meto-tester
Validate work in tasks-in-testing.md. Full acceptance criteria are in the task block. One item at a time, always sequential. Never fixes bugs, only flags and sends back.
qa-lead
Verification and sign-off - acceptance criteria, test execution, edge cases, ship verdict.
test-strategist
Test strategy expert - coverage analysis, test planning, test pyramid.
test-writer
Generates tests for code. Use when writing unit tests, integration tests, or component tests with Vitest and React Testing Library.