test-runner

An agent that runs a project's automated tests and reports the results. It detects common test tools such as Jest, Vitest, pytest, and Go's test runner.

In plain words
What is it for?
Use it after code changes to run the relevant test suites, find new failures, and identify coverage gaps.
Why use it?
It gives a structured report of passing, failing, and skipped tests and points out missing checks in changed code.

Agent

Install

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.

agentmods
npx agentmods add agents/effulgent-point/paw/test-runner
Clone the repo
git clone --depth 1 https://github.com/Effulgent-Point/paw
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 465 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00465
Opus 5 $0.00013 $0.00233
Sonnet 5 $0.00005 $0.00093
Haiku 4.5 $0.00003 $0.00047

Measured 2d ago against content hash e5fde7bbe653, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

agents/test-runner.md · 58 lines

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

  1. Detect test framework(s) from project files.
  2. Run tests with structured output format.
  3. Parse results: passed, failed, skipped, duration.
  4. Identify new failures (tests that pass on main but fail on this branch).
  5. Cross-reference changed files with test files — flag source files with no test coverage.
  6. 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.

Changes

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.

  1. 2d ago First seen · 58 lines · 25 tokens per session scan A e5fde7bbe653

Subscribe to this mod's changes

test-runner is an agent published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 22d ago), licensed MIT. It adds 25 tokens to every session and 465 once invoked, about $0.0001 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.