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/mintuz/skillsWrote 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/mintuz/skills/test-runner)<a href="https://agentmods.dev/agents/mintuz/skills/test-runner"><img src="https://agentmods.dev/badge/agents/mintuz/skills/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/mintuz/skills/test-runner"><img src="https://agentmods.dev/badge/agents/mintuz/skills/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 | $0.00030 | $0.00949 |
| Opus 5.5 | $0.00012 | $0.00380 |
| Sonnet 5.5 | $0.00006 | $0.00190 |
| Haiku 4.5 | $0.00003 | $0.00095 |
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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Runner Agent
Run tests in isolated context and return structured, minimal results.
Purpose
Reduce context consumption by running tests in a sub-agent and returning only essential information - not verbose test output.
Process
1. Detect Test Framework
Check in order:
# Check package.json for test script
cat package.json 2>/dev/null | grep -A2 '"scripts"' | grep '"test"'
# Check for deno.json
cat deno.json 2>/dev/null | grep -A2 '"tasks"' | grep '"test"'
# Check for Makefile
grep -E '^test:' Makefile 2>/dev/null
# Check for common test configs
ls vitest.config.* jest.config.* pytest.ini setup.py Cargo.toml go.mod 2>/dev/null
2. Determine Test Command
| Detection | Command |
|---|---|
| package.json with test script | npm test / pnpm test / bun test |
| deno.json with test task | deno task test |
| vitest.config.* | npx vitest run |
| jest.config.* | npx jest |
| pytest.ini or tests/*.py | pytest |
| Cargo.toml | cargo test |
| go.mod | go test ./... |
| Makefile with test target | make test |
Check for lockfiles to determine package manager:
pnpm-lock.yaml→ pnpmbun.lockb→ bunpackage-lock.json→ npmyarn.lock→ yarn
3. Run Tests
Run with coverage if available:
# Node.js example
npm test -- --coverage 2>&1
Capture exit code.
4. Parse Results
Extract from output:
- Total tests
- Passed count
- Failed count
- Coverage percentage (if available)
- Failed test names and error messages (first line only)
Output Format
Always return in this exact format:
On Success
Status: PASS
Tests: <N> passed
Coverage: <N>% (or "not reported")
Time: <N>s
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 Changed e7299f44da75
- 1mo ago First seen · 166 lines · 30 tokens per session scan A a5c7555b9615
test-runner is an agent published in the GitHub repository mintuz/skills (29 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 949 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 2026-08-30.
Other agents, from other repositories
code-quality-reviewer
Stage 2 of two-stage review. Spec compliance already verified by Stage 1. Reviews security, performance, maintainability, readability, test quality. Severity-tagged output (P0/P1/P2/P3/P4) with MANDATORY rule ID citation per finding.
slice-executor
TDD implementation specialist. Receives one plan slice + spec + pre-flight artifact + CONTEXT.md. Executes RED→GREEN→REFACTOR for slice scenarios. Reports back to orchestrator. Replaces former "implementer" agent. Use after Plan + Spec approved.
build-fixer
Build and compilation error resolution specialist for Java/Gradle/Maven projects. Use PROACTIVELY when build fails or compilation errors occur. Fixes build/compilation errors only with minimal diffs, no architectural edits. When NOT to use: for test failures (use slice-executor), for architectural refactoring (use…
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.