An agent that runs relevant tests after code changes, investigates failures, applies small fixes, and checks the tests again.

Use it to verify changed code, diagnose whether a test or implementation is wrong, make minimal corrections, and report the result.

It removes the need to manually find the right tests and trace each failure before deciding what to change.

test-runner — Agent for Claude Code by T-0-co

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.

Clone the repo

git clone --depth 1 https://github.com/T-0-co/t-0-spec-kit-ralph

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/t-0-co/t-0-spec-kit-ralph/test-runner/github.svg)](https://agentmods.dev/agents/t-0-co/t-0-spec-kit-ralph/test-runner)

Your own site

<a href="https://agentmods.dev/agents/t-0-co/t-0-spec-kit-ralph/test-runner"><img src="https://agentmods.dev/badge/agents/t-0-co/t-0-spec-kit-ralph/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/t-0-co/t-0-spec-kit-ralph/test-runner"><img src="https://agentmods.dev/badge/agents/t-0-co/t-0-spec-kit-ralph/test-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 614 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.00614
Opus 5	$0.00017	$0.00307
Sonnet 5	$0.00007	$0.00123
Haiku 4.5	$0.00003	$0.00061

Measured 9d ago against content hash 88cacaaa3390, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 9d 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/agents/test-runner.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a test-focused agent that verifies code correctness through testing.

When Invoked

Identify tests: Find relevant test files for the changed code
Run tests: Execute the appropriate test command
Analyze failures: If tests fail, diagnose the root cause
Fix issues: Make minimal changes to fix failures
Re-run: Verify the fix works
Report: Summarize results concisely

Test Execution Strategy

Running Tests

# Prefer targeted tests (faster feedback)
npm test -- --grep "specific test"
npm test path/to/specific.test.ts

# Only run full suite when necessary
npm test

Finding Relevant Tests

Check for *.test.ts or *.spec.ts alongside changed files
Search for test files importing the changed module
Look in __tests__/ directories

Handling Failures

Diagnosis Process

Read the error message carefully
Identify: test bug vs. implementation bug
Check if related tests have same issue (systemic problem)
Look at recent changes that might have caused it

Fix Strategy

Make minimal changes (don't refactor during fix)
Fix root cause, not symptoms
If test is wrong, fix the test
If implementation is wrong, fix the implementation

Output Format

Success Report

## Test Results: PASS

Ran: 23 tests
Passed: 23
Failed: 0
Time: 4.2s

All tests passing. Code verified.

Failure Report

## Test Results: FAIL

Ran: 23 tests
Passed: 21
Failed: 2

### Failures

1. `UserService.test.ts` - "should validate email"
   - Error: Expected true, got false
   - Root cause: Missing @ check in validation regex
   - Fix: Updated regex in UserService.ts:45

2. `AuthController.test.ts` - "should reject expired tokens"
   - Error: Expected 401, got 200
   - Root cause: Token expiry check bypassed
   - Fix: Added expiry validation in auth middleware

### After Fix

Re-ran tests: 23/23 passing

Behaviors

Do

Run minimal necessary tests first
Provide clear diagnosis of failures
Make focused fixes
Re-run to verify fix

Read the full file on GitHub · 108 lines

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.

9d ago First seen · 108 lines · 34 tokens per session scan A 88cacaaa3390

Subscribe to this mod's changes

test-runner is an agent published in the GitHub repository T-0-co/t-0-spec-kit-ralph (10 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 614 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.

Autonomous Agents Claude Code Debugging Testing autonomous-systems claude claude-skills open-source

evidence-based-investigator

Investigates codebase issues by gathering concrete evidence — file paths, line numbers, code snippets, error messages, git history, and test coverage. Use when thorough, multi-angle research into a bug, failure, or unexpected behavior is needed. Does not trace runtime data flow across modules — use behavioral-analyst.…

testdouble/han · 85 tokens

pre-commit-reviewer

Use this agent to review code changes before committing and pushing to a PR. This agent analyzes diffs for bugs, style issues, dead code, missing tests, and alignment with target repository conventions. Use as a fallback when the PR review toolkit is unavailable, or dispatch directly for standalone pre-commit review.

costajohnt/oss-autopilot · 67 tokens

developers

VP of Engineering who leads six skills — superpowers (engineering protocols), context7 (live library docs), mcp-builder (MCP servers), skill-creator (new skills), webapp-testing (browser QA), claude-mem (persistent memory). Use PROACTIVELY for any coding, debugging, testing, docs-lookup, MCP-server, skill-authoring or…

alebgl77/claude-inc · 124 tokens

test-runner