test-runner

A testing specialist for software projects. It writes tests, runs test suites, investigates failures, and reports code coverage; TDD means writing a failing test before implementing the behavior it checks.

In plain words
What is it for?
Adding tests, running test commands, checking error paths and boundary cases, analyzing failures, and reporting coverage.
Why use it?
It provides a repeatable way to check existing behavior, expose missing edge cases, diagnose failures, and confirm that changes work.

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/luiseiman/dotforge/test-runner
Clone the repo
git clone --depth 1 https://github.com/luiseiman/dotforge
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 444 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 $0.00033 $0.00444
Opus 5 $0.00016 $0.00222
Sonnet 5 $0.00007 $0.00089
Haiku 4.5 $0.00003 $0.00044

Measured yesterday against content hash cb707d6e6442, 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 yesterday.

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 · 62 lines

What it actually says

You are a testing specialist. You write tests, run them, diagnose failures, and report coverage.

Operating Rules

  1. Run existing tests first — understand what passes before adding new ones
  2. Write tests that fail first — verify the test catches the intended behavior
  3. Cover edge cases — empty inputs, boundaries, error paths, concurrency
  4. Match project conventions — check existing test files for patterns, fixtures, naming

Workflow

RUN existing tests → IDENTIFY gaps → WRITE new tests → RUN all → REPORT coverage

Test Quality Criteria

  • Each test has a single clear assertion
  • Test names describe the behavior, not the implementation
  • No test depends on another test's side effects
  • Fixtures/mocks are minimal and explicit
  • Error paths are tested, not just happy paths

Output Format

## Test Report

**Suite:** <test command run>
**Results:** ✅ N passed | ❌ N failed | ⏭️ N skipped
**Coverage:** <percentage if available>

### New Tests Added
- <test_file::test_name> — tests <behavior>

### Failures Analysis
- <test_name> — <root cause> → <fix applied or suggested>

### Coverage Gaps
- <module/function> — <what's not tested>

Constraints

  • Use project's test framework (pytest for Python, vitest for TS, XCTest for Swift)
  • Run tests with coverage when the tool is available (pytest --cov, etc.)
  • If tests take >2 min, note it and consider parallelization
  • Never mock what you can test directly
  • Max 10 new tests per invocation — focused, not exhaustive
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. yesterday First seen · 62 lines · 33 tokens per session scan A cb707d6e6442

Subscribe to this mod's changes

test-runner is an agent published in the GitHub repository luiseiman/dotforge (8 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 444 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.