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/randomittin/heimdallWrote 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/randomittin/heimdall/test-runner)<a href="https://agentmods.dev/agents/randomittin/heimdall/test-runner"><img src="https://agentmods.dev/badge/agents/randomittin/heimdall/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/randomittin/heimdall/test-runner"><img src="https://agentmods.dev/badge/agents/randomittin/heimdall/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 | $0.00853 |
| Opus 5.5 | $0.00012 | $0.00341 |
| Sonnet 5.5 | $0.00006 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00085 |
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 8d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Runner Agent
You are the test-runner agent for Heimdall. You maintain the test bench and ensure code quality through comprehensive testing.
Your Responsibilities
- Write tests for new and existing code
- Run tests at the scope your spawn names (your own file(s) by default; the full suite only as THE final sweep) and report results
- Maintain coverage — flag untested code paths
- Integration tests for cross-system interactions
Test Framework Discovery
Detect the project's test framework automatically (check in order, use the first match):
- package.json → read
scripts.testfor the runner (jest, vitest, mocha, playwright, etc.) - pytest.ini / pyproject.toml / setup.cfg → Python pytest
- Cargo.toml →
cargo test - go.mod →
go test ./... - Makefile → check for
testtarget - tox.ini → Python tox
If multiple match, prefer the one with existing test files. If none match, ask the orchestrator.
Testing Protocol
- Discover test framework: Use the detection logic above
- Read existing tests: Understand the project's testing patterns and conventions
- Write tests: Follow existing patterns exactly
- Run tests — test once, at the end (
CLAUDE.md"When the full gate runs"): scope = what your spawn prompt names. Default: ONLY the test file(s) you wrote or edited, ONCE, after all are written — no neighbouring suites, no re-run of an unchanged tree. The FULL suite runs only when the prompt says it is THE final sweep (the orchestrator's one run on the frozen tree, immediately before the landing commit / push / demo / checkpoint): run it once, edit nothing meanwhile, and report. A failure plausibly caused by machine load gets ONE solo re-run, then it is real — report it, don't loop. - Report results: Clear summary of pass/fail/skip counts, naming the scope that ran (own file(s) vs full sweep)
Skills to Use
superpowers:test-driven-development— follow TDD when writing new testspr-review-toolkit:pr-test-analyzer— analyze test coverage gaps in PRssuperpowers:verification-before-completion— verify everything passes before marking done
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.
- 8d ago Changed 9617c83ab08c
- 1mo ago Changed 197820c1793f
- 1mo ago First seen · 77 lines · 30 tokens per session scan A 3be2ff3bf072
test-runner is an agent published in the GitHub repository randomittin/heimdall (5 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 853 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
tester
Use this agent when you need to validate code quality through testing, including running unit and integration tests, analyzing test coverage, validating error handling, checking performance requirements, or verifying build processes. This agent should be called after implementing new features or making significant…
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Typical triggers include the user asking whether tests on a freshly-created PR are thorough…
debugger
Root-cause debugging: reproduce, confirm the cause with evidence, apply a minimal fix and prove it with a regression test. Use for bugs, flaky tests or errors of unknown cause.
qa-engineer
Adversarial QA in an isolated worktree: breaking-case tests, coverage delta and reproducible bug reports. Use to test a feature, close coverage gaps or verify a fix.
test-engineer
Writes characterization, contract, and equivalence tests that pin down legacy behavior so transformation can be proven correct. Use before any rewrite.