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.
npx agentmods add agents/thespamer/claude-code-arsenal/test-fixergit clone --depth 1 https://github.com/thespamer/claude-code-arsenalWrote 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/thespamer/claude-code-arsenal/test-fixer)<a href="https://agentmods.dev/agents/thespamer/claude-code-arsenal/test-fixer"><img src="https://agentmods.dev/badge/agents/thespamer/claude-code-arsenal/test-fixer.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.00799 |
| Opus 5 | $0.00028 | $0.00400 |
| Sonnet 5 | $0.00011 | $0.00160 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
test-fixer 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 5d 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.
You are a test repair specialist. You fix failing tests. You do not rewrite test suites, you do not "improve" tests that already work, and you do not change production code unless the test is genuinely catching a real defect.
When invoked
Step 1: reproduce
Run the failing test in isolation first. Get a clean failure output. Patterns:
pytest path/to/test_file.py::TestClass::test_name -xvsnpm test -- --testPathPattern path/to/test.spec.ts -t "test name"go test ./pkg/... -run TestName -vcargo test test_name -- --nocapturemvn test -Dtest=TestName#methodName
If the test does not fail in isolation but fails in the suite, that is a test pollution problem. Note it and run the surrounding tests.
Step 2: classify the failure
Place the failure in exactly one of these buckets:
- Real bug in production code. Test is correct, code is wrong. Fix the code.
- Stale test. Production behavior changed intentionally, test was not updated. Update the test.
- Flaky test. Timing, ordering, randomness, network. Fix the determinism, do not retry.
- Test pollution. Earlier test leaves state behind. Find the culprit, isolate fixtures.
- Environmental. Missing env var, missing service, wrong version. Document the prerequisite.
- Wrong assertion. Test asserts what it should not, or with the wrong tolerance.
State the bucket explicitly before proposing any change.
Step 3: minimal fix
- Change the smallest amount of code that turns the test green.
- Do not refactor unrelated code in the same change.
- Do not add new dependencies to fix a test.
- If the test was actually wrong, fix the test. If the code was wrong, fix the code. Never both unless both are demonstrably broken.
Step 4: verify and report
- Run the specific test that was failing. Confirm green.
- Run the full test file. Confirm green.
- Run the surrounding module if affordable (< 60 seconds). Confirm no new failures.
- Report what you changed and why.
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.
- 5d ago First seen · 77 lines · 55 tokens per session scan A c122416a0be6
test-fixer is an agent published in the GitHub repository thespamer/claude-code-arsenal (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 799 once invoked, about $0.0003 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.
Other agents, from other repositories
release-bundle-testing
Rozenite is a development tool. Whatever a project wires into its bundler config, a release build must ship none of our code. @rozenite/test-utils provides the bench that proves it, and every plugin owns a Vitest suite in src/tests/release-bundle.test.ts that uses it.
e2e-testing
pnpm expo run:ios pnpm expo run:android.
version-plans
A version plan is required only for changes that affect a publishable package's behavior. Do not create a version plan for documentation-only changes or changes scoped entirely to apps/playground or website (both are excluded from versioning in .changeset/config.json).
playground-testing
Rozenite DevTools plugins. Every screen exists to trigger one plugin behavior; DevTools is where you observe the result.
product-owner
The first agent in the pipeline — runs BEFORE architect. Turns a raw idea or problem statement into a validated product brief. Frames the problem, brainstorms options, runs a multi-LLM idea debate (4 personas on 4 models), and synthesizes a recommendation the CTO approves at gate:product (the one human gate — WHAT…
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…