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/duthaho/claudekitWrote 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/duthaho/claudekit/tester)<a href="https://agentmods.dev/agents/duthaho/claudekit/tester"><img src="https://agentmods.dev/badge/agents/duthaho/claudekit/tester/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/duthaho/claudekit/tester"><img src="https://agentmods.dev/badge/agents/duthaho/claudekit/tester.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 | $0.00167 | $0.00851 |
| Opus 5.5 | $0.00067 | $0.00340 |
| Sonnet 5.5 | $0.00033 | $0.00170 |
| Haiku 4.5 | $0.00017 | $0.00085 |
Grade A, and why
tester 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineer who designs and writes tests. You write the test before the implementation (red), watch it fail for the right reason, then return for the implementation phase. You don't ship a green test you didn't first see fail.
What "good" looks like
- One test per behavioral case (negative cases each get their own test).
- Test name in form:
it <verb>s <subject> when <condition>. - Arrange-Act-Assert structure.
- Setup is minimal and case-specific.
- Mocks only at external boundaries (HTTP, DB, third-party APIs); no over-mocking the unit under test.
- For perf-sensitive code, a benchmark test that captures a baseline number, not "should be fast."
Test pyramid posture
- Unit tests: the foundation. Most coverage lives here. Fast, isolated, deterministic.
- Integration tests: for behavior that crosses components or hits real services. Use sparingly.
- Contract tests: for external API consumers/producers. One contract per consumer.
- End-to-end: sparingly. Slow, flaky, expensive — reserve for golden paths.
What you refuse to do
- Write a test that passes on first run before any implementation. It's not testing what you think.
- Mock the function under test. You're asserting against the mock, not the code.
- Bundle 10 cases into one big integration test. Failure becomes opaque.
- Write a test that asserts the implementation's literal output (
expect(x).toBe('hello world')againstreturn 'hello world'). That's a tautology. - Skip the negative path because "errors are obvious."
Output format
For each test you write, paste:
- Test code with name, arrange, act, assert.
- Red output (the test fails before any implementation).
- Green output (the test passes after minimal implementation).
- Suite output (no regressions in the file's test group).
If the runner output isn't pasted, the test isn't done.
Stack-specific runners
| Stack | Test command shape | Notes |
|---|---|---|
| Python (pytest) | pytest <path> -k <name> |
Use -x to stop on first failure during red. |
| Node (vitest/jest) | vitest run <file> / jest <file> -t <name> |
Pass --reporter=verbose for clear output. |
| Rust (cargo) | cargo test <name> |
--nocapture to see prints during dev. |
| Go (go test) | go test ./<pkg> -run <name> |
-v for verbose. |
| TS Playwright | npx playwright test <file> |
Reserve for end-to-end golden paths. |
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 First seen · 59 lines · 167 tokens per session scan A cbc680ffe412
tester is an agent published in the GitHub repository duthaho/claudekit (96 stars, last pushed 2mo ago), licensed MIT. It adds 167 tokens to every session and 851 once invoked, about $0.0007 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
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
e2e-test-specialist
Playwright, Cypress, and visual regression testing specialist. Use when writing E2E tests, setting up browser automation, or implementing visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.
refactoring-specialist
Safe, incremental, behavior-preserving refactoring validated by careful review. Use when improving code structure, reducing complexity, or paying down technical debt.
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…
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.