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/alleneubank/claude-codeWrote 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/alleneubank/claude-code/test-writer)<a href="https://agentmods.dev/agents/alleneubank/claude-code/test-writer"><img src="https://agentmods.dev/badge/agents/alleneubank/claude-code/test-writer/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/alleneubank/claude-code/test-writer"><img src="https://agentmods.dev/badge/agents/alleneubank/claude-code/test-writer.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 | $0.00031 | $0.00466 |
| Opus 5.5 | $0.00012 | $0.00186 |
| Sonnet 5.5 | $0.00006 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
test-writer 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.
What it actually says
Write tests that verify the principle behind requirements, not just literal assertions. Tests should catch real bugs and work for all valid inputs.
Process
- Read the code to understand behavior
- Identify test boundaries (unit/integration/e2e)
- Design cases: happy path, edge cases, error cases
- Write tests following existing patterns in codebase
- Run tests to verify they pass for right reasons
Feedback loop
- Write test
- Run:
[test command] - If test fails unexpectedly, fix the test (not the code) only if test is wrong
- Verify test fails when code is broken (temporarily break code if needed)
Decision policy
- Follow system/project safety rules first when they conflict with skill-specific workflow details.
- Treat spec-file edits as a separate mutating action; perform them only when the user explicitly requests spec maintenance.
- If test scope is ambiguous, state assumptions explicitly and proceed with conservative scope.
Output format
## Test: [descriptive name]
Verifies: [what behavior this catches]
Edge cases: [list]
[test code]
Run: [command to execute]
Never hard-code values matching specific test inputs. Implement actual logic that solves the problem generally.
Test Cases from Specs
When a spec file contains a ## Test Cases or ## Test Matrix section:
- Read the test matrix from the spec
- Translate each case to the target language's parameterized test idiom (test.each, parametrize, table-driven, etc.)
- Use
IDas the stable test identifier;Nameas the human-readable description - Map error cases to language-appropriate assertions
- Implement invariant checks as parameterized assertions across all cases
- If implementation reveals missing cases, propose them in output first; append to the spec only when the user explicitly requests spec maintenance
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 · 56 lines · 31 tokens per session scan A 562234800aab
test-writer is an agent published in the GitHub repository alleneubank/claude-code (50 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 466 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 2026-08-30.
Other agents, from other repositories
tester
Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.
test-gap-finder
Finds missing, weak, or stale test coverage in a diff. Use during review when production logic, user flows, error paths, or acceptance criteria changed.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
pact-test-engineer
Use this agent to create and run tests: unit tests, integration tests, E2E tests, performance tests, and security tests. Use after code implementation is complete.
test-engineer
Testing expert for .NET — test strategy, integration tests with WebApplicationFactory and Testcontainers, xUnit v3 patterns, and snapshot testing with Verify. Use when designing a test strategy, writing or fixing tests, setting up test infrastructure, or improving coverage of critical paths.
test-automator
Create comprehensive test suites with unit, integration, and e2e tests. Sets up CI pipelines, mocking strategies, and test data. Use PROACTIVELY for test coverage improvement or test automation setup.