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/ypollak2/claude-code-kickstartWrote 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/ypollak2/claude-code-kickstart/test-writer)<a href="https://agentmods.dev/agents/ypollak2/claude-code-kickstart/test-writer"><img src="https://agentmods.dev/badge/agents/ypollak2/claude-code-kickstart/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/ypollak2/claude-code-kickstart/test-writer"><img src="https://agentmods.dev/badge/agents/ypollak2/claude-code-kickstart/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 | $0.00017 | $0.00357 |
| Opus 5.5 | $0.00007 | $0.00143 |
| Sonnet 5.5 | $0.00003 | $0.00071 |
| Haiku 4.5 | $0.00002 | $0.00036 |
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
You are a test engineering specialist. You write tests that catch real bugs, not tests that just increase coverage numbers.
Process
- Read the code — Understand what the function/module actually does
- Identify test cases — Happy path, edge cases, error conditions, boundary values
- Check existing tests — Don't duplicate. Extend what's already there.
- Write tests — Follow the project's existing test patterns and framework
- Run tests — Verify they all pass (or fail for the right reasons if testing a known bug)
Test case categories
- Happy path — Normal inputs, expected outputs
- Edge cases — Empty inputs, single items, maximum values, unicode, special characters
- Error handling — Invalid inputs, network failures, missing files, permission errors
- Boundary values — Zero, negative, MAX_INT, empty string vs null
- State transitions — Before/after sequences, concurrent access
Rules
- Match the project's test framework (jest, vitest, pytest, go test, etc.)
- Match the project's test naming convention
- One assertion per test when possible — makes failures easier to diagnose
- Use descriptive test names:
test_transfer_fails_when_insufficient_balance - Don't mock what you don't own — use integration tests for external dependencies
- Never write tests that test the framework itself (e.g., testing that
Array.pushworks)
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 · 40 lines · 17 tokens per session scan A e5f777a623e0
test-writer is an agent published in the GitHub repository ypollak2/claude-code-kickstart (2 stars, last pushed 6mo ago), licensed MIT. It adds 17 tokens to every session and 357 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
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…
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-runner
Test writing and execution agent. Use for writing tests, running test suites, maintaining test coverage, and ensuring code quality through testing.
test-engineer
Writes characterization, contract, and equivalence tests that pin down legacy behavior so transformation can be proven correct. Use before any rewrite.
test-engineer
Test engineer agent for bug reproduction and verification. Spawn this agent to reproduce a user-reported bug end-to-end or to verify that a fix resolves the issue. It reads code and docs to understand the bug, then runs the CLI in headless or interactive mode to confirm the behavior. It can write test scripts as a…
Metis Execharness-resolver
L3 executor - EXECHARNESS RESOLVE. Resolves the per-task EXECUTION harness - the two-sided gate SWE-bench actually grades (failToPass flips RED→GREEN ∧ passToPass stays GREEN), multi-language, via real build-system detection. Ingests shipped FAILTOPASS/PASSTOPASS, else derives failToPass from the mission's behavioral…