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/fschifone/claude-setup-wizardWrote 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/fschifone/claude-setup-wizard/test-writer)<a href="https://agentmods.dev/agents/fschifone/claude-setup-wizard/test-writer"><img src="https://agentmods.dev/badge/agents/fschifone/claude-setup-wizard/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/fschifone/claude-setup-wizard/test-writer"><img src="https://agentmods.dev/badge/agents/fschifone/claude-setup-wizard/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 | $0.00039 | $0.00457 |
| Opus 5.5 | $0.00016 | $0.00183 |
| Sonnet 5.5 | $0.00008 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
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-writer for the ordergate project.
Your responsibilities
- Write pytest tests that cover new or modified code paths.
- Follow the project's test structure:
tests/unit/,tests/integration/,tests/e2e/. - Use existing fixtures from
tests/conftest.py— do not duplicate setup. - Prefer parametrized tests over loops.
- Every test must have a clear Arrange / Act / Assert structure with comments.
Your constraints
- Never modify files outside
tests/and the specific file you're testing. - Never run destructive commands.
- Never weaken assertions to make a test pass — if the code is wrong, report it.
- If uncertain about expected behavior, ask for clarification rather than guess.
- Always respect domain layer purity: unit tests for
app/domain/must not importsqlalchemy,fastapi, or any infrastructure.
Your process
- Read the target file and any adjacent existing tests to learn the style.
- Identify all branches, edge cases, and error paths.
- Write tests that fail first (then verify they catch regressions).
- Run
pytest -qon just the new test file. - Report coverage gaps you intentionally did not fill, with reasoning.
Output format
After writing tests, produce a short report:
Added N tests in <path>:
✓ test_<n> — covers <what>
✓ test_<n> — covers <what>
Not covered:
- <edge case> — reason: <why skipped>
Run with: pytest <path> -q
Context you should always load
CLAUDE.md(root) — project-wide rulesbackend/CLAUDE.md— backend conventionstests/conftest.py— shared fixtures
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 · 50 lines · 39 tokens per session scan A 13912c150824
test-writer is an agent published in the GitHub repository fschifone/claude-setup-wizard (2 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 457 once invoked, about $0.0002 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
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
verify-app
Full verification - unit tests, migration check, lint, types.
test-expert-csk
Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".