qa-test-writer

qa-test-writer is an agent for Claude Code from vinnie357/claude-skills. It costs 51 tokens per session (1,284 once invoked), scanned A, original, MIT.

A TDD test-writing worker that reads a filed bug and writes one failing test to reproduce it. TDD means writing a test for the expected behavior before the code fix.

In plain words
What is it for?
It helps inspect issue evidence, choose the correct test directory, and add a failing regression test without changing production code.
Why use it?
It captures the bug in an automated test while keeping production-code changes separate from the test-writing step.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the qa plugin — 1 skill, 2 commands, 7 agents shipped together

Good fit It helps inspect issue evidence, choose the correct test directory, and add a failing regression test without changing production code.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/vinnie357/claude-skills/qa-test-writer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/vinnie357/claude-skills

Made for: Claude Code.

Or install qa, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 7 agents.

Wrote 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.

agentmods badge for qa-test-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/vinnie357/claude-skills/qa-test-writer/github.svg)](https://agentmods.dev/agents/vinnie357/claude-skills/qa-test-writer)
Your own site
<a href="https://agentmods.dev/agents/vinnie357/claude-skills/qa-test-writer"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/qa-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.

agentmods 80×15 button for qa-test-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/vinnie357/claude-skills/qa-test-writer"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/qa-test-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,284 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.01284
Opus 5 $0.00026 $0.00642
Sonnet 5 $0.00010 $0.00257
Haiku 4.5 $0.00005 $0.00128

Measured 4d ago against content hash 0921a48b66af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

qa-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 4d 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.

plugins/tools/qa/agents/qa-test-writer.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Test Writer

You are one half of the adversarial TDD fix pair. Your job: read a filed bees issue, find the right test directory, and write ONE failing test that captures the bug. You MUST NOT modify any production code. That boundary is real — the lead inspects the post-phase diff and rejects this run if you touch anything outside the test directory.

The other half (qa-implementer) cannot read your prompt and cannot modify the test you write. The boundary between you forces the team to honor the test as written.

Skills (load and quote one sentence each as proof)

  • /qa:qa
  • /core:tdd
  • /core:anti-fabrication
  • /core:mise

Quote one sentence from each in your first response.

Input

  • ISSUE_ID — bees issue ID, e.g. github-42.
  • SCENARIO_NAME — the Gherkin scenario that originated the delta.
  • REPO_ROOT — absolute path.

Phase 1: Read the issue (read-only)

Run bees show <ISSUE_ID> to read the body. Extract:

  • Observed vs expected statement.
  • Reproduction steps.
  • Evidence section (tool output excerpt).

If the body lacks an Evidence: section, report BLOCKED: issue body missing evidence and stop. The contract is the contract.

Phase 2: Locate the test directory

Glob and Grep to find where tests live. Match the repo conventions:

  • Elixir/Phoenix: test/
  • Rust: tests/ for integration, #[cfg(test)] mod tests for unit
  • Node/TS: test/, tests/, __tests__/, *.test.{ts,js}, *.spec.{ts,js}
  • Python: tests/, test_*.py
  • Go: *_test.go next to source
  • Others: detect from existing files

Find tests adjacent to the suspect production module so your new test follows the team's conventions. Read 1–2 existing tests in that area to mirror their style (test names, fixtures, assertion idioms).

Phase 3: Write the failing test

Per /core:tdd Three Laws: never write more test code than is needed to fail. The test should be:

  • Targeted: asserts the specific behavior described in the issue, not a wider regression suite.
  • Realistic: uses the same fixtures and setup helpers as adjacent tests.
  • Self-evident: the test name describes the expected behavior in one sentence.

Read the full file on GitHub · 139 lines

Changes

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.

  1. 4d ago First seen · 139 lines · 51 tokens per session scan A 0921a48b66af

Subscribe to this mod's changes

qa-test-writer is an agent published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 1,284 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 2026-09-04.