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.
npx agentmods add skills/mountainunicorn/add/test-writernpx skills add MountainUnicorn/add --skill test-writergit clone --depth 1 https://github.com/MountainUnicorn/addWrote 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/skills/mountainunicorn/add/test-writer)<a href="https://agentmods.dev/skills/mountainunicorn/add/test-writer"><img src="https://agentmods.dev/badge/skills/mountainunicorn/add/test-writer.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.02579 |
| Opus 5 | $0.00009 | $0.01290 |
| Sonnet 5 | $0.00004 | $0.00516 |
| Haiku 4.5 | $0.00002 | $0.00258 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADD Test Writer Skill v{{VERSION}}
Generate comprehensive failing tests from a feature specification. This is the RED phase of TDD — write tests before implementation.
Overview
Test Writer converts acceptance criteria and user test cases from a spec into failing, runnable tests. The output is test files that:
- Compile and execute but fail (RED state)
- Have clear, descriptive names mapped to ACs
- Cover all acceptance criteria and user test cases
- Follow the project's test conventions
- Are production-quality (good error messages, clear assertions)
Pre-Flight Checks
-
Verify spec file exists and is readable
- Read the spec at the provided path
- Extract frontmatter: feature name, version, status
-
Parse acceptance criteria
- Read the Acceptance Criteria section
- Extract each AC with its ID (AC-001, AC-002, etc.)
- Extract the criteria description and conditions
-
Parse user test cases
- Read the User Test Cases section (if present)
- Extract each UT with ID (UT-001, UT-002, etc.)
- Note the setup, actions, and expected outcomes
-
Load test framework configuration
- Read .add/config.json
- Identify test.framework (jest, pytest, vitest, mocha, pytest, etc.)
- Load test.convention (naming pattern, directory structure, imports)
- Check test.type to determine default test type
-
Identify test file location
- Determine target directory from config (typically
tests/or__tests__/) - Determine file naming from convention
- Check if test file already exists; if so, append new tests
- Determine target directory from config (typically
-
Check for session handoff — per the Session-Handoff Preflight in
${CLAUDE_PLUGIN_ROOT}/references/skill-epilogue.md
Execution Steps
Step 1: Analyze Acceptance Criteria
For each acceptance criterion:
- Extract the requirement statement
- Break down into testable assertions
- Identify input conditions, actions, and expected outputs
- Note any data setup required
- Consider both happy path and edge cases
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.
- 4d ago First seen · 337 lines · 18 tokens per session scan A 9311f0c7842b
test-writer is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 2,579 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
maestro-work
Drive one accepted implementation unit test-first - smallest falsifiable behavior, minimum edits, evidence that names the real falsifier.
red-green-refactor
Guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green. Use when a user asks to practice TDD, write tests first, follow red-green-refactor, do test-driven development, write failing tests before code, or phrases like…
superpowers-zh
Use when constraining AI coding with Chinese TDD methodology, systematic debugging, code review, and verification workflows. Superpowers-zh: Chinese adaptation of the Superpowers AI-assisted programming skills and methodologies.
absolute-work
End-to-end, phase-gated SDLC for AI coding agents: relentless design interview → reviewed spec → dependency-graphed task board → safe-wave TDD execution → verification → converge. Handles features, bugs, refactors, greenfield projects, planning breakdowns, and migrations. Triggers on "absolute work", "build this…
writing-skills
Methodology for creating effective skills using TDD principles. Use when creating new skills, editing existing skills, or authoring plugin components. Triggers on: 'create skill', 'write skill', 'new skill', 'skill authoring'.
simple-tdd
Test-driven development methodology — write the failing test first, then the minimum code to pass it.