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 skills add stark-ai-de/agent-skills --skill test-first-implementationgit clone --depth 1 https://github.com/stark-ai-de/agent-skillsWrote 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/stark-ai-de/agent-skills/test-first-implementation)<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/test-first-implementation"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/test-first-implementation.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 5.1 | $0.00050 | $0.00627 |
| Opus 5 | $0.00025 | $0.00313 |
| Sonnet 5 | $0.00010 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
test-first-implementation 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 7d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-First Implementation
Goal
Drive implementation from observable behavior: write a failing test, make it pass with the smallest change, then refactor without changing behavior.
When to use
- The user asks for TDD, red-green-refactor, test-first implementation, or regression-first work.
- A feature can be expressed as observable behavior, API output, UI state, CLI output, or integration behavior.
- A bug fix should start with a failing regression test.
When not to use
- The repo has no runnable feedback loop and the user only needs a prototype.
- The task is documentation-only or configuration-only.
- The user explicitly asks for implementation without adding tests.
Inputs to inspect
- User story, acceptance criteria, bug reproduction, or expected behavior.
- Existing tests, test helpers, fixtures, and package scripts.
docs/agents/validation.mdwhen present.- Nearby production code only after selecting the behavior boundary.
Workflow
- Identify the smallest vertical behavior slice.
- Choose the most stable observable test boundary; avoid testing private implementation details.
- Write or update a test that fails for the right reason.
- Run the focused test and capture the red result.
- Implement the minimum production change.
- Run the focused test again and capture the green result.
- Refactor only if it improves clarity without broadening scope.
- Run the smallest relevant validation suite.
Safety rules
- Do not test private helpers just to make coverage easy.
- Do not add snapshots for behavior that should be asserted directly.
- Do not change production code before proving the test fails unless the repo cannot run tests.
- Do not broaden the feature while chasing test convenience.
References
No bundled references. Use downstream docs/agents/validation.md for test commands and domain docs for expected behavior when present.
Scripts
No bundled scripts.
Output format
Return:
- Behavior slice selected
- Test boundary and why it was chosen
- Red result
- Implementation summary
- Green result
- Follow-up validation
- Remaining risks
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.
- 7d ago First seen · 87 lines · 50 tokens per session scan A 65ff574e4372
test-first-implementation is a skill published in the GitHub repository stark-ai-de/agent-skills (5 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 627 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 2026-08-31.
Other skills, from other repositories
write-tests
Write meaningful tests from acceptance criteria, risk, security invariants, module boundaries, and regression history. Use when adding or updating tests, writing a test plan, or covering a new feature or bug fix.
tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
react-web
React web development with hooks, React Query, Zustand.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
test-driven-development
Enforces TDD discipline with RED-GREEN-REFACTOR cycle. Use when writing new features, fixing bugs, or refactoring code. Ensures tests genuinely verify behavior.