tdd

A test-driven development workflow using small vertical feature slices. Test-driven development, or TDD, means writing a failing test first, making it pass, then improving the code.

In plain words
What is it for?
Use it when building test-first, red-green-refactor changes, deciding where tests belong, or testing parsers, databases, command-line handlers, and scripts.
Why use it?
It keeps each change focused on one observable behavior and encourages verification after every passing step.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/stainless-code/codemap/tdd
Any agent
npx skills add stainless-code/codemap --skill tdd
Clone the repo
git clone --depth 1 https://github.com/stainless-code/codemap

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 672 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.00672
Opus 5 $0.00016 $0.00336
Sonnet 5 $0.00006 $0.00134
Haiku 4.5 $0.00003 $0.00067

Measured yesterday against content hash 8bf221d47570, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tdd 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 yesterday.

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.

.agents/skills/tdd/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test-driven development

Vertical RED→GREEN cycles — one behavior per loop, not horizontal "all tests then all code". Aligns with tracer-bullets and verify-after-each-step.

This repo

  • Runner split per docs/testing-coverage.md:
    • bun test ./src — co-located unit tests (parsers, DB, engines, CLI/MCP handlers). Mock at parser/DB seams.
    • bun run test:golden — index fixtures/minimal, run SQL scenarios vs committed goldens.
    • bun run test:scriptsscripts/**/*.test.mjs.
    • bun run test:agent-eval — probe/live agent eval harness (after golden index when applicable).
  • Co-locate tests next to the module (src/db.tssrc/db.test.ts).
  • After each GREEN: format/lint/typecheck per verify-after-each-step.
  • Mock at the parser or DB seam (fake :memory: DB, stub adapter input), never inside the engine under test. See PATTERNS.md.

Workflow

1. Planning

Confirm behaviors to test (not implementation steps) with the user. Prefer deep modules — small public surface (extractFileData, batchInsert, a recipe handler), complex internals.

2. Tracer bullet (within slice)

RED:   one test for first behavior → bun test <file>   (or test:golden when recipe/SQL output is the contract)
GREEN: minimal code to pass → re-run

3. Incremental loop

For each behavior: RED → GREEN → run affected tests. One test at a time; no speculative features.

4. Refactor

After GREEN — look for duplication, long methods, shallow modules, feature envy. Run bun test <file> after each step. Never refactor while RED. For production polish on a completed slice, harden-pr lite may run in parallel with tracer-bullet commits.

Checklist per cycle

[ ] Test describes behavior, not implementation
[ ] Test uses the public seam only (parser entry, DB insert path, CLI handler, recipe output)
[ ] Test would survive an internal refactor
[ ] Code is minimal for this test
[ ] bun test (or test:golden / test:scripts) passes on touched file(s)

Read the full file on GitHub · 56 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 56 lines · 32 tokens per session scan A 8bf221d47570

Subscribe to this mod's changes

tdd is a skill published in the GitHub repository stainless-code/codemap (8 stars, last pushed 6d ago), licensed MIT. It adds 32 tokens to every session and 672 once invoked, about $0.0002 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.

Related

Other skills, from other repositories