tdd

tdd is a skill for Claude Code, Codex from bartolli/kmd. It costs 133 tokens per session (1,945 once invoked), scanned A, original, MIT.

A test-driven development workflow for implementing one user-story slice at a time. It uses the story’s Gherkin scenarios—structured Given/When/Then examples—as the test specification and follows a red-green-refactor cycle.

In plain words
What is it for?
Implementing a ready-to-build slice from a wiki story, writing integration tests from scenarios, and checking the project’s specifications and architecture decisions before coding.
Why use it?
It turns written requirements into integration tests and keeps tests focused on observable behavior, reducing tests that break during harmless code refactoring.

Skill for Claude CodeCodex

Part of the wiki-sdd plugin — 9 skills, 5 hooks shipped together

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/bartolli/kmd/tdd
Any agent
npx skills add bartolli/kmd --skill tdd
Clone the repo
git clone --depth 1 https://github.com/bartolli/kmd

Made for: Claude Code, Codex.

Or install wiki-sdd, the plugin that ships this one along with the rest of its 9 skills, 5 hooks.

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 tdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/bartolli/kmd/tdd.svg)](https://agentmods.dev/skills/bartolli/kmd/tdd)
Your own site
<a href="https://agentmods.dev/skills/bartolli/kmd/tdd"><img src="https://agentmods.dev/badge/skills/bartolli/kmd/tdd.svg" alt="Measured on agentmods" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,945 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 $0.00133 $0.01945
Opus 5 $0.00067 $0.00972
Sonnet 5 $0.00027 $0.00389
Haiku 4.5 $0.00013 $0.00194

Measured 3d ago against content hash 829548719597, 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 3d 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/claude/wiki-sdd/skills/tdd/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD — Vertical Tracer-Bullet Test-Driven Development

Take ONE ready-for-agent slice from a wiki story and implement it with the red-green-refactor loop. The story's Gherkin scenarios ARE the test specification — translate them directly into integration tests.

Prerequisites

  • WIKI_SCOPE: <scope> declared in the project instructions.
  • Target slice exists in a story file at projects/<scope>/plan/<plan-name>/story-N-<slug>.md.
  • The parent story's triage_state is ready-for-agent. If needs-info or needs-triage, suggest /triage first.

Philosophy

Test behavior through public interfaces, not implementation details. Code can change entirely; tests shouldn't.

  • Good tests are integration-style: they exercise real code paths through public APIs. They describe what the system does, not how. They survive refactors.
  • Bad tests are coupled to implementation: mock internal collaborators, test private methods, query internals directly. Warning sign: test breaks when you refactor but behavior hasn't changed.

A story's Gherkin scenarios are your test specification. Each Scenario block translates to one integration test. Given/When/Then maps to setup/action/assertion.

Anti-pattern: Horizontal slicing — REFUSED

DO NOT write all tests first, then all implementation. This is "horizontal slicing" — treating RED as "write all tests" and GREEN as "write all code."

WRONG (horizontal):
  RED:   test1, test2, test3, test4, test5
  GREEN: impl1, impl2, impl3, impl4, impl5

RIGHT (vertical):
  RED→GREEN: test1→impl1
  RED→GREEN: test2→impl2
  RED→GREEN: test3→impl3

Why horizontal produces crap tests:

  • Tests written in bulk test imagined behavior, not actual behavior.
  • You end up testing the shape of things rather than user-facing behavior.
  • Tests become insensitive to real changes.
  • You outrun your headlights — committing to test structure before understanding the implementation.

If you find yourself writing test #2 before test #1's implementation passes, stop. Finish the green for #1 first.

Read the full file on GitHub · 177 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. 3d ago First seen · 177 lines · 133 tokens per session scan A 829548719597

Subscribe to this mod's changes

tdd is a skill published in the GitHub repository bartolli/kmd (7 stars, last pushed 23d ago), licensed MIT. It adds 133 tokens to every session and 1,945 once invoked, about $0.0007 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.