tdd

tdd is a skill for Claude Code, Codex from lootlog/monorepo. It costs 60 tokens per session (376 once invoked), scanned A, original, MIT.

A guide to test-driven development (TDD), a way of writing a test for the intended behavior before writing the code that implements it.

In plain words
What is it for?
Use it for feature work, bug fixes, regression tests, and behavior changes with a practical unit, component, integration, or end-to-end test path.
Why use it?
It provides a focused check for the change and helps catch regressions without building unnecessarily large or brittle tests.

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

Made for: Claude Code, Codex.

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/lootlog/monorepo/tdd.svg)](https://agentmods.dev/skills/lootlog/monorepo/tdd)
Your own site
<a href="https://agentmods.dev/skills/lootlog/monorepo/tdd"><img src="https://agentmods.dev/badge/skills/lootlog/monorepo/tdd.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 376 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 $0.00060 $0.00376
Opus 5 $0.00030 $0.00188
Sonnet 5 $0.00012 $0.00075
Haiku 4.5 $0.00006 $0.00038

Measured 5d ago against content hash 1dbd8aa4a620, 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 5d 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.

.agents/skills/tdd/SKILL.md · 35 lines

What it actually says

Test-driven development

Make the intended behavior executable before changing production code.

Workflow

  1. Identify the intended behavior, current behavior, affected public seam, and smallest observable reproduction.
  2. Choose the narrowest existing test layer that can express the behavior. Prefer Vitest unit, component, or integration patterns already used by that workspace.
  3. Add one focused failing test. Assert behavior, not private implementation.
  4. Run it and confirm that it fails for the intended reason.
  5. Make the smallest production change that passes the test.
  6. Run the focused test again, then relevant adjacent tests, typecheck, and lint in proportion to the change.
  7. Refactor only while the tests remain green.

When a failing test is impractical

Do not build a large harness, mock most of the system, or introduce brittle timing merely to claim TDD. State why a focused failing test is not practical and use the closest executable check: a targeted script, an existing integration path, browser automation against the running app, a response assertion, or generated-output comparison.

Guardrails

  • Do not change assertions to bless incorrect behavior.
  • Do not test private functions when a public seam exists.
  • Mock only boundaries that cannot run locally.
  • Keep regression coverage specific to the defect.
  • For flaky behavior, first make the signal deterministic or measure its reproduction rate.

Report

Name the failing-before evidence, the passing-after evidence, and every adjacent check performed. If no red test was practical, report the substitute evidence explicitly.

Files

What ships with it

3 files 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. 5d ago First seen · 35 lines · 60 tokens per session scan A 1dbd8aa4a620

Subscribe to this mod's changes

tdd is a skill published in the GitHub repository lootlog/monorepo (10 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 376 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.