tdd

tdd is a skill for Claude Code, Codex from kaininx/PlainTab. It costs 37 tokens per session (560 once invoked), scanned A, original, MIT.

Test-driven development (TDD) guidance for PlainTab, where you write a check for user-visible behavior before changing the code, then make it pass and improve the code.

In plain words
What is it for?
Useful for testing runtime modules, settings, saved configuration, wallpaper loading, and the rendered new-tab page with Node scripts, browser checks, or manual verification.
Why use it?
It helps catch regressions by defining what should work before implementation changes begin.

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

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/kaininx/plaintab/tdd.svg)](https://agentmods.dev/skills/kaininx/plaintab/tdd)
Your own site
<a href="https://agentmods.dev/skills/kaininx/plaintab/tdd"><img src="https://agentmods.dev/badge/skills/kaininx/plaintab/tdd.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 560 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 $0.00037 $0.00560
Opus 5 $0.00018 $0.00280
Sonnet 5 $0.00007 $0.00112
Haiku 4.5 $0.00004 $0.00056

Measured 3d ago against content hash a682a128f7c2, 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.

.agents/skills/tdd/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PlainTab TDD

Use this skill when changing runtime behavior. Adapted for PlainTab from Matt Pocock's tdd skill.

Philosophy

Tests should describe observable behavior through the public interface, not internal structure. In PlainTab, the public interface might be a runtime module API, a settings interaction, a stored config shape, a wallpaper source lifecycle, or the rendered new-tab page.

PlainTab has no package manager or test framework. Do not add one. Use focused Node scripts, browser automation, and existing validation commands.

Before Code

  1. Read .claude/rules/00-core.md and the relevant module rule.
  2. Identify the behavior to lock down in user-facing language.
  3. Choose the smallest useful feedback loop:
    • Node script in docs/ai-tasks/ for pure JS behavior.
    • Browser/Playwright check for DOM, settings, command palette, or wallpaper rendering.
    • Manual web-mode check only when automation is not practical.
  4. Name the check after behavior, not implementation.

Red-Green Loop

Work one vertical slice at a time:

  1. RED: write one failing check for one behavior.
  2. Verify RED: run it and confirm it fails for the expected reason.
  3. GREEN: write the smallest production change to pass.
  4. Verify GREEN: run the check again.
  5. Repeat for the next behavior.

Do not write a batch of tests and then a batch of implementation. Do not refactor while RED.

PlainTab Test Shape

Good checks:

  • Exercise real modules and real serialized config shapes.
  • Preserve existing localStorage keys unless the task includes a migration.
  • Cover extension/web-mode differences when the behavior depends on browser APIs.
  • Assert visible wallpaper safety when touching image layers: at least one layer should remain visible.
  • Assert language key completeness when adding UI copy.

Avoid:

  • Adding npm, package.json, lint frameworks, test frameworks, or frontend frameworks.
  • Tests that only assert private helper names or DOM implementation details unrelated to behavior.
  • Long startup work in repro code that would never exist in the real first-paint path.

Read the full file on GitHub · 64 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. 3d ago First seen · 64 lines · 37 tokens per session scan A a682a128f7c2

Subscribe to this mod's changes

tdd is a skill published in the GitHub repository kaininx/PlainTab (88 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 560 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 2026-08-30.