copilot-tdd-harness: Skill for Claude Code

.github/skills/tdd-planning/SKILL.md

tdd-planning is a skill for Claude Code from mrlarson2007/copilot-tdd-harness. It costs 45 tokens per session (684 once invoked), scanned A, original, MIT.

A planning guide for test-driven development (TDD), a method of writing a failing test before the code that makes it pass. It chooses the smallest concrete behavior to implement next and describes it with Given, When, Then steps.

In plain words
What is it for?
Use it before starting a TDD cycle or between cycles when you need to choose the next behavior, define its inputs and outputs, or identify missing requirements.
Why use it?
It turns broad or unclear requests into a testable next step. It also surfaces edge cases early and tells you when the request is too ambiguous to begin safely.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is mrlarson2007/copilot-tdd-harness's own configuration. It tells Claude Code how to work on copilot-tdd-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything copilot-tdd-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mrlarson2007/copilot-tdd-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mrlarson2007/copilot-tdd-harness/master/.github/skills/tdd-planning/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mrlarson2007/copilot-tdd-harness

Made for: Claude Code.

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-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrlarson2007/copilot-tdd-harness/tdd-planning/github.svg)](https://agentmods.dev/skills/mrlarson2007/copilot-tdd-harness/tdd-planning)
Your own site
<a href="https://agentmods.dev/skills/mrlarson2007/copilot-tdd-harness/tdd-planning"><img src="https://agentmods.dev/badge/skills/mrlarson2007/copilot-tdd-harness/tdd-planning/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tdd-planning

Your own site · 80×15
<a href="https://agentmods.dev/skills/mrlarson2007/copilot-tdd-harness/tdd-planning"><img src="https://agentmods.dev/badge/skills/mrlarson2007/copilot-tdd-harness/tdd-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 684 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00045 $0.00684
Opus 5 $0.00023 $0.00342
Sonnet 5 $0.00009 $0.00137
Haiku 4.5 $0.00005 $0.00068

Measured 9d ago against content hash 05e8fcafab83, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tdd-planning 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 9d 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.

.github/skills/tdd-planning/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD Planning Skill

Use this skill before the first RED cycle and again between cycles when the next behavior is not already obvious.

This skill is for planning only. It should not write production code, write tests, or execute a RED -> GREEN cycle.

Purpose

Help the agent think like a strong software engineer using TDD:

  • clarify what the user actually wants
  • identify candidate behaviors from a feature request
  • prefer edge cases before happy path when appropriate
  • choose the smallest falsifiable next slice
  • decide whether the request is concrete enough to start RED
  • when creating a test plan, use Given, When, Then format to specify each behavior and its expected outcome

Clarification Rules

Stop and ask exactly one focused question when the request is still too ambiguous to support a meaningful failing test.

Treat the request as too ambiguous when any of the following are true:

  • it names a category but not a specific behavior
  • it names multiple plausible behaviors without a clear first slice
  • choosing the next test would require guessing inputs, outputs, or scope

Do not self-resolve category-level ambiguity just because one option looks smallest.

Treat category-level requests as mandatory clarification points even if one candidate looks like the narrowest path. For example, "add another arithmetic subcommand" requires a question; do not assume subtract, multiply, or any other operation just to keep moving.

Do not use phrases like "assuming the new subcommand is...", "to proceed autonomously", or "I can pick the smallest behavior" when the request is still ambiguous. Ask the focused question instead and wait.

Planning Rubric

When multiple candidate behaviors are available, prefer the one that best fits this order:

  1. Can be described as one externally visible behavior
  2. Can be proven by one failing test
  3. Protects an edge case or risky boundary first, when that makes sense
  4. Requires the smallest production change that still moves the feature forward
  5. Leaves room for obvious follow-up cycles without speculative design

Read the full file on GitHub · 95 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. 9d ago First seen · 95 lines · 45 tokens per session scan A 05e8fcafab83

Subscribe to this mod's changes

tdd-planning is a skill published in the GitHub repository mrlarson2007/copilot-tdd-harness (5 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 684 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.