copilot-tdd-harness: Skill for Claude Code

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

requirements-planning is a skill for Claude Code from mrlarson2007/copilot-tdd-harness. It costs 22 tokens per session (664 once invoked), scanned A, original, MIT.

A planning aid for turning a broad software request into specific, testable behaviors. BDD means describing software behavior in business-readable scenarios, while TDD means using tests to guide development.

In plain words
What is it for?
It helps identify scenarios and express them as Given, When, Then statements. When the request is unclear, it asks one focused question before continuing.
Why use it?
It reduces confusion before coding starts by clarifying what the user needs and exposing edge cases. It keeps planning separate from writing production code and tests.

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/requirements-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 requirements-planning

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mrlarson2007/copilot-tdd-harness/requirements-planning"><img src="https://agentmods.dev/badge/skills/mrlarson2007/copilot-tdd-harness/requirements-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 664 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 $0.00022 $0.00664
Opus 5 $0.00011 $0.00332
Sonnet 5 $0.00004 $0.00133
Haiku 4.5 $0.00002 $0.00066

Measured 10d ago against content hash 129ef5a7d10a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

requirements-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 10d 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/requirements-planning/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Requirements Planning Skill

Use this skill before development to help break down a broad or ambiguous requirement into concrete, testable behaviors.

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

Purpose

Your audience is a software team that needs help breaking down a broad or ambiguous requirement into concrete, testable behaviors. The goal is to help the team think like a strong software engineer, QA, and requirements analyst using BDD and TDD principles to:

  • clarify what the user actually wants
  • identify candidate behaviors from a feature request
  • outline edge cases
  • outline key scenarios
  • express each planned behavior as a Given, When, Then scenario

Interaction Model

This skill is interactive.

  • The user provides the initial feature or behavior prompt.
  • The skill helps the user refine that request into concrete scenarios.
  • If the request is still ambiguous, ask exactly one focused clarification question and wait.
  • Do not continue planning until the user answers the clarification question.

Clarification Rules

Stop and ask exactly one focused question when any of the following are true:

  • the request names a feature area but not a specific behavior
  • the request has multiple plausible interpretations or stakeholder outcomes
  • the next Given, When, Then scenario would require guessing inputs, outputs, actors, or scope

Do not self-resolve ambiguity just because one option looks reasonable.

Required Output

When the request is clear enough, produce a requirements plan with these sections:

  • feature summary
  • stakeholders or affected users
  • assumptions or open questions
  • scenarios

Each scenario must:

  • describe one externally visible behavior
  • use explicit Given, When, Then formatting
  • include happy path or edge case intent clearly enough to guide later implementation and testing

File Output

When the plan is ready, propose writing it to a markdown file under:

Read the full file on GitHub · 83 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. 10d ago First seen · 83 lines · 22 tokens per session scan A 129ef5a7d10a

Subscribe to this mod's changes

requirements-planning is a skill published in the GitHub repository mrlarson2007/copilot-tdd-harness (5 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 664 once invoked, about $0.0001 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.