copilot-tdd-harness: Skill for Claude Code

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

tdd-green is a skill for Claude Code from mrlarson2007/copilot-tdd-harness. It costs 35 tokens per session (566 once invoked), scanned A, original, MIT.

A guide for the green phase of test-driven development, or TDD: writing the smallest production-code change that makes a failing test pass.

In plain words
What is it for?
Use it to implement one tested behavior, distinguish compilation failures from assertion failures, run the narrow test, and commit after it passes.
Why use it?
It prevents unnecessary implementation, test changes, and early refactoring while a behavior is being added.

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-green/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-green

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mrlarson2007/copilot-tdd-harness/tdd-green"><img src="https://agentmods.dev/badge/skills/mrlarson2007/copilot-tdd-harness/tdd-green.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 566 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 $0.00035 $0.00566
Opus 5 $0.00017 $0.00283
Sonnet 5 $0.00007 $0.00113
Haiku 4.5 $0.00003 $0.00057

Measured 9d ago against content hash 5151c4d13777, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tdd-green 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-green/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD Green Phase Skill

Purpose

  • Write the simplest code to make the failing test pass
  • Do not modify tests in this phase
  • No refactoring or generalization
  • Commit after tests pass

Inputs

  • Failing test id
  • Skill and asset references
  • Project code style patterns from .github/instructions/tdd-patterns.instructions.md
  • Canonical GREEN style guide placeholder at .github/skills/tdd-green/assets/project-code-style-patterns.md

Outputs

  • Changed production files
  • Test pass summary

Steps

  1. Load .github/skills/tdd-green/assets/project-code-style-patterns.md first, then load core asset files for minimal implementation, anti-patterns, and commit discipline
  2. Check whether the RED test compiles.
    • If the test references missing production symbols (types, methods, fields), the only allowed edit is the smallest possible compile-only stub — no behavior.
    • Run the narrow test again. It must now compile and fail at runtime/assertion level before proceeding.
    • This is the distinction between structural red (compile failure) and behavioral red (assertion failure). Both are RED; behavior must not be added until you are at behavioral red.
  3. Judge the next GREEN move before editing production code.
  • Ask whether the change is the dumbest possible thing that makes only the current test pass.
  • If the change also solves untested cases, tries to generalize, or looks like the feature instead of the slice, it is too broad.
  • Prefer a constant, hardcoded branch, or the narrowest exact-case behavior the current test demands.
  • Do not move from behavioral red into generalized implementation just because the change is small.
  1. Write minimal code to pass the test
  2. Use tdd-test-run with a test_run_request contract whose expected result is a passing narrow check for the protected test or slice
  3. If the observed result does not match the expected GREEN outcome, revert only the scoped production changes and return to the preceding GREEN decision point
  4. Run the broader validation required by project policy through tdd-test-run before reporting GREEN complete
  5. Return contract output

Read the full file on GitHub · 54 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. 9d ago First seen · 54 lines · 35 tokens per session scan A 5151c4d13777

Subscribe to this mod's changes

tdd-green is a skill published in the GitHub repository mrlarson2007/copilot-tdd-harness (5 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 566 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.