copilot-tdd-harness: Skill for Claude Code

.github/skills/tdd-test-run/SKILL.md

tdd-test-run is a skill for Claude Code from mrlarson2007/copilot-tdd-harness. It costs 41 tokens per session (456 once invoked), scanned A, original, MIT.

A test-driven development (TDD) step checker that runs the required test command and compares the result with the expected pass or fail outcome.

In plain words
What is it for?
Running and checking RED, GREEN, or REFACTOR steps in a TDD workflow, including targeted tests and scoped rollback after an unexpected result.
Why use it?
It prevents work from being marked complete based only on assumptions. If verification fails, it rolls back only the changes covered by that step.

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-test-run/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-test-run

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mrlarson2007/copilot-tdd-harness/tdd-test-run"><img src="https://agentmods.dev/badge/skills/mrlarson2007/copilot-tdd-harness/tdd-test-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 456 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 $0.00041 $0.00456
Opus 5 $0.00020 $0.00228
Sonnet 5 $0.00008 $0.00091
Haiku 4.5 $0.00004 $0.00046

Measured 9d ago against content hash 6b3d4056daff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tdd-test-run 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-test-run/SKILL.md · 51 lines

What it actually says

TDD Test Run Phase Skill

Purpose

  • Run the exact verification step required by RED, GREEN, or REFACTOR
  • Compare actual test output with the declared expected result
  • Prevent optimistic phase transitions that are not backed by execution
  • Revert only the in-scope changes for the current step when verification fails

Inputs

  • Phase name (red, green, or refactor)
  • Narrow or broad test command hint
  • Expected outcome contract (fail or pass, relevant test names, expected signal)
  • Files in scope for rollback
  • Project test command guidance from .github/instructions/tdd-patterns.instructions.md
  • Canonical test-run guidance placeholder at .github/skills/tdd-test-run/assets/project-test-run-patterns.md

Outputs

  • Verification command output
  • Match or mismatch result
  • Scoped rollback summary when a mismatch occurs

Steps

  1. Load .github/skills/tdd-test-run/assets/project-test-run-patterns.md first.
  2. Run the narrowest practical verification command that satisfies the contract.
  3. Compare the observed output with the declared expected result.
  4. If the expected result matches, return test_run_result with status: ok.
  5. If the expected result does not match:
    • Revert only the files listed in the contract scope.
    • Do not revert unrelated user changes.
    • If scoped rollback cannot be done safely, return status: escalate.
  6. Return test_run_result with the command output, match status, and any reverted files.

Completion Checks

  • The verification command actually ran.
  • The expected result was checked explicitly, not assumed.
  • Any rollback was limited to the scoped files for the current step.
  • A mismatch never advances the workflow to the next phase.
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 · 51 lines · 41 tokens per session scan A 6b3d4056daff

Subscribe to this mod's changes

tdd-test-run is a skill published in the GitHub repository mrlarson2007/copilot-tdd-harness (5 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 456 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.