copilot-tdd-harness: Agent for Claude Code

.github/agents/tdd-cycle-runner.agent.md

tdd-cycle-runner is an agent for Claude Code from mrlarson2007/copilot-tdd-harness. It costs 56 tokens per session (381 once invoked), scanned A, original, MIT.

An agent that runs one complete TDD cycle for a single software behavior. A cycle moves through Red, Green, Commit, and Refactor, then reports success or asks for help if a step fails.

In plain words
What is it for?
It takes a scenario slice and the relevant instructions, runs the four development stages, validates each result, and returns either a completed-cycle summary or an escalation report.
Why use it?
It keeps each development cycle small and controlled instead of mixing many changes together. It checks the handoff between each stage and escalates problems clearly.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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/agents/tdd-cycle-runner.agent.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-cycle-runner

README.md
[![agentmods](https://agentmods.dev/badge/agents/mrlarson2007/copilot-tdd-harness/tdd-cycle-runner.svg)](https://agentmods.dev/agents/mrlarson2007/copilot-tdd-harness/tdd-cycle-runner)
Your own site
<a href="https://agentmods.dev/agents/mrlarson2007/copilot-tdd-harness/tdd-cycle-runner"><img src="https://agentmods.dev/badge/agents/mrlarson2007/copilot-tdd-harness/tdd-cycle-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 381 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 $0.00056 $0.00381
Opus 5 $0.00028 $0.00191
Sonnet 5 $0.00011 $0.00076
Haiku 4.5 $0.00006 $0.00038

Measured 6d ago against content hash 9cdebe64256f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tdd-cycle-runner 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 6d 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/agents/tdd-cycle-runner.agent.md · 57 lines

What it actually says

TDD Cycle Runner Agent

Purpose

  • Owns the execution of a single TDD cycle for a scenario slice
  • Routes through Red, Green, Commit, Refactor phases
  • Loads phase skill and asset files for each step
  • Handles all contract handoffs and escalation
  • Reports only cycle-complete or escalate to the main orchestrator

Inputs

  • Scenario slice
  • Skill and asset references for each phase
  • Global guardrails and gates

Outputs

  • Cycle summary (on success)
  • Escalation contract (on failure)

Steps

  1. Receive start_cycle contract from main orchestrator
  2. For each phase (Red, Green, Commit, Refactor):
    • Load SKILL.md and asset files
  • Execute phase guidance through the loaded phase skill
  • Validate contract result
  • On failure, escalate to main orchestrator
  1. On completion, return cycle_complete contract

Quality Criteria

  • Only minimal context passed to each phase
  • All contract handoffs validated
  • No direct communication with main orchestrator by phase skill executions
  • Progressive disclosure enforced
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. 6d ago First seen · 57 lines · 56 tokens per session scan A 9cdebe64256f

Subscribe to this mod's changes

tdd-cycle-runner is an agent published in the GitHub repository mrlarson2007/copilot-tdd-harness (5 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 381 once invoked, about $0.0003 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.