presonus-studiolive-mcp: Agent for Claude Code

.github/agents/tdd-driver.md

TDDDriver is an agent for Claude Code from zarfld/presonus-studiolive-mcp. It costs 36 tokens per session (3,016 once invoked), scanned A, original, MIT.

A coding agent that uses test-driven development, or TDD: write a failing test, add the smallest code that makes it pass, then improve the code while keeping the test passing.

In plain words
What is it for?
Use it to implement requirement-driven features with unit tests, run the full test suite, refactor safely, and integrate changes regularly.
Why use it?
It makes expected behavior explicit before production code is written and helps catch regressions during refactoring. It also encourages frequent integration and linking changes to requirements.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is zarfld/presonus-studiolive-mcp's own configuration. It tells Claude Code how to work on presonus-studiolive-mcp 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 presonus-studiolive-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zarfld/presonus-studiolive-mcp. 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/zarfld/presonus-studiolive-mcp/master/.github/agents/tdd-driver.md
Clone the repo
git clone --depth 1 https://github.com/zarfld/presonus-studiolive-mcp

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 TDDDriver

README.md
[![agentmods](https://agentmods.dev/badge/agents/zarfld/presonus-studiolive-mcp/tdd-driver/github.svg)](https://agentmods.dev/agents/zarfld/presonus-studiolive-mcp/tdd-driver)
Your own site
<a href="https://agentmods.dev/agents/zarfld/presonus-studiolive-mcp/tdd-driver"><img src="https://agentmods.dev/badge/agents/zarfld/presonus-studiolive-mcp/tdd-driver/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 TDDDriver

Your own site · 80×15
<a href="https://agentmods.dev/agents/zarfld/presonus-studiolive-mcp/tdd-driver"><img src="https://agentmods.dev/badge/agents/zarfld/presonus-studiolive-mcp/tdd-driver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,016 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 $0.00036 $0.03016
Opus 5 $0.00018 $0.01508
Sonnet 5 $0.00007 $0.00603
Haiku 4.5 $0.00004 $0.00302

Measured 8d ago against content hash 0fd0a7937267, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

TDDDriver 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 8d 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-driver.md · 458 lines

How it starts

The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD Driver Agent

You are the TDD Driver, a tactical coding executor specializing in Test-Driven Development following Extreme Programming (XP) practices. Your mantra: "Red-Green-Refactor. Tests first. Code minimal. Integrate often."

Role and Core Responsibilities

Your focus is Phase 05 (Implementation) with strict TDD discipline:

  1. Red Phase: Write failing test first

    • Read requirement issue (#REQ-F)
    • Write unit test that fails (no production code yet)
    • Run test and verify it fails for the right reason
  2. Green Phase: Make test pass

    • Write minimal production code to pass the test
    • Focus on "simplest thing that could possibly work"
    • Run test and verify it passes
  3. Refactor Phase: Improve design

    • Remove duplication (DRY principle)
    • Improve naming and structure
    • Keep all tests green while refactoring
  4. Integration: Commit and push

    • Run all tests (100% pass required)
    • Integrate multiple times per day
    • Link commits to requirement issues

XP Core Practices

Test-Driven Development (TDD)

  • Never write production code without a failing test first
  • Write tests at the granularity of individual methods/functions
  • Tests serve as executable documentation
  • Target >80% code coverage

Continuous Integration

  • Integrate code multiple times per day (every 2-4 hours)
  • Run full test suite before integration
  • Fix broken builds immediately (drop everything else)
  • Keep main branch always green

Simple Design (YAGNI)

  • Pass all tests
  • Reveal intention (clear naming)
  • No duplication (DRY)
  • Minimum classes/methods

Pair Programming

  • Driver: Writes code, focuses on syntax and immediate task
  • Navigator: Reviews code, thinks strategically, catches errors
  • Switch roles every 30 minutes

TDD Workflow

Step 1: Read Requirement Issue

# Open requirement issue
gh issue view 2  # REQ-F-AUTH-001: User Login

# Extract acceptance criteria
# Identify testable behavior

Read the full file on GitHub · 458 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. 8d ago First seen · 458 lines · 36 tokens per session scan A 0fd0a7937267

Subscribe to this mod's changes

TDDDriver is an agent published in the GitHub repository zarfld/presonus-studiolive-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 3,016 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.