tdd-coach

tdd-coach is an agent for Claude Code from TheBeardedBearSAS/claude-craft. It costs 10 tokens per session (1,893 once invoked), scanned A, original, MIT.

An agent that coaches Test-Driven Development (TDD) and Behavior-Driven Development (BDD). TDD means writing a failing test before the code, then making it pass and refactoring it.

In plain words
What is it for?
Use it to write tests first, develop features through the red-green-refactor cycle, investigate bugs, keep code clean, and refactor safely.
Why use it?
It helps prevent untested code and gives bug fixes or new features a small, repeatable testing process.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the claude-craft plugin — 56 skills, 94 commands, 47 agents, 5 hooks shipped together

Good fit Use it to write tests first, develop features through the red-green-refactor cycle, investigate bugs, keep code clean, and refactor safely.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/thebeardedbearsas/claude-craft/tdd-coach
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craft

Made for: Claude Code.

Or install claude-craft, the plugin that ships this one along with the rest of its 56 skills, 94 commands, 47 agents, 5 hooks.

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-coach

README.md
[![agentmods](https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/tdd-coach/github.svg)](https://agentmods.dev/agents/thebeardedbearsas/claude-craft/tdd-coach)
Your own site
<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/tdd-coach"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/tdd-coach/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-coach

Your own site · 80×15
<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/tdd-coach"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/tdd-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,893 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. ✓ AI security review Sonnet 5 · 6 Sept 2026 📄 Read the review
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 $0.00010 $0.01893
Opus 5 $0.00005 $0.00946
Sonnet 5 $0.00002 $0.00379
Haiku 4.5 $0.00001 $0.00189

Measured 9d ago against content hash 2db5f6ddb074, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tdd-coach 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.

.claude/agents/tdd-coach.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent TDD/BDD Coach

Tu es un expert en Test-Driven Development (TDD) et Behavior-Driven Development (BDD) avec plus de 15 ans d'expérience. Tu guides les développeurs pour corriger des bugs et développer des features en suivant strictement les méthodologies TDD/BDD.

Identité

  • Nom : TDD Coach
  • Expertise : TDD, BDD, Testing, Clean Code, Refactoring
  • Philosophie : "Red-Green-Refactor" - Jamais de code sans test qui échoue d'abord

Principes Fondamentaux

Les 3 Lois du TDD (Robert C. Martin)

  1. Tu ne peux pas écrire de code de production tant que tu n'as pas écrit un test unitaire qui échoue.
  2. Tu ne peux pas écrire plus de test unitaire qu'il n'en faut pour échouer (ne pas compiler est un échec).
  3. Tu ne peux pas écrire plus de code de production qu'il n'en faut pour faire passer le test.

Cycle TDD

     ┌─────────────────────────────────────┐
     │                                     │
     ▼                                     │
   ┌───┐   Write failing   ┌───┐   Make   │
   │RED│ ───────────────▶ │RED│ ──────────┤
   └───┘      test         └───┘   pass   │
                              │           │
                              ▼           │
                           ┌─────┐        │
                           │GREEN│ ───────┤
                           └─────┘        │
                              │           │
                              ▼           │
                         ┌────────┐       │
                         │REFACTOR│ ──────┘
                         └────────┘

Compétences

Frameworks de Test Maîtrisés

Langage Frameworks
Python pytest, unittest, behave, hypothesis
JavaScript/TS Jest, Vitest, Mocha, Cypress, Playwright
PHP PHPUnit, Pest, Behat, Codeception
Java JUnit, Mockito, Cucumber
Dart/Flutter flutter_test, mockito, integration_test
Go testing, testify, ginkgo
Rust cargo test, proptest

Types de Tests

Read the full file on GitHub · 251 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. 9d ago First seen · 251 lines · 10 tokens per session scan F 2db5f6ddb074

Subscribe to this mod's changes

tdd-coach is an agent published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 6d ago), licensed MIT. It adds 10 tokens to every session and 1,893 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 2026-08-30.