tdd

tdd is a command for coding agents from RchGrav/claudebox. It costs 7 tokens per session (681 once invoked), scanned A, original, MIT.

A strict Test-Driven Development workflow. TDD means writing one failing test first, adding the smallest code that passes it, and then improving the code without breaking the test.

In plain words
What is it for?
Developing new code one behavior at a time, making legacy code testable with characterization tests, and committing each complete test-and-code cycle.
Why use it?
It prevents large untested implementations and keeps each code change tied to a specific expected behavior.

Command

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.

agentmods
npx agentmods add commands/rchgrav/claudebox/tdd
Clone the repo
git clone --depth 1 https://github.com/RchGrav/claudebox

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/rchgrav/claudebox/tdd.svg)](https://agentmods.dev/commands/rchgrav/claudebox/tdd)
Your own site
<a href="https://agentmods.dev/commands/rchgrav/claudebox/tdd"><img src="https://agentmods.dev/badge/commands/rchgrav/claudebox/tdd.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 681 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00007 $0.00681
Opus 5 $0.00003 $0.00341
Sonnet 5 $0.00001 $0.00136
Haiku 4.5 $0.00001 $0.00068

Measured 5d ago against content hash 9032ac39f9f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tdd 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 5d 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.

commands/tdd.md · 76 lines

What it actually says

You are now in TDD mode. Follow strict Test-Driven Development discipline.

Task: $ARGUMENTS

ASSESSMENT: Determine your scenario first

  • Greenfield code: New code or well-tested existing code → Standard TDD cycle
  • Legacy code: Hard-to-test existing code → Characterization test → refactor → TDD

GREENFIELD TDD RULES - ENFORCE STRICTLY:

  1. ONE TEST CASE AT A TIME

    • Write exactly ONE failing test case
    • Implement minimal code to make it pass
    • Refactor if needed while keeping tests green
    • Commit the complete cycle together
  2. COMMIT REQUIREMENTS

    • Each commit: test + implementation + documentation updates
    • Commit message: "Add [specific behavior] with test"
    • Never commit failing tests
    • All related changes in same commit
  3. WORKFLOW ENFORCEMENT

    • Before any implementation: Ask "What is the ONE specific test case?"
    • Refuse bulk implementation requests
    • Force focus on current failing test only
    • Include documentation updates when code changes require them
  4. TDD CYCLE PHASES

    • RED: Write failing test, verify it fails for right reason
    • GREEN: Minimal implementation to pass test (no extra features)
    • REFACTOR: Improve design while keeping tests green

LEGACY CODE TDD RULES:

Assessment phase:

  • Identify why current code is hard to test (tight coupling, mixed concerns, dependencies, etc.)
  • Determine if refactoring would make it more testable
  • Plan the safest refactoring approach

Legacy TDD workflow:

  1. Characterization test first - Write test that captures current behavior as safety net
  2. Refactor for testability - Extract functions, inject dependencies, separate concerns
  3. Add targeted unit tests - Test the newly extracted/refactored components
  4. TDD for new behavior - Follow greenfield rules for new functionality

Commit sequence example:

  • "Add characterization test for user authentication flow"
  • "Extract password validation into separate function"
  • "Add unit test for password validation logic"
  • "Add password strength requirements with test"

Key principles:

  • Never refactor without a safety net (characterization test)
  • Make smallest possible changes to enable testing
  • Focus refactoring on the specific area you need to modify
  • Use Michael Feathers "Legacy Code Dilemma" techniques when needed

When to use this approach:

  • Modifying existing untested code
  • Code with hard-to-mock dependencies
  • Tightly coupled functions that mix multiple concerns
  • Legacy code that wasn't designed with testing in mind

BEHAVIORAL PROMPTS:

  • "Is this greenfield or legacy code?"
  • "What specific behavior are you testing?"
  • "Does this implementation do MORE than needed for the test?"
  • "Any design improvements before the next test case?"

Stay disciplined. Assess scenario first. One test case. Minimal implementation. Clean design.

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. 5d ago First seen · 76 lines · 7 tokens per session scan A 9032ac39f9f3

Subscribe to this mod's changes

tdd is a command published in the GitHub repository RchGrav/claudebox (1,144 stars, last pushed 1y ago), licensed MIT. It adds 7 tokens to every session and 681 once invoked, about $0.0000 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.