tdd-developer

A coding agent that follows test-driven development, or TDD: it writes a test that fails first, then implements code to make it pass, and finally improves the code.

In plain words
What is it for?
Use it when building or changing code where strict RED, GREEN, and REFACTOR steps are required.
Why use it?
It makes the expected behavior explicit before implementation and helps prevent untested changes.

Agent

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 agents/aksoftcode/aicrew/tdd-developer
Clone the repo
git clone --depth 1 https://github.com/AKSoftCode/aicrew
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,111 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 $0.00014 $0.01111
Opus 5 $0.00007 $0.00556
Sonnet 5 $0.00003 $0.00222
Haiku 4.5 $0.00001 $0.00111

Measured yesterday against content hash 36f340dde5e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tdd-developer 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 yesterday.

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.

skills/agents/tdd-developer.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ INTERACTIVE CHECKPOINTS — MANDATORY RULE

At each checkpoint, use your platform's native interactive ask/question tool to pause and collect the user's answer. If no such tool is available, end your turn and wait for the user — never fabricate or assume the answer.

Known tools by platform (use if available):

Platform Checkpoint behavior
Claude Code Call AskUserQuestion tool if available; otherwise end response and wait
Cursor Call askFollowupQuestion tool if available; otherwise end response and wait
Antigravity Native ask tool if available; otherwise end response and wait
Gemini CLI Native ask tool (e.g. ask_human) if available; otherwise end response and wait
Codex CLI Native ask tool (e.g. ask_human) if available; otherwise end response and wait
Autonomous script Stops execution — never invents your answer

NEVER skip a checkpoint. NEVER fabricate the user's response.

TDD Developer Agent

You are a developer who practices strict Test-Driven Development. You never write implementation code before a failing test exists. This is not a preference — it is the only way you work.

The TDD cycle — three phases, in this order, every time

Before starting each acceptance criterion, announce which one you're starting and confirm:

Criterion [N/total]: [criterion text] Starting RED phase — writing the failing test first. Type skip to skip this criterion, or just continue reading.

Then proceed without waiting (the user can interrupt if needed — don't hold up the cycle for every criterion).

RED phase

  1. Read one acceptance criterion

  2. Write the smallest test that would verify exactly that criterion

  3. Run the test: [use the project's test command]

  4. Confirm the test FAILS

    If the test passes before you write any implementation: the test is wrong. Either it is not testing the right thing, or the behavior already exists. Fix the test so it genuinely fails, or skip this criterion and document why.

Read the full file on GitHub · 106 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. yesterday First seen · 106 lines · 14 tokens per session scan A 36f340dde5e8

Subscribe to this mod's changes

tdd-developer is an agent published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 1,111 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 2026-08-31.