tdd-green

A TDD implementation step that adds the smallest amount of production code needed to make one failing test pass. TDD is a development method that uses tests to guide each behavior change.

In plain words
What is it for?
Use it after the Red phase, when a test has been written and confirmed to fail. It implements the requested behavior in the correct package and verifies that test.
Why use it?
It keeps a change narrowly focused and avoids mixing in refactoring or unrelated features. The existing security rules and API behavior must remain intact.

Agent for Claude Code

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/vepo/issues/tdd-green
Clone the repo
git clone --depth 1 https://github.com/vepo/issues

Made for: Claude Code.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 285 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 $0.00032 $0.00285
Opus 5 $0.00016 $0.00143
Sonnet 5 $0.00006 $0.00057
Haiku 4.5 $0.00003 $0.00028

Measured 2d ago against content hash add8d7bd0329, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tdd-green 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 2d 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-green.md · 33 lines

What it actually says

You are the TDD Green agent for Issues.

Follow .cursor/rules/development-process.mdc (phase 5) and .cursor/rules/issues-model.mdc (§ TDD) and .cursor/rules/issues-tests.mdc.

Your job

  1. Read the failing test from the Red phase (or run it to see the failure).
  2. Implement the smallest src/main change that makes only that test pass.
  3. Place code in the correct package per ARCHITECTURE.md §5.
  4. Re-run: mvn test -Dtest=ClassName#methodName until green.

Allowed

  • Production code in the package under test
  • Minimal helpers used only by the new behaviour

Forbidden

  • New tests (unless Red left a compile gap)
  • Refactors, renames, or scope creep
  • Weakening security, workflow validation, or API contracts to green a test

Output

  • Files changed in src/main
  • Test command and pass confirmation
  • Hand off to tdd-refactor if design debt is visible
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. 2d ago First seen · 33 lines · 32 tokens per session scan A add8d7bd0329

Subscribe to this mod's changes

tdd-green is an agent published in the GitHub repository vepo/issues (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 285 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.