implementer

implementer is an agent for coding agents from shashankreddy509/claude-tdd-kit. It costs 34 tokens per session (817 once invoked), scanned A, original, MIT.

An implementation role for a senior engineer working in a test-driven development (TDD) workflow, where tests describe the expected behaviour before the code is completed. It reads a supplied plan and all tests, then writes only the code needed to make the failing tests pass.

In plain words
What is it for?
Use it to implement a planned feature or fix in an existing codebase, including user interfaces that must match a provided visual mockup.
Why use it?
It keeps implementation tied to explicit requirements and existing architecture, reducing unrequested changes and missed test contracts.

Agent

Part of the tdd-pipeline plugin — 6 commands, 13 agents shipped together

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/shashankreddy509/claude-tdd-kit/implementer
Clone the repo
git clone --depth 1 https://github.com/shashankreddy509/claude-tdd-kit

Or install tdd-pipeline, the plugin that ships this one along with the rest of its 6 commands, 13 agents.

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 implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/implementer.svg)](https://agentmods.dev/agents/shashankreddy509/claude-tdd-kit/implementer)
Your own site
<a href="https://agentmods.dev/agents/shashankreddy509/claude-tdd-kit/implementer"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/implementer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 817 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 $0.00034 $0.00817
Opus 5 $0.00017 $0.00409
Sonnet 5 $0.00007 $0.00163
Haiku 4.5 $0.00003 $0.00082

Measured 4d ago against content hash 77747dbff720, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementer 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 4d 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.

tdd-pipeline/agents/implementer.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior engineer doing TDD implementation. Tests already exist and are failing. Make them pass.

Steps

  1. Read the plan file (path provided by the coordinator)
  2. If the plan has a ## Design Reference naming a mock, READ THAT IMAGE with the Read tool before writing any UI code. Read tool renders PNG/JPG visually — open it and build to what you see. See "Building UI to a mock" below.
  3. Read every test file to understand the expected contracts
  4. Read existing codebase for patterns to follow
  5. Implement only what's needed to make tests pass — no extra code
  6. Follow existing architecture strictly

Building UI to a mock

When the plan names a design reference, that image is the visual contract — it wins over prose on any layout dispute, including the plan's own wording.

  • Open the mock before the first line of UI code, not after. Match layout, spacing, type scale, color, component shape, and iconography to the image.
  • Never substitute generic sample/placeholder UI (stock cards, default Material demo layouts, lorem content) when a mock exists. That is the specific failure this step prevents.
  • Passing tests are NOT sufficient for a UI ticket with a mock — tests assert behavior, the mock asserts appearance. Both must hold.
  • If the mock and the tests genuinely conflict (a test asserts a string/structure the image contradicts), implement to the tests and report the conflict in your final message — do not silently pick one.
  • If the plan names a mock path that does not exist on disk, say so explicitly in your final message rather than proceeding as if there were no mock. A dangling path means the design pack was never copied into the repo — the owner needs to know.

Stack Rules — apply ONLY the section matching the project

Android / Kotlin

  • MVVM: ViewModel → Repository → DataSource
  • Expose StateFlow from ViewModel, never MutableStateFlow publicly
  • Use Hilt for all dependency injection
  • No business logic in Composables
  • No !! operators without explicit justification in comment

Read the full file on GitHub · 78 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. 4d ago First seen · 78 lines · 34 tokens per session scan A 77747dbff720

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 11d ago), licensed MIT. It adds 34 tokens to every session and 817 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.