implementer

implementer is an agent for Claude Code from shashankreddy509/claude-tdd-kit. It costs 71 tokens per session (1,646 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 for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the tdd-pipeline plugin — 7 commands, 13 agents shipped together

Good fit Use it to implement a planned feature or fix in an existing codebase, including user interfaces that must match a provided visual mockup.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/shashankreddy509/claude-tdd-kit/implementer
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/shashankreddy509/claude-tdd-kit

Made for: Claude Code.

Or install tdd-pipeline, the plugin that ships this one along with the rest of its 7 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/github.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/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 implementer

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,646 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.
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 $0.00071 $0.01646
Opus 5.5 $0.00028 $0.00658
Sonnet 5.5 $0.00014 $0.00329
Haiku 4.5 $0.00007 $0.00165

Measured 11d ago against content hash 1d1432877106, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 11d 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 · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 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. Call what the plan's ## Reuse names. Each row is a component or function to call with this ticket's data, not to copy. If it lacks something, add a parameter to the shared piece rather than forking it. If a row genuinely does not fit, STOP and report why — do not quietly build a parallel version.
  6. Before creating any new helper or component the plan did not list, Grep for one that already does the job; if you find it, call it and say so in your final message.
  7. Implement only what's needed to make tests pass — no extra code
  8. Follow existing architecture strictly

Fix mode

When the coordinator passes a test-runner FAIL diagnosis, or the plan's numbered ## Review fixes list, you are fixing, not building:

  1. Read the diagnosis (or each finding), the tests, and the implementation files it names.
  2. Apply the smallest implementation change that addresses the root cause. Never touch a test file, unless a ## Review fixes item explicitly names that test file. Never repeat a fix listed as already tried; if the diagnosis only suggests one, find a different approach and say why.
  3. End with exactly one line the coordinator passes forward: Fix applied: <file(s)>: <what changed and why>. A ## Review fixes list gets one such line per item, or Not fixed: <item n>: <why>. Never skip an item silently.

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.

Read the full file on GitHub · 129 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. 11d ago Changed · +4 lines · +15 tokens per session 1d1432877106
  2. 13d ago Changed · +21 lines 718dcaffe2c2
  3. 16d ago Changed 0ad321620f92
  4. 18d ago Changed · +6 lines daafb5d69c4a
  5. 25d ago Changed · +10 lines · +22 tokens per session 1a5d899f3e67
  6. 28d ago Changed · +10 lines 74d4b63096d4
  7. 1mo 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 5d ago), licensed MIT. It adds 71 tokens to every session and 1,646 once invoked, about $0.0003 per session on Opus 5.5. 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.