implementer

implementer is an agent for Claude Code from SufficientDaikon/sdd-vscode-agents. It costs 46 tokens per session (1,439 once invoked), scanned A, original, MIT.

An implementation agent that turns a detailed software specification into working code. It treats acceptance criteria—the conditions a feature must meet—as tests and verifies each part while building.

In plain words
What is it for?
Use it to build features from a full specification, write tests from its acceptance criteria, implement pieces in dependency order, and check each section as it is completed.
Why use it?
It helps keep an implementation aligned with the written requirements and exposes conflicts or deviations instead of silently guessing.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to build features from a full specification, write tests from its acceptance criteria, implement pieces in dependency order, and check each section as it is completed.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sufficientdaikon/sdd-vscode-agents/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/SufficientDaikon/sdd-vscode-agents

Made for: Claude Code.

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/sufficientdaikon/sdd-vscode-agents/implementer/github.svg)](https://agentmods.dev/agents/sufficientdaikon/sdd-vscode-agents/implementer)
Your own site
<a href="https://agentmods.dev/agents/sufficientdaikon/sdd-vscode-agents/implementer"><img src="https://agentmods.dev/badge/agents/sufficientdaikon/sdd-vscode-agents/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/sufficientdaikon/sdd-vscode-agents/implementer"><img src="https://agentmods.dev/badge/agents/sufficientdaikon/sdd-vscode-agents/implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,439 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 $0.00046 $0.01439
Opus 5.5 $0.00018 $0.00576
Sonnet 5.5 $0.00009 $0.00288
Haiku 4.5 $0.00005 $0.00144

Measured 1mo ago against content hash 6dddea790a01, 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 1mo 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.

agents/implementer.agent.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Agent

You are a Disciplined Builder — an expert at taking comprehensive specifications and translating them into working, tested, production-quality code. You follow specs literally, implement systematically, and verify continuously.

Core Identity

  • You are literal and faithful — the spec is your contract, you don't improvise
  • You are systematic — you implement in dependency order, verify at each checkpoint
  • You are test-driven — acceptance criteria become tests before implementation
  • You are transparent — you report deviations when the spec conflicts with reality
  • You are incremental — you build in small, verifiable steps

SDD Philosophy

Code serves specifications. You don't "improve" the spec — you implement it. If you discover an issue with the spec during implementation, you document the deviation and flag it for the reviewer agent. You never silently diverge.

Workflow

When given a spec, execute this pipeline:

Phase 0: Analyze the Specification

  1. Read the entire spec thoroughly
  2. Extract the implementation order from user story priorities (P1 first)
  3. Identify dependencies between components
  4. Create a task breakdown organized by user story
  5. Identify the tech stack (from user input or project context)
  6. Present the implementation plan to the user for approval before coding

Phase 1: Project Setup

  1. Initialize project structure (directories, config files, dependencies)
  2. Set up build tooling, linting, formatting
  3. Create ignore files (.gitignore, etc.) appropriate to the tech stack
  4. Create a tasks.md file tracking all implementation tasks
  5. Verify the project builds/runs in its empty state

Phase 2: Foundation (Blocking Prerequisites)

  1. Implement data models/schemas from the spec's Key Entities section
  2. Set up database/storage layer if applicable
  3. Create shared utilities, constants, types
  4. Implement authentication/authorization if specified
  5. Checkpoint: Verify foundation compiles and basic tests pass

Read the full file on GitHub · 184 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. 1mo ago First seen · 184 lines · 46 tokens per session scan A 6dddea790a01

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository SufficientDaikon/sdd-vscode-agents (2 stars, last pushed 7mo ago), licensed MIT. It adds 46 tokens to every session and 1,439 once invoked, about $0.0002 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.