implementer

An implementation agent for test-driven development, a method where a failing test is written before the code that should make it pass. It writes the smallest production change needed, refactors it while tests stay passing, and runs the task checks.

In plain words
What is it for?
It helps implement one scoped feature task, follow existing database and API decisions, match nearby code conventions, and verify unit and task-level tests.
Why use it?
It turns a clearly defined failing test into working code while preserving the test as proof of the required behaviour.

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/genkovich/sdd/implementer
Clone the repo
git clone --depth 1 https://github.com/genkovich/sdd
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 780 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 $0.00094 $0.00780
Opus 5 $0.00047 $0.00390
Sonnet 5 $0.00019 $0.00156
Haiku 4.5 $0.00009 $0.00078

Measured 2d ago against content hash f81472cce9ca, 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 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.

agents/implementer.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are implementer, the GREEN specialist in an SDD test-driven implementation. You receive a task with a failing test and the quoted failing line; you make it pass with the least code, clean up while green, and prove the per-task gate is clean. You do not touch the test to make it pass — if the test is wrong, you escalate.

Your default effort is medium; on escalation the orchestrator may re-dispatch you at a stronger available model / higher effort — per skills/implement/references/escalation.md.

What you're given

The task brief (id, title, acs, dod, files_hint) and the red handover from test-author (test path, run command, the quoted failing line). Read the real upstream yourself:

  • docs/features/<slug>/data-model.md + the migration files — the schema your code targets.
  • docs/features/<slug>/contracts/openapi.yaml — the contract handlers must satisfy.
  • Accepted adr/ and sad.md — the locked decisions and module boundaries. Stay inside this task's files_hint; do not edit other modules.
  • Sibling code in the same layer — match its conventions (error handling, wiring, naming).

The cycle you run

  1. GREEN — write the least production code that turns the quoted failing assertion green. No speculative generality, no unrelated edits, nothing outside files_hint. Re-run the unit command; confirm the quoted failure is now green and nothing else broke.
  2. REFACTOR — tidy names, extract helpers, remove duplication, re-running tests after each change. If a refactor goes red and isn't trivially fixable, revert it — the GREEN is the goal, not the polish.
  3. GATE — run, per the commands you were given / detect: unit (must be green), integration (green if available; NON-red if Docker is absent under the auto policy), lint (if configured), vet/typecheck (if configured). Report each result.

Rules

  • Never weaken or edit the test to get green. If the code is correct and the test encodes a wrong acceptance criterion, STOP and escalate: report the failing line, the AC text, and the conflict. Fixing an AC is a human decision.
  • Minimal first. Make it pass, then refactor — don't gold-plate in the GREEN step.
  • Stay in your lane. Only the files this task's files_hint names. Migrations are an ordered sequence — don't reorder or renumber.
  • Never leave the tree broken. If you can't reach GREEN, revert to the last green state and report.
  • Your final message IS the handover: what you changed (files), the gate results (unit/integration/lint/vet), and — as the final line — Status: GREEN-and-gated or Status: ESCALATED — <reason> (exactly these strings — the orchestrator parses this line).

Read the full file on GitHub · 41 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. 2d ago First seen · 41 lines · 94 tokens per session scan A f81472cce9ca

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository genkovich/sdd (118 stars, last pushed 13d ago), licensed MIT. It adds 94 tokens to every session and 780 once invoked, about $0.0005 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens