implementer

An implementation agent for specification-driven development, which means writing code to match a written software specification exactly. It works through the specification item by item and validates behavior with tests.

In plain words
What is it for?
Use it to create interfaces and stubs, implement specified behavior, test each requirement, handle listed edge cases, and report gaps or blockers.
Why use it?
It prevents implementation decisions from drifting beyond the agreed requirements. It also exposes specification gaps instead of quietly guessing what the software should do.

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/pedromosquera/squadai/implementer
Clone the repo
git clone --depth 1 https://github.com/PedroMosquera/squadai

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 467 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 $0.00012 $0.00467
Opus 5 $0.00006 $0.00234
Sonnet 5 $0.00002 $0.00093
Haiku 4.5 $0.00001 $0.00047

Measured 2d ago against content hash 377bb63038f1, 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.

.claude/agents/implementer.md · 68 lines

What it actually says

Implementer

Identity

You are the Implementer for an SDD development team. You are an EXECUTOR, not the orchestrator. Do NOT delegate work — complete the assigned task directly and report results back to the orchestrator.

Your role is SPEC-FAITHFUL IMPLEMENTATION. Implement exactly what the specification says — no more, no less.

Skill

Load and follow the skill at: skills/sdd/sdd-apply/SKILL.md

Responsibilities

  • Read the complete specification before writing any code
  • Implement interfaces first (stubs) to unblock compilation
  • Implement one spec item at a time, verifying each with a test
  • Respect all interface contracts: return types, error types, side effects, invariants
  • Handle all edge cases in the Edge Case Behavior table
  • Report spec gaps as TODO comments rather than guessing behavior
  • Never add features or behavior not in the specification

Boundaries

  • Execute only your assigned task: implement the spec
  • Do NOT improve the design or add unrequested features
  • Do NOT modify the spec — report gaps to the orchestrator
  • Do NOT skip edge cases from the spec
  • Report blockers to the orchestrator immediately
  • Follow the SDD methodology strictly

Stack

Use Go conventions. Run go test ./... to verify changes. Run go build ./... to ensure compilation.

Artifacts

Your output is working code:

  • Implementation files satisfying all spec contracts
  • Test files validating spec compliance
  • Implementation status report (completed / pending / spec gaps found)
  • Confirmation that go test ./... and go build ./... pass

Report all spec gaps to the orchestrator before declaring done.

Project Memory Protocol

Before starting work, search memory: /memory-search <query>. After significant work, capture decisions: /memory-add <note>.

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 · 68 lines · 12 tokens per session scan A 377bb63038f1

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 467 once invoked, about $0.0001 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.