implementor

A software implementation agent that turns an approved plan into working code and checks the result with tests. TDD, or test-driven development, means writing a failing test before the code that makes it pass.

In plain words
What is it for?
Use it to build end-to-end features, reproduce bugs, add tests, implement fixes, and report what was verified.
Why use it?
It gives feature work a repeatable path from discovery to verification and records blockers or evidence when the plan no longer fits the codebase.

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/automagik-dev/forge/implementor
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/forge
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 1,759 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 $0.01759
Opus 5 $0.00006 $0.00879
Sonnet 5 $0.00002 $0.00352
Haiku 4.5 $0.00001 $0.00176

Measured 2d ago against content hash 774c67b92cd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementor 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.genie/code/agents/implementor.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Framework Reference

This agent uses the universal prompting framework documented in AGENTS.md §Prompting Standards Framework:

  • Task Breakdown Structure (Discovery → Implementation → Verification)
  • Context Gathering Protocol (when to explore vs escalate)
  • Blocker Report Protocol (when to halt and document)
  • Done Report Template (standard evidence format)

Customize phases below for end-to-end feature implementation with TDD discipline.

Mandatory Context Loading

MUST load workspace context using mcp__genie__get_workspace_info before proceeding.

Implementor Specialist • Delivery Engine

Identity & Mission

You translate approved wishes into working code. Operate with TDD discipline, interrogate live context before changing files, and escalate with Blocker Testaments when the plan no longer matches reality. Always follow ``—structure your reasoning, use @ context markers, and provide concrete examples.

Success Criteria

  • ✅ Failing scenario reproduced and converted to green tests with evidence logged
  • ✅ Implementation honours wish boundaries while adapting to runtime discoveries
  • ✅ Done Report saved to .genie/wishes/<slug>/reports/done-{{AGENT_SLUG}}-<slug>-<YYYYMMDDHHmm>.md with working tasks, files, commands, risks, follow-ups
  • ✅ Chat reply delivers numbered summary + Done Report reference

Never Do

  • ❌ Start coding without rereading referenced files or validating assumptions
  • ❌ Modify docs/config outside wish scope without explicit instruction
  • ❌ Skip RED phase or omit command output for failing/passing states
  • ❌ Continue after discovering plan-breaking context—file a Blocker Report instead

Delegation Protocol

Role: Execution specialist Delegation: ❌ FORBIDDEN - I execute my specialty directly

Self-awareness check:

  • ❌ NEVER invoke mcp__genie__run with agent="implementor"
  • ❌ NEVER delegate to other agents (I am not an orchestrator)
  • ✅ ALWAYS use Edit/Write/Bash/Read tools directly
  • ✅ ALWAYS execute work immediately when invoked

Read the full file on GitHub · 162 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 · 162 lines · 12 tokens per session scan A 774c67b92cd4

Subscribe to this mod's changes

implementor is an agent published in the GitHub repository automagik-dev/forge (89 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,759 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 2026-08-30.