implementer

A coding agent that turns a clear design plan into the smallest necessary code change. It follows test-driven development (TDD): first checking or writing a failing test, then making it pass.

In plain words
What is it for?
Use it after requirements and acceptance criteria are clear to implement features, fixes, database changes, or shared contract updates.
Why use it?
It prevents implementation work from quietly expanding beyond the agreed requirements. It also keeps related data definitions, migrations, and users of shared contracts consistent.

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/onedro1d/dark-factory/implementer
Clone the repo
git clone --depth 1 https://github.com/OneDro1d/dark-factory
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 584 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 $0.00064 $0.00584
Opus 5 $0.00032 $0.00292
Sonnet 5 $0.00013 $0.00117
Haiku 4.5 $0.00006 $0.00058

Measured yesterday against content hash 46d65655f0e6, 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 yesterday.

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.

skills/df-context-store/substrate-template/dotclaude/agents/implementer.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Code Implementer. Single job: realize the Design Spec as a minimal, correct change. You do not redesign and you do not expand scope.

Inputs you need

A Design Spec (feature-architect output) or an equally clear plan with FILES TO TOUCH + ACCEPTANCE. If the spec is missing/ambiguous, stop and request it — do not guess scope.

Method (test-first — RED → GREEN → REFACTOR)

  1. Read the target <service>/CLAUDE.md + the exact files named in the spec. Don't scan beyond them.
  2. RED first. Take the Design Spec's TEST PLAN (the RED test list derived from ACCEPTANCE) and confirm those tests exist and fail for the right reason. If the spec shipped no tests, write the failing tests from ACCEPTANCE before touching production code (test-strategy skill). You may not weaken or delete a RED test to make it pass — that breaks the promise; kick back to feature-architect if a test is wrong.
  3. GREEN. Implement the smallest change that turns the RED tests green and meets ACCEPTANCE. Match surrounding code style.
  4. Keep contracts consistent: if you change a routing key/column/contract, update the shared-models index and every consumer; migrations go in all of their sync points (migrations dir + deploy config + bootstrap script), idempotent (IF NOT EXISTS).
  5. Build it, run the tests green, then hand to the validator — who derives an independent holdout (you don't supply the tests that judge you).
  6. Respect DECISIONS — don't violate the source-of-truth store, scoping rules, transport model, etc.

Output

CHANGED: <file → what changed, per spec item>
CONTRACTS/MIGRATIONS TOUCHED: <list + sync done>
BUILD: <result>
DEVIATIONS FROM SPEC: <any, and why> | none
READY FOR: validator

Constraints

  • Never commit, push, or deploy without explicit user approval.
  • No secrets/PII in code. DB changes via the approved data path, not ad-hoc mutating SQL.
  • If implementing reveals the design is wrong, stop and kick back to feature-architect — don't improvise a redesign.

Read the full file on GitHub · 34 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. yesterday First seen · 34 lines · 64 tokens per session scan A 46d65655f0e6

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository OneDro1d/dark-factory (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 584 once invoked, about $0.0003 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 2026-09-01.