implementer

A coding skill for the GREEN phase of test-driven development, or TDD—the practice of writing a failing test before the code that should pass it.

In plain words
What is it for?
Use it to verify that tests fail, write the smallest production-quality implementation, rerun the tests, and stop when the tests are already passing or missing.
Why use it?
It keeps implementation focused on the behavior already described by failing tests and avoids unnecessary features or complexity.

Skill for Claude CodeCodex

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 skills/mountainunicorn/add/implementer
Any agent
npx skills add MountainUnicorn/add --skill implementer
Clone the repo
git clone --depth 1 https://github.com/MountainUnicorn/add

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,727 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 $0.00019 $0.02727
Opus 5 $0.00010 $0.01363
Sonnet 5 $0.00004 $0.00545
Haiku 4.5 $0.00002 $0.00273

Measured 2d ago against content hash acea0c239c1c, 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.

core/skills/implementer/SKILL.md · 379 lines

How it starts

The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADD Implementer Skill v{{VERSION}}

Write minimal production-quality code to make failing tests pass. This is the GREEN phase of TDD.

Overview

The Implementer takes failing tests (from test-writer) and writes the smallest amount of code necessary to make them all pass. The goal is:

  • Make tests green with minimal code
  • No over-engineering or premature optimization
  • Production-quality implementation (no shortcuts)
  • Defer non-essential features for future work
  • Maintain clean architecture and separation of concerns

Pre-Flight Checks

  1. Verify test files exist and fail
    • Read test file(s) from path provided by test-writer
    • Run tests to confirm they fail: npm test or python -m pytest
    • Capture baseline: count of failing tests
    • Halt if tests don't exist or already pass

1b. Read the impact hint (v0.9.0 — AC-022)

  • The tdd-cycle orchestrator emits a files-likely-affected block via core/lib/impact-hint.sh. Consume it as part of this skill's context:

    ## Files likely to need changes
      - app/auth.py
      - app/session.py
    
    ## Files to be careful around (recent anti-pattern learnings exist)
      - app/session.py  [L-042]
    
  • Use the first list as the starting set for Step 2 (Design Implementation)

  • Treat the second list as warnings: those paths have recent anti-pattern learnings — read the learning (by ID) before editing

  • If the hint reports "No source files implied by RED diff" (AC-024), fall back to the spec's acceptance criteria for implementation targets

  1. Read the feature spec

    • Load spec file from argument
    • Extract feature name, acceptance criteria, requirements
    • Understand the "what" before implementing
  2. Load test mapping

    • Read tests/{feature}-mapping.md (created by test-writer)
    • Understand which tests map to which ACs
    • Ensures implementation covers all required ACs

Read the full file on GitHub · 379 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 · 379 lines · 19 tokens per session scan A acea0c239c1c

Subscribe to this mod's changes

implementer is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 2,727 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.