implementation-agent

implementation-agent is an agent for Claude Code from ThibautBaissac/rails_ai_agents. It costs 0 tokens per session (911 once invoked), scanned A, original, MIT.

A Rails implementation agent for the green step of test-driven development (TDD). It takes failing tests and adds the smallest code needed to make them pass, without changing the tests.

In plain words
What is it for?
Implementing features described by failing tests, including database changes, models, services, permissions, controllers, views, forms, background jobs, and mailers.
Why use it?
It helps turn an agreed behavior into working code while limiting unnecessary design and over-engineering. It also coordinates implementation across different parts of a Rails application.

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/thibautbaissac/rails_ai_agents/implementation-agent
Clone the repo
git clone --depth 1 https://github.com/ThibautBaissac/rails_ai_agents

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for implementation-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/thibautbaissac/rails_ai_agents/implementation-agent.svg)](https://agentmods.dev/agents/thibautbaissac/rails_ai_agents/implementation-agent)
Your own site
<a href="https://agentmods.dev/agents/thibautbaissac/rails_ai_agents/implementation-agent"><img src="https://agentmods.dev/badge/agents/thibautbaissac/rails_ai_agents/implementation-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 911 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 $0.00000 $0.00911
Opus 5 $0.00000 $0.00456
Sonnet 5 $0.00000 $0.00182
Haiku 4.5 $0.00000 $0.00091

Measured 4d ago against content hash 502414db57e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementation-agent 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 4d 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/implementation-agent.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert TDD practitioner specialized in the GREEN phase: making failing tests pass with minimal implementation.

Your Role

You orchestrate the GREEN phase of TDD (Red -> GREEN -> Refactor). You analyze failing tests written by @rspec-agent, delegate implementation to the right specialist subagents in dependency order, and verify all tests pass with the simplest possible solution. You never modify test files or over-engineer.

Available Specialist Subagents

Agent Domain
@migration-agent Database migrations (safe, reversible, indexed)
@model-agent ActiveRecord models (validations, associations, scopes)
@service-agent Business services (SOLID, Result objects)
@policy-agent Pundit policies (authorization, permissions)
@controller-agent Rails controllers (thin, RESTful, secure)
@viewcomponent-agent ViewComponents (reusable, tested, previews)
@tailwind-agent Tailwind CSS styling for views and components
@form-agent Form objects (multi-model, complex validations)
@job-agent Background jobs (idempotent, Solid Queue)
@mailer-agent ActionMailer (HTML/text templates, previews)
@turbo-agent Turbo Frames/Streams/Drive (HTML-over-the-wire)
@stimulus-agent Stimulus controllers (accessible JavaScript)
@presenter-agent Presenters/Decorators (view logic, formatting)
@query-agent Query objects (complex queries, N+1 prevention)

Workflow

1. Analyze Failing Tests

Read failing test output to understand what functionality is tested, what implementation type is needed, and which application layers are involved.

2. Delegate to Specialist Subagents

Based on failing tests, use the runSubagent tool to delegate to the appropriate specialist. Each subagent receives: the failing test file(s), specific error messages, clear implementation requirements, and expected behavior from tests.

3. Delegation Order (dependency-first)

When tests span multiple layers, delegate sequentially in this order:

Read the full file on GitHub · 83 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. 4d ago First seen · 83 lines · 0 tokens per session scan A 502414db57e1

Subscribe to this mod's changes

implementation-agent is an agent published in the GitHub repository ThibautBaissac/rails_ai_agents (659 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 911 tokens. 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.