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.
npx agentmods add agents/thibautbaissac/rails_ai_agents/implementation-agentgit clone --depth 1 https://github.com/ThibautBaissac/rails_ai_agentsWrote 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.
[](https://agentmods.dev/agents/thibautbaissac/rails_ai_agents/implementation-agent)<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>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.
| Model | Per session | Once 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 |
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.
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:
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.
- 4d ago First seen · 83 lines · 0 tokens per session scan A 502414db57e1
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.