OpenClacky is an open-source AI coding agent that uses OpenAI-compatible models to perform tasks through tools and subagents. It is intended for developers who want an agent with flexible model choice and lower token usage. The catalogue skills and agents extend its workflows and capabilities.
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 skills add clacky-ai/openclacky --skill newgit clone --depth 1 https://github.com/clacky-ai/openclackyWrote 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/skills/clacky-ai/openclacky/new)<a href="https://agentmods.dev/skills/clacky-ai/openclacky/new"><img src="https://agentmods.dev/badge/skills/clacky-ai/openclacky/new/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/clacky-ai/openclacky/new"><img src="https://agentmods.dev/badge/skills/clacky-ai/openclacky/new.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00010 | $0.01132 |
| Opus 5 | $0.00005 | $0.00566 |
| Sonnet 5 | $0.00002 | $0.00226 |
| Haiku 4.5 | $0.00001 | $0.00113 |
Grade A, and why
new 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 10d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create New Project
Usage
When user wants to create a new Rails project:
- "help me create a new Rails project"
- "I want to start a new Rails project"
- "/new"
Process Steps
0. Ask Project Type and Requirement
Before doing anything, call ask_user with a structured prompt. Use the following as a guide:
zh:
{
"question": "请选择项目类型,并用一句话描述你想做什么:",
"context": "开始新项目前需要知道项目类型和需求,请先完成填写。",
"options": ["⚡ Demo — 无数据库,AI 自由发挥,快速原型", "🏗️ Production — 真实应用,可部署,完整 Rails 配置"]
}
en:
{
"question": "Choose a project type and describe what you want to build in one sentence:",
"context": "Tell us what kind of project to create so we can get started.",
"options": ["⚡ Demo — no database, AI builds freely, quick prototype", "🏗️ Production — real app, ready to deploy, full Rails setup"]
}
Based on user's choice:
- If Demo: do NOT follow the Rails setup steps below. Instead, freely build a simple HTML/CSS/JS (or React) prototype directly in the working directory based on their requirement. Use your creativity.
- If Production: continue with steps 1–3 below (full Rails flow).
1. Check Directory Before Starting
Before running the setup script, check if current directory is empty:
- Use glob tool to check if directory has files:
glob("*", base_path: ".") - If directory is NOT empty, ask user for confirmation: "Current directory is not empty. Continue anyway? (y/n)"
- If user declines, abort and suggest creating project in an empty directory
2. Run Setup Script
Execute the create_rails_project.sh script (see Supporting Files below) in current directory.
Use the exact absolute path shown in the Supporting Files section:
<absolute path to create_rails_project.sh from Supporting Files>
The script will automatically:
Step 1: Clone Template
- Clone rails-template-7x-starter to a temporary directory
- Move all files to current directory
- Delete template's .git directory
- Initialize new git repository with initial commit
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 131 lines · 10 tokens per session scan A 0dcdbb5cfa82
new is a skill published in the GitHub repository clacky-ai/openclacky (1,187 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 1,132 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.
Other skills, from other repositories
rails-dev
Opinionated Rails conventions: rich models, concerns, CRUD-everything, state-as-records, minimal dependencies, Minitest with fixtures. Load this skill BEFORE any code-level thinking, not only before editing a file. It is required the moment a task touches Rails code in ANY way: designing or even just discussing a data…
laravel-engineering
Laravel implementation discipline for tracing context, reusing present contracts, keeping code simple, preserving failures, and verifying the changed critical path. Use when implementing, refactoring, debugging or reviewing Laravel code where callers, configuration, data flow or proof of correctness may be unclear.
webman
Expert skill for the webman framework (a long-lived, in-memory PHP framework based on workerman). Covers routing, controllers, middleware, database/Redis, custom processes, timers, coroutines (v2), plugin development, and guarding against memory leaks and cross-request state pollution under the resident process model.…
layered-rails
Write, refactor, and review Rails code using layered architecture principles from "Layered Design for Ruby on Rails Applications". Use when writing or refactoring Rails code — models, controllers, services, jobs, mailers, policies, forms, query objects, presenters, view components, state machines, serializers, or…
rails-api-controllers
RESTful API controller patterns for Ruby on Rails. Use when: (1) Building JSON APIs, (2) API versioning, (3) Error handling and status codes, (4) Authentication with tokens/JWT, (5) Rate limiting, (6) CORS configuration, (7) Pagination and filtering, (8) API documentation, (9) Testing API endpoints.
rails-mailers
Use when sending emails - ActionMailer with async delivery via SolidQueue, templates, previews, and testing.