TheRealSeanDonahoe

Ijfw — DevOps skill for Claude Code

DevOps community

IJFW — It Just Fcking Works.

How to install Ijfw

This entry records only its repository, not the path inside it, so there is no exact command to give. Open TheRealSeanDonahoe/ijfw and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Ijfw does

IJFW — It Just F*cking Works. Ferrox Labs' local-first infrastructure for AI coding agents: shared memory, smart routing, multi-AI cross-audits, disciplined workflow.

Alternatives in DevOps

  • Context Infrastructure — A context and memory system for AI coding agents 774 ★
  • Video Podcast Maker — AI-powered video podcast creation skill for coding agents 529 ★
  • Xora — Learn how to build and deploy a SaaS landing page with modern UI and mobile-first principles while strengtheni 449 ★

README

Ferrox Labs' IJFW (It Just F*cking Works): local-first infrastructure for AI coding agents, shown as eight engines: shared memory (cross-session recall), workflow discipline (plan, gate, execute), cross-audit (multi-model review), specialist bench (skills on demand), token savings (smarter routing), observability (local dashboard), learns you (adapts from edits), and design contract (one design system). Runs under Claude Code, Codex, Gemini, Cursor, Windsurf, Copilot, OpenCode, Qwen, Kimi, OpenClaw, Aider, and more.

CI npm version license MIT

Your AI tools are brilliant, forgetful, undisciplined, and alone. One install fixes all four.

**IJFW is one shared brain, and a full operating layer, for every AI coding tool you use.** Install it once and your tools remember across sessions, plan before they build, check each other's work for hallucinations, pull in the right specialist for the job, and quietly cut your token bill. All on your machine. All yours.

npm install -g @ijfw/install && ijfw-install

Cross-tool memory demo. Monday, in Claude Code: 'we use Zod for validation, never Yup; API errors return { error, code }', and IJFW stores it locally. Wednesday, in Cursor, a different tool: 'add validation to the signup route', and Cursor writes a Zod schema returning { error, code }, recalled from IJFW memory, local. You told one tool; every tool remembered; nothing left your machine.</div> </section> </div> <section class=

Related Skills

Kherep — DevOps skill for Claude Code

Kherep

Orchestration layer for Claude Code and Codex: shared rules, hooks, skills and agents, model and tool routing,

DevOps community
Claytonia — DevOps skill for Claude Code

Claytonia

Claytonia — the Lentago Labs agent-fleet system, a.k.a. the bullpen: five self-hosted headless coding agents o

DevOps community
Rementum — DevOps skill for Claude Code

Rementum

Self-hosted shared memory infrastructure for AI agents with versioned knowledge and conflict-safe writes.

DevOps community
Lemurkit — DevOps skill for Claude Code

Lemurkit

AI Sovereignty - The team cognition for AI agents. The remote MCP connector on Cloudflare. KV is for Transacti

DevOps community
Claude Local Stack — DevOps skill for Claude Code

Claude Local Stack

Claude Code stack for Apple Silicon — local MLX + AWS Bedrock routing, token compression, plugin management

DevOps community
Setu — DevOps skill for Claude Code

Setu

A cross-platform Go CLI that streamlines local AI development workflows by bridging issue trackers (Jira / Azu

DevOps community

Related Agents

Inference Architect — DevOps & Infrastructure agent for Claude Code

Inference Architect

You are the system Inference Architect — a senior ML infrastructure engineer specializing in local LLM serving

DevOps & Infrastructure community
Gsc Page Experience — Security agent for Claude Code

Gsc Page Experience

Page-experience / security-posture analyst. Pulls Mozilla Observatory, SSL Labs, and a local header probe to g

Security community
Part 11: Auto-Capture Hook (Stop Manually Writing Memory) — Data & AI agent for Claude Code

Part 11: Auto-Capture Hook (Stop Manually Writing Memory)

By Terp - Terp AI Labs --- The vault system from Part 9 is powerful, but there's a gap: you have to manually w

Data & AI community