Moorai — AI skill for Claude Code
On-device guardrails for AI coding agents.
How to install Moorai
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open gitayg/moorai and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Moorai does
On-device guardrails for AI coding agents. Hooks check prompts, file reads, shell commands, writes, web fetches and MCP calls before they run and scan tool output after. Validated end to end on Claude Code; Codex CLI, Copilot CLI, Cursor and Gemini CLI adapters tested on fixtures. Stdio MCP proxy for hosts without hooks. MIT.
Alternatives in AI
- Wp Acf — Fast WordPress ACF/content-model scan - checks CPT vs taxonomy vs field choices, field-group hygiene, repeater 76 ★
- Browser39 — A headless browser for AI agents that fetches modern web pages, runs JavaScript, manages sessions, and returns 52 ★
- Opencues — Turn any text field into a two-way LLM channel: it reads what you write and fills what you ask 43 ★
README
MoorAI
On-device guardrails for AI coding agents. Your prompts and files stay on the machine.
[](LICENSE) [](#install) [](https://github.com/gitayg/moorai/actions)
**MoorAI reviews what your developers send to AI coding agents — and what those agents read, run, and reply — right on the device, before anything is exposed.** Secrets, PII, and source code never leave the machine to be checked. Your security team sees content-free signals, never the prompts.
Let your engineers use AI freely. Keep your data in-house.
The problem
Your developers use Claude Code, Cursor, and Copilot. Those agents don't just read what's typed — they **read files into context** (a stray `.env`), **call MCP tools** with whatever arguments they were given, and **reply** with whatever the model generates. Prompt review alone misses most of it, and every cloud DLP tool solves it by **sending your prompts to their servers to inspect**.
That's the exact trade MoorAI refuses.
What it does
- Context interception — stops a secret or PII being read into the agent's context (e.g. an agent slurping a
.env), not just typed in a prompt. Via the agent's PreToolUse hooks, on-device. An enrolled device enforces the policy (block, or hold for sign-off); a device that isn't enrolled coaches: the agent is told what it touched and the read goes ahead. What comes back into the agent — command output, MCP results, sub-agent reports, fetched pages — is scanned after the tool runs as untrusted inbound content. - Agency Enforcement — bounds what an agent is allowed to do: inspects
mcp__*tool-call arguments for secrets/policy violations and blocks them, and enforces an approved-MCP-serve
Related Skills
Guard Layer
Runtime guardrails between an AI agent and its tools: scan what it reads, gate what it does, and track the ses
Dsh Plugin Hooks
DeepSeek Harness plugin: Claude-Code-style lifecycle hooks for DSH. Configure shell commands that run automati
Agentlint
Local guardrails for AI coding agents. Check proposed file changes and shell commands, block risky patterns, a
Claude Mod Trail
A side pane of every file Claude reads or changes this session, in any folder or drive, lit up live (reads pur
Post Task Retro
USE WHEN any task or sweep is complete. Writes a structured self-reflection (Reflexion Q1–Q6 + AI-automation a
Aparte
Private AI chat that runs entirely in your browser: your own keys or on-device models (WebLLM, Ollama), MCP to
Related Agents
Agent Specialist
Design, build, and optimize AI agents with strong output contracts, guardrails, and behavioral consistency. Us
SEO Matomo
Matomo Reporting API analyst. Fetches organic traffic, top landing pages, device / country breakdowns, and ref
Core Worker
Builds ONE measured demand cluster family for a semantic core — expands seeds through the demand APIs, phrases