BAGOMBEKA-JOB-DEV

Shiin — AI skill for Claude Code

AI community

Shiin is an agent-agnostic authorization layer for AI agent actions.

How to install Shiin

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

What Shiin does

Shiin is an agent-agnostic authorization layer for AI agent actions. It sits between AI agents (Claude Code, Codex CLI, Cursor, MCP clients, and custom agents) and the things they act on: files, commands, networks, and services. For every action an agent proposes, Shiin decides whether to allow it, deny it, or hold it for a human to approve.

Alternatives in AI

Cursor Talk To Figma MCP — TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c 7k ★
Firecrawl MCP Server — 🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM c 6.1k ★
Browserwing — BrowserWing turns your browser actions into MCP commands Or Claude Skill, allowing AI agents to control browse 1.2k ★

README

Shiin

Shiin is an agent-agnostic authorization layer for AI agent actions. It is designed to sit between AI agents (Claude Code, Codex CLI, Cursor, MCP clients, and custom agents) and the files, commands, networks, and services they act on. For every action an agent proposes, Shiin decides with explicit, deterministic policy whether to `allow` it, `deny` it, or hold it as `pending` until a human approves it, and it records tamper-evident evidence of that decision. One policy applies to every agent, and no decision ever depends on the output of a language model.

[!IMPORTANT] **Pre-alpha: specification phase.** Shiin has no product code and no releases, so there is nothing to install or run yet. This repository contains the design: documentation, specifications, architecture decision records, and a small Rust tool that checks the documentation. Everything this README says about Shiin's behavior describes the intended design.

The problem in 30 seconds

AI coding agents act with the authority of the person who runs them. An agent that can edit files can also delete them, an agent that can run tests can run any command, and an agent that can fetch documentation can send data to any host the machine can reach. Agents make mistakes, they can be manipulated by instructions hidden in the text they read, and they usually have far more access than the task needs. OWASP lists that last risk as [LLM06:2025 Excessive Agency](https://genai.owasp.org/llmrisk/llm062025-excessive-agency/).

Each agent host ships its own controls, but those controls are configured separately for every agent, do not know the task, leave little evidence, and rarely say how strong their protection is.

Consider the instruction "Fix the login bug. Do not change the database schema." The agent is allowed to run database commands, so when it decides to add a column, every existing control sees an authorized action. Only a control that knows the task can see that the action contradicts the