tomascupr

Operant — Security skill for Claude Code

Security community

Self-hosted agents in Slack and Teams on your infra.

How to install Operant

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

What Operant does

Self-hosted agents in Slack and Teams on your infra. Per-user OAuth, per-human audit, RBAC, approvals, 2,500+ SaaS tools via Pipedream Connect. MIT-licensed control plane for OpenClaw.

Alternatives in Security

  • MCP Security Checklist (SlowMist) — Comprehensive checklist: input validation, rate limiting, RBAC, credential management, container hardening 819 ★
  • ThinkWatch — Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII 817 ★
  • Pocketpaw — Your AI agent in 30 seconds 775 ★

README

Operant

[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE) [![Release](https://img.shields.io/github/v/tag/tomascupr/operant?label=release&sort=semver&color=success)](https://github.com/tomascupr/operant/releases) [![verify](https://github.com/tomascupr/operant/actions/workflows/verify.yml/badge.svg)](https://github.com/tomascupr/operant/actions/workflows/verify.yml) [![Node 24](https://img.shields.io/badge/node-24%2B-brightgreen)](package.json) [![Stars](https://img.shields.io/github/stars/tomascupr/operant?style=flat&color=yellow)](https://github.com/tomascupr/operant/stargazers) [![PRs welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)

**The MIT-licensed, self-hosted control plane for AI agents in Slack and Microsoft Teams: every action runs as the human who asked, not a shared bot, with per-user OAuth to 3,000+ tools.**

Hosted agents — now including Anthropic's [Claude Tag](https://www.anthropic.com/news/introducing-claude-tag) — put one shared Claude in your channels that acts for everyone. Every employee's actions land in the audit log under "the workspace did it." Operant doesn't. Each person finds the app they need, connects their own Gmail, Notion, GitHub, Linear, HubSpot, or other Pipedream account, and asks the agent to work right where they already are, in Slack or Microsoft Teams. The agent calls tools under that human's own connection, and every session, policy decision, and tool call names the person who triggered it.

![Operant dashboard: Setup tab at first load](docs/assets/dashboard.png)

Quickstart

**One command** — pulls the official images, generates fresh secrets, and boots the whole stack (Postgres + control plane + OpenClaw gateway):

curl -fsSL https://raw.githubusercontent.com/tomascupr/operant/v0.6.0/install.sh | bash

It writes a self-contained `operant/` directory and prints your dashboard URL and admin login token when it finishes. Requires only Docker wit

Related Skills

Wardendeck — Security skill for Claude Code

Wardendeck

Self-hosted IM ↔ local AI coding agent control plane with approvals, audit and isolation (Feishu/Lark + Claude

Security community
Agentic AI Security Starter Kit — Security skill for Claude Code

Agentic AI Security Starter Kit

Working code examples to defend against Agentic AI threats: prompt injection detection, Claude Code hooks, OPA

Security community
OpenTag — Security skill for Claude Code

OpenTag

Open-source, channel-native agent gateway for Slack. Route team threads to Claude Code, Codex, OpenCode, Docke

Security community
Auth Review Local — Security skill for Claude Code

Auth Review Local

Deep-dive auth security review using a local LM Studio model. OAuth, JWT, sessions, CSRF, MFA, RBAC, multi-ten

Security community
Auth Review — Security skill for Claude Code

Auth Review

Deep-dive authentication and authorization security review: OAuth/OIDC, JWT, sessions, CSRF, MFA, RBAC, privil

Security community
Preloop — Security skill for Claude Code

Preloop

The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime obs

Security community

Related Agents

ZeroClaw Android — Data & AI agent for Claude Code

ZeroClaw Android

Run AI agents 24/7 on your Android phone. Native Rust core, 25+ providers (OpenAI, Claude, Gemini, Groq, DeepS

Data & AI community
Infra Mesh — Development agent for Claude Code

Infra Mesh

Mesh network specialist. Peer enrollment, groups, routes, policies, setup keys, and management-plane diagnosti

Development community
Appsec Auth Reviewer — Security agent for Claude Code

Appsec Auth Reviewer

Use proactively for deep-dive authentication and authorization security reviews: OAuth 2.0/OIDC implementation

Security community