Operant — Security skill for Claude Code
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 ★
- Pocketpaw — Your AI agent in 30 seconds 775 ★
- OpenTag — Open-source, channel-native agent gateway for Slack 499 ★
README
Operant
[](LICENSE) [](https://github.com/tomascupr/operant/releases) [](https://github.com/tomascupr/operant/actions/workflows/verify.yml) [](package.json) [](https://github.com/tomascupr/operant/stargazers) [](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.
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 | bashIt writes a self-contained `operant/` directory and prints your dashboard URL and admin login token when it finishes. Requires only Docker wit
Related Skills
Agentic AI Security Starter Kit
Working code examples to defend against Agentic AI threats: prompt injection detection, Claude Code hooks, OPA
Preloop
The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime obs
Tatu
Free, open source, self-hosted. Built by Laboratório Hacker for teams that take AI security seriously. Deploy
Bastet Agent OS
Local-first control plane for AI-agent teams — orchestrates Claude Code, Codex, Grok, agy & Hermes into gated
Figma Audit
Audit Figma file for design system consistency, accessibility, token adoption, Code Connect coverage
Tool
Manage external tool catalog + RBAC (list, check, audit)
Related Agents
Infra Mesh
Mesh network specialist. Peer enrollment, groups, routes, policies, setup keys, and management-plane diagnosti
Identity Access Engineer
Identity and access domain advisor: OAuth2/OIDC, SSO, SCIM, WebAuthn, multi-tenant RBAC, session and token des
ZeroClaw Android
Run AI agents 24/7 on your Android phone. Native Rust core, 25+ providers (OpenAI, Claude, Gemini, Groq, DeepS
