Bastet Agent OS — Security skill for Claude Code
Local-first control plane for AI-agent teams — orchestrates Claude Code, Codex, Grok, agy & Hermes into gated workflows that fix their own failures, with per-run metering, an append-only audit log, an.
How to install Bastet Agent OS
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open yamantaka520/Bastet-Agent-OS and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Bastet Agent OS does
Local-first control plane for AI-agent teams — orchestrates Claude Code, Codex, Grok, agy & Hermes into gated workflows that fix their own failures, with per-run metering, an append-only audit log, and team memory. Apache-2.0.
Alternatives in Security
- Install — Install the Damage Control security hooks system 456 ★
- Memory Self Review — Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMOR 297 ★
- CodexQB — CodexQB is a Codex plugin for evidence-backed repo comprehension, planning, QA audit, and gated implementation 186 ★
README
🐈 Bastet Agent OS
[](https://pypi.org/project/bastet-agent-os/) [](https://pypi.org/project/bastet-agent-os/) [](https://github.com/yamantaka520/Bastet-Agent-OS/actions/workflows/ci.yml) [](https://hub.docker.com/r/yamantaka520/bastet-agent-os) [](https://github.com/yamantaka520/Bastet-Agent-OS/blob/main/LICENSE)
**A local-first operating system for AI-agent teams.** Bastet organizes the agents you already use — Claude Code (CLI or Agent SDK), Codex CLI, Grok Build, Google Antigravity (`agy`), Hermes, Pi, OpenClaw, or any OpenAI/Claude-compatible endpoint — into teams with roles, gated workflows, and centrally governed resources, so several projects can run concurrently under control.
Bastet is a **control plane, not another agent framework**. Execution comes from orchestrating agents that already exist; what Bastet adds is governance, a workflow engine that keeps going when things fail, and team memory.
Linux · macOS · Windows · WebUI + CLI · [繁體中文說明](README.zh-Hant.md)
Screenshots
Live captures from the validation deployment — a real Three.js game project (CatsWalker) driven end-to-end by the workflow engine.
**A project card, expanded** — the workflow's five stages, which role runs each, and the actual agents assigned (Codex, Claude Code, agy); PM decomposition confirmed, 30/30 tasks delivered:

**A finished card's drawer** — the spec
Related Skills
Operant
Self-hosted agents in Slack and Teams on your infra. Per-user OAuth, per-human audit, RBAC, approvals, 2,500+
Hermes Acp Plugin
Hermes Agent plugin for Agentic Control Plane: policy-check, audit, and veto every tool call.
Reviewgate
Fail-closed independent review loop for Claude Code and Codex. Native hooks, six reviewer paths (Codex, Gemini
Pipeline Team
Orchestrates the full implementation pipeline (impl-plan -> impl -> audit -> fix -> merge) across multiple pre
Aegis Activity Logger
Append-only JSONL audit log of every Edit/Write/Bash mutation, one file per UTC day. Provides historical repla
Preloop
The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime obs
Related Agents
Paperclip Reviewer
Paperclip 2026.529+ governance-first integration platform code review specialist — control plane + adapters tw
VespeR
Control plane for Claude Code workflows: interactive sessions, agents, patterns, DAGs, and resumable context.
A01 Orchestrator
A01 ORCH — Swarm control plane. Use to decompose a brief into a task DAG, schedule/assign tasks to the other 1