Hermes Claude Code Bridge — Security skill for Claude Code
Run Claude Code or OpenCode as an OpenAI-compatible backend — a security-first, read-only Lead DevOps/SRE agent from laptop to GKE.
How to install Hermes Claude Code Bridge
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open ch-muhammad-asim/hermes-claude-code-bridge and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Hermes Claude Code Bridge does
Run Claude Code or OpenCode as an OpenAI-compatible backend — a security-first, read-only Lead DevOps/SRE agent from laptop to GKE.
Alternatives in Security
- Anthropic Cybersecurity Skills — 734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work 3.8k ★
- Pocketpaw — Your AI agent in 30 seconds 775 ★
- Claude Bootstrap — Opinionated project initialization with security-first guardrails, spec-driven atomic todos, LLM testing patte 536 ★
README
🌉 Hermes × Claude Code Bridge
**Run [Claude Code](https://claude.com/claude-code) as an OpenAI-compatible backend — anywhere.** From a single Windows laptop to a production GKE cluster, with a **security-first, read-only** operations posture. 🔒
[](./mac) [](./windows) [](./ubuntu-desktop) [](./docker) [](./kubernetes)
[](https://www.youtube.com/watch?v=m8k2GGRldiU)
🎥 Watch it in action
**[I Turned Claude Code Into an OpenAI-Compatible SRE Agent on GKE 🤖☸️](https://www.youtube.com/watch?v=m8k2GGRldiU)** A full walkthrough — deploying the read-only agent on GKE, and watching Hermes **diagnose and fix** a broken Kubernetes deployment through the three-gate security model, then revoke access. 📺 More cloud/DevOps/SRE deep-dives on [**@devopsgang**](https://www.youtube.com/@devopsgang).
🧭 What is this?
A small, dependency-light **HTTP bridge** that turns your authenticated **Claude Code CLI** into an **OpenAI-compatible `/v1/chat/completions` endpoint**. Any tool, SDK, or agent gateway that speaks the OpenAI API can now use Claude Code as its model backend — with streaming, real token accounting, concurrency control, and tool-permission enforcement.
It ships with five production-tested ways to run it, and pairs with the **Hermes agent gateway** to deliver a
Related Skills
Polyagent
Multi-provider AI agent bridge — an MCP server that lets Claude Desktop delegate tasks (security scans, code r
Understudy
One AI, Every Role — A system that configures teams of specialized AI agents (Architect, Backend, Frontend, De
Ops Engineering Skills
Open-source, cross-agent Agent Skills for DevOps, DevSecOps, Cloud, Kubernetes/platform engineering, CI/CD too
AegisGate
Open-source security gateway for LLM APIs — prompt injection detection, PII redaction, dangerous response sani
Claude Code Dev Agents
A comprehensive collection of specialized Claude Code subagents for software development lifecycle. Domain-agn
Millieskills
Research-driven universal AI Agent Skills for UI/UX, code repair, security, testing, architecture, backend/API
Related Agents
Opencode
Coding subagent that runs inside opencode, on any provider and model opencode supports (OpenAI, Google, Moonsh
Beam SRE
Use this agent as the Senior Platform Engineer / BEAM SRE — the on-call defender of the Living Platform's Plan
Infra Expert
Use this agent as a distinguished Infrastructure/K8s/SRE authority for peer-review-level infrastructure review