Runtime Base — Security skill for Claude Code
1Claw's runtime base images and agent-framework templates (Hermes, OpenClaw, OpenCode, OpenClaude, Claude Code, Codex, Amp) — public so anyone running an agent on 1Claw can audit exactly what's in the.
How to install Runtime Base
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open 1clawAI/runtime-base and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Runtime Base does
1Claw's runtime base images and agent-framework templates (Hermes, OpenClaw, OpenCode, OpenClaude, Claude Code, Codex, Amp) — public so anyone running an agent on 1Claw can audit exactly what's in the container.
Alternatives in Security
- OpenTag — Open-source, channel-native agent gateway for Slack 499 ★
- Query Token Audit — Audit token security to detect scams, honeypots, and malicious contracts across BSC, Base, Solana, and Ethereu 483 ★
- Curate Security Results — Run Security Tests & Curate Results — Public-Safe Snapshots 295 ★
README
1Claw Runtime Base
The container image every 1Claw-hosted agent runtime actually runs. Public so anyone running an agent on 1Claw — or thinking about it — can read exactly what's inside the box: what gets installed, what the entrypoint does before your agent's first line of code runs, and how each supported framework is wired up.
What's here
Dockerfile— the base image: Node 24 LTS + Python 3, the@1claw/cli, and the 1Claw Shroud sidecar (built from source in the same build stage, not fetched as a binary).entrypoint.sh/healthcheck.sh— what actually runs when a runtime container starts, and how its health is checked.templates/— one directory per supported agent framework (hermes,openclaw,opencode,openclaude,claude-code,codex,amp), plus plainnode,python, andbinaryruntimes for bring-your-own-agent images, and ashared/directory (native agent server, chat bridge) every framework template pulls from.k8s/— the Kubernetes manifests used where a runtime isn't a Cloud Run service.scripts/— build/publish helpers.SETUP.md— day-to-day operational notes for this image.
Building it yourself
The base `Dockerfile`'s build context is the parent of this repo and the sidecar's, so to build it exactly as CI does, check both out as siblings:
packages/
├── runtime-base/ (this repo)
└── 1claw-shroud-sidecar/ (github.com/1clawAI/1claw-shroud-sidecar)
git clone https://github.com/1clawAI/runtime-base.git packages/runtime-base
git clone https://github.com/1clawAI/1claw-shroud-sidecar.git packages/1claw-shroud-sidecar
cd packages
docker build -f runtime-base/Dockerfile -t runtime-base:latest .
Relationship to the main 1Claw repo
This is extracted from [1clawAI/1claw](https://github.com/1clawAI/1claw)'s `packages/runtime-base`, which vendors it in as a git submodule at the same pat
Related Skills
Jev Skill Router
Jev-powered skill router & security auditor for any AI agent (Codex, Claude Code, OpenCode, Hermes): ONE cheap
Hermes Claude Code Bridge
Run Claude Code or OpenCode as an OpenAI-compatible backend — a security-first, read-only Lead DevOps/SRE agen
Kali Pentest
Kali Linux penetration testing skill for AI agents (Claude Code, OpenClaw, Hermes Agent). 200+ CLI tools, 15 s
Pfm
MANDATORY — route every change to CLAUDE.md, .claude/, the .codex/ mirror or templates/ here. /pfm {change req
Bastet Agent OS
Local-first control plane for AI-agent teams — orchestrates Claude Code, Codex, Grok, agy & Hermes into gated
Reviewgate
Fail-closed independent review loop for Claude Code and Codex. Native hooks, six reviewer paths (Codex, Gemini
Related Agents
Hermes Agent
Integration file for a Hermes-style personal agent system. Use when a Hermes deployment (a self-hosted assista
Ensemble Curator
High-volume triage agent for external-AI-agent PRs (Codex, Jules, Hermes, Droid, Aider, etc.). Analyzes, conso
Tp API Surface Tracker
PROACTIVELY use this when the user asks "what changed in our public API", "did we break anyone", "is this a br