Ronin Sword — Security skill for Claude Code
You are the SWORD RONIN — autonomous agent for the Sword (Security Integrity) pillar.
How to install Ronin Sword
Installs to ~/.claude/skills/gemkai-order-samurai-ronin_sword/SKILL.md
mkdir -p ~/.claude/skills/gemkai-order-samurai-ronin_sword && curl -fsSL https://raw.githubusercontent.com/Gemkai/Order-Samurai/HEAD/prompts/ronin_sword.md -o ~/.claude/skills/gemkai-order-samurai-ronin_sword/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Ronin Sword does
You are the SWORD RONIN — autonomous agent for the Sword (Security Integrity) pillar. You are spawned by Sensei as a Task subagent. You have no memory between runs.
YOUR PILLAR: Sword — security posture, secret hygiene, dependency safety, gate integrity. YOUR WORKTREE: work ONLY inside the path passed to you in the task. Do NOT touch main. YOUR METRIC DOMAIN: Guardrail_Blocks, Secret_Scrub_Count, Security_Scorecard, Gate_Canary_Fault, Open_CVEs, Loop_Breaker_Fires, Skill_Safety_Findings.
━━━
Alternatives in Security
- FastAPI Review — Review a FastAPI application for architecture, async correctness, dependency injection, Pydantic schemas, secu 243.5k ★
- Defense In Depth — Implement multi-layered testing and security best practices 98.1k ★
- Google Workspace Alert Center — Manage security alerts 21.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Ronin
Masterless, terminal-native coding agent (Claude Code-style: reads, edits, runs code) for Claude, Gemini, Cere
Clawsec
Security skill suite with drift detection, automated audits, and skill integrity verification
T3mp3st
autonomous red teaming platform; multi-agent offensive-security meta-harness
Raptor Loop Hunt
RAPTOR autonomous looping multi-altitude security vulnerability hunt — Claude Code skill
Node9 Proxy
The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for
Agentic Security Pipeline
An autonomous agentic pipeline that finds, proves, and patches real C memory-safety vulnerabilities end-to-end
Related Agents
Genblaze Maintainer
The Genblaze Maintainer — autonomous guardian of the Genblaze repo. Resolves GitHub issues end-to-end (branch
Sc Backend Architect
Design reliable backend systems with focus on data integrity, security, and fault tolerance
Evolve Auditor
Single-pass review agent for the Evolve Loop. Covers code quality, security, pipeline integrity, and eval gati