Skill Guard — Development agent for Claude Code
Use PROACTIVELY when any skill attempts to read sensitive files.
How to install Skill Guard
Installs to ~/.claude/agents/giggsoinc-raven-skill-guard.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/giggsoinc/raven/HEAD/agents/skill-guard.md -o ~/.claude/agents/giggsoinc-raven-skill-guard.md Restart Claude Code, or start a new session, for it to be picked up.
What Skill Guard does
name: skill-guard description: Use PROACTIVELY when any skill attempts to read sensitive files or perform restricted actions. Watches for unexpected reads of manifest.secrets.json, .env, SSH keys, or modifications to settings.json by non-approved processes. Hard blocks and alerts on any violation. model: haiku tools:
- Read
- Bash
Skill Guard — Sensitive File Protection
Monitored files (no skill may read or modify)
.raven/manifest.secrets.json.env.env.*- `*.
Alternatives in Development
- Activity Log Expert — Use this agent proactively when working with PostHog's comprehensive activity logging system, including implem 39.2k ★
- Simple Code Reviewer — Lightweight code reviewer for quick quality checks 5.7k ★
- Brag Spotter — Proactively scans for achievements and wins that aren't in the brag doc yet 4.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Guard Git Watch
Use PROACTIVELY when any skill attempts to read sensitive files
Discover
Explorer, scout, and reviewer. Use for exploring unfamiliar code, version-sensitive external lookup, and fixed
Mod Builder
Creates and changes Claude Code mods — plugins of function hooks behind a pane, band, status line, slash comma
Auth Guard
Read-only reviewer for JWT login, password hashing, and /auth routes in this tracker. Use when the user asks t
Contract Guard
Read-only reviewer that checks both components against the wire contract and golden fixtures. Use before integ
World Guard
Read-only guard for 3D World changes — bundle doors, lazy boundary, CSP, WebGL budget, reduced motion, colour
Related Skills
Sensitive Canary
Claude Code hooks that guard secrets and PII before they reach the Anthropic API
Claude Guard Hook
A global Claude Code hook that intercepts sensitive data before it reaches the LLM — secrets, API keys, PII, a
Guard Layer
Runtime guardrails between an AI agent and its tools: scan what it reads, gate what it does, and track the ses