Armorclaude
Intent-based security enforcement for Claude Code. ArmorClaude makes Claude declare what it intends to do before doing it, then checks every tool call against that plan. Adds policy rules, intent drift detection, cryptographic proofs, and audit logging to the ArmorIQ platform. Works in both Claude Code CLI and Claude Desktop. Install with one curl command, optionally connect to ArmorIQ for signed JWT tokens and dashboard visibility.
Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code
Category: Security — see all ranked ›
Work: Agent configuration · Security review
Who it is for: Agent operator · Security engineer
“Documents fail-closed blocking, the one-time install line, and every env var default”
- tashan score: 68.0
- Expertise: 79.0 (solid)
- Adoption: 2 repos
- Health: active
- GitHub stars: 44
- Contributors: 8
- License: MIT
Security audit
Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.
source ↗ · plugin:armoriq/armorclaude/armorclaude
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›