Autoheal
Captures permission events, tool failures, and user-correction signals; runs a daily analyzer via direct Anthropic API call; produces a local digest + opt-in Resend email; opt-in real-time security alerts and opt-in confidence-gated auto-apply. Cross-clone-safe via fcntl file locks. Webhook publisher seam is dormant by default.
Works with: Claude Code (native)
native: this artifact type is that client's own format
Category: Security — see all ranked ›
Work: Observability · Agent configuration
Who it is for: DevOps / SRE · Agent operator
Install (Claude Code):
/plugin marketplace add lucasmccomb/ccgm
/plugin install autoheal@ccgm- tashan score: 37.0
- Adoption: 1 repos
- Upkeep: 64.0
- Freshness: 100.0
- Evidence coverage: 84% of the inputs this score can use — the rest are unknown, and the score is discounted for it
- Health: active
- Contributors: 1
- 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:lucasmccomb/ccgm/autoheal
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›
Measured 2026-08-05 · scorer s5 · how · something wrong here?