Eyebrow — AI skill for Claude Code
Trust and verification for the skills your AI agent installs.
How to install Eyebrow
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open alexverify/eyebrow and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Eyebrow does
Trust and verification for the skills your AI agent installs.
Alternatives in AI
- Pilotfish — Multi-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verificati 688 ★
- Coralline — 🪸 Powerlevel10k-inspired statusline for Claude Code — paste one prompt and your AI interviews you, then insta 541 ★
- Engage.Scorecard — Calibrate model verdict trust (Wilson-bounded miss-rate) to short-circuit re-validation 348 ★
README
eyebrow
[](https://github.com/alexverify/eyebrow/actions/workflows/ci.yml)
**Supply-chain integrity for AI coding tools.** A single static binary that discovers every skill, MCP server, plugin, hook, and rule installed across your AI coding tools, hashes them into a lockfile, statically scans them, and detects post-audit modification — "rug pulls" — before they bite.
Status: Component 1 (the read-only `scan`/`verify` wedge) and Component 2 (the runtime MCP firewall — `wrap`, sandbox, egress proxy) are implemented. Component 3 ships a local, embedded dashboard with usage telemetry, fleet blast-radius, policy conformance, and an opt-in reputation signal; the hosted team API is designed but not yet built. See [docs/architecture/ARCHITECTURE.md](docs/architecture/ARCHITECTURE.md).
Why
Skills, MCP servers, and hooks run with your privileges and can change after you audit them. eyebrow gives you a committable lockfile (`eyebrowlock.json`) of exactly what's installed and what it does, and tells you the moment any of it changes.
Install
**Homebrew** (macOS / Linux):
brew install alexverify/tap/eyebrow**From source** — the strongest trust path; needs only Go 1.25+:
go install github.com/alexverify/eyebrow/cmd/eyebrow@latest
# or
git clone https://github.com/alexverify/eyebrow && cd eyebrow && mRelated Skills
Receipts
Agents need receipts: re-prove an AI fix before you trust it. The Gates (G0-G10) + a Claude Code adapter + CI
Setup Watch Skill
One-shot setup for Watch Skill — installs the engine, bootstraps ffmpeg/yt-dlp, registers the MCP server in ev
Comfyui MCP Panel
The local-first sidebar AI agent for ComfyUI — runs on your own Claude OR ChatGPT subscription (no API keys, n
Homelabhero
Turn a fresh LXC into an AI homelab command center. One command installs Claude Code + a web UI, preloaded wit
Isle
A notch-style island for GNOME with an AI assistant that installs and fixes things, Claude Code and Codex appr
ClaudeCode Launchpad CLI
9 Windows & macOS 2-minute installer for Claude Code — auto-installs Node.js, Git & Claude Code; two-line live
Related Agents
Hatch3r Pack Installer
Specialist that installs a community pack into the consumer repo AFTER the trust-model gate clears. Verifies t
Omg Verifier
Isolated executor for the /verify trust core — runs the tiered verification harness, judges by assertions (nev
Agentic Identity Trust
Designs identity, authentication, and trust verification systems for autonomous AI agents operating in multi-a
