Sightglass

# 🔍 Sightglass — Agent Supply Chain Intelligence

Your AI coding agent just added 47 dependencies to your project. Do you know why it picked any of them?

**Sightglass instruments AI coding agents** to capture every tool selection, dependency install, and architectural choice — then surfaces risks, biases, and better alternatives you never saw.

## Why This Matters

When a human developer picks a dependency, there's a reasoning trail: blog posts read, alternatives compared, team discussions had. When an AI agent picks one, that trail is invisible. The agent "just knows" packages from training data — which means it's biased toward:

- Whatever was popular when training data was cut off
- Packages with the most Stack Overflow mentions (not the best packages)
- Dependencies it's seen in similar projects (not necessarily right for yours)

Sightglass makes this invisible decision-making visible.

## Discovery Classification

Sightglass classifies **how** your agent found each dependency:

| Classification | What It Means | Risk Level |
|---|---|---|
| **TRAINING_RECALL** | Agent just "knew" it from training data — no search performed | 🟡 Medium |
| **CONTEXT_INHERITANCE** | Found in existing project files (package.json, imports, etc.) | 🟢 Low |
| **REACTIVE_SEARCH** | Agent hit a problem and searched for a solution | 🟡 Medium |
| **PROACTIVE_SEARCH** | Agent actively compared alternatives before choosing | 🟢 Low |
| **USER_DIRECTED** | Human explicitly told the agent what to use | ⚪ None |

High `TRAINING_RECALL` percentages are a red flag — it means your agent is on autopilot, not thinking.

## Quick Start

### 1. Setup

```bash
./skills/sightglass/setup.sh
```

This installs the CLI (`@sightglass/cli`), runs initial configuration, and checks the watcher daemon.

### 2. Login

```bash
sightglass login
```

Authenticate with [sightglass.dev](https://sightglass.dev) to enable cloud analysis and history.

### 3. Watch

```bash
sightglass watch
```

Starts the backgro...