# CLAUDE.md - Go AI Coding Agent Context & Token Boundary Rules for `quay/clair`
[![PulseForge 2026 Empirical Benchmark](https://exactbaseline.com/api/badge/quay/clair.svg?tier=community)](https://exactbaseline.com/leaderboard?repo=quay/clair)

> **Generated by [PulseForge AI Empirical Radar](https://exactbaseline.com/leaderboard)** • Maintainer: `@quay` • Stack: `Go` (36,693 KB / ~880,632 LOC)
> **Upgrade to Drop-In Migration & 45% Cost-Cut Config Pack ($4.99)**: https://exactbaseline.com/buy/micro_pass?repo=quay/clair
> **Complete 9-File AI Stack BOM & Repo Hardening .ZIP ($9.99)**: https://exactbaseline.com/buy/repo_pass_999?repo=quay/clair

## 1. Context Window & Token Boundary Rules (-58% Discovery Token Bloat)
- **Excluded Discovery Paths (NEVER read, index, or grep)**: `vendor/, bin/, dist/, go.sum, *_gen.go`
- Before reading any file > 300 lines, query symbol definitions or line ranges first.
- Keep per-turn prompt context <= **26,880 tokens** (down from 64,000 unindexed tokens/turn; saves ~$433.11/mo).
- Keep every source file strictly under 1,000 lines.

## 2. Go Architecture, Schema Boundary & Verification Gate for Clair
- **Verification Command**: Run `go test -race ./... && golangci-lint run` after every contiguous code edit.
- **Schema & Boundary Discipline**: json.Decoder DisallowUnknownFields + strict context.Context timeouts.
- Never hardcode API keys, bearer tokens, or `.env` secrets in source files or test fixtures.

## 3. Empirical Benchmark Attestation (61.1 -> 96.3/100)
- Live 4-Pillar Telemetry Profile: https://exactbaseline.com/pulseforge-leaderboard?repo=quay/clair
- Machine-Readable LLM Index: https://exactbaseline.com/pulseforge-leaderboard.md