Architecture Rules Generator

Produce hot memory for coding agents: a single always-loaded {harness_root}/rules/architecture-rules.md that encodes how this repository is structured and which constraints agents must not violate.

This is not a business spec (codebase-reverse-spec) or an SDD planning artifact (bootstrap-brownfield). It is the constitution — loaded every session, kept lean, written for machine consumption with explicit paths and do/don't rules.

Design principles

1. Agent-first — file paths, entry points, forbidden zones, and test commands. A developer skimming prose is not the audience.
2. Lean by default — target 80–200 lines (hard cap ~250). Depth belongs in scoped layer rules or docs/; this file routes to them.
3. Evidence-based — every rule must trace to something found in the repo. Mark inferred items; do not invent stack or patterns.
4. Load-bearing — agents trust this absolutely. Stale rules cause silent failures; prefer omission over guesswork.
5. Separation — universal architecture here; file-type or domain detail in sibling rules (backend-rules.md, frontend-rules.md, etc.).

See references/compression-guide.md when the draft exceeds the line budget.

Harness discovery

See ../nextstage-harness/references/harness-discovery.md and ../nextstage-harness/references/rules-sync.md.