v1.0.0 — Initial release (retroactively tagged)

Note: This release is tagged retroactively against commit 0e3d60d. The repo went straight from v1.0.0 work to v1.1.0 before the first public release was cut; this tag exists for completeness of the version history. New installs should use v1.1.0 which adds the Warden role and the /goal contract on top of everything here.

Initial installable form of claude-layers — the four-layer behavioral configuration system for Claude Code.

What's in v1.0.0

• Layer 1 (CLAUDE.md) — eight numbered behavioral guidelines drawn from Karpathy's late-2025 Claude Code notes (HN discussion). Read before write, surface confusion, hold position under challenge, surgical edits.
• Layer 2 — three role overlays:
  • FORGE.md (builder) — implements specs, refuses to architect
  • QUILL.md (writer) — writes specs/docs, refuses to write code
  • SCOUT.md (investigator) — traces and reports, refuses to decide the fix
• Layer 3 — project overlays: PROJECT_TEMPLATE.md plus three reference examples (PROJECT_WEBAPP, PROJECT_API, PROJECT_CLI)
• Orchestrator (ARGENT.md) — composes context across layers and routes operator requests to the right specialist
• Bash installer — --minimal, --yes, --help flags; idempotent
• Docs — LAYERING_MODEL.md, ROUTING_PATTERNS.md, CREATING_OVERLAYS.md

Install

curl -fsSL https://raw.githubusercontent.com/frontier-infra/claude-layers/main/install.sh | bash

Upgrade path

→ v1.1.0 adds the Warden verifier role, the /goal manifest + verification protocol, and a binding orchestrator dispatch contract that refuses to spawn generic workers.

🤖 Generated with Claude Code

v1.1.0 — Warden role + /goal contract

First public release of claude-layers — a layered behavioral configuration system for Claude Code.

This release ships the full v1.1.0 stack: the universal Layer 1 base, four role overlays (Forge/Quill/Scout/Warden), three example project overlays, the orchestrator overlay (Argent), and the verifiable /goal contract loop.

What's in the box

• Layer 1 (CLAUDE.md) — eight numbered behavioral guidelines drawn from Karpathy's late-2025 Claude Code notes (HN discussion). Read before write, surface confusion, hold position under challenge, surgical edits.
• Layer 2 — four role overlays:
  • FORGE.md (builder) — implements specs, refuses to architect
  • QUILL.md (writer) — writes specs/docs, refuses to write code
  • SCOUT.md (investigator) — traces and reports, refuses to decide the fix
  • WARDEN.md (verifier) — runs the /goal manifest, signs off or kicks back
• Layer 3 — project overlays: PROJECT_TEMPLATE.md plus three reference examples (PROJECT_WEBAPP, PROJECT_API, PROJECT_CLI)
• Orchestrator (ARGENT.md) — composes context across layers; v1.1.0 adds a binding dispatch contract that refuses to spawn "general-purpose" workers (every dispatch must name a role overlay, a project overlay, and a /goal manifest)
• Slash commands — /goal writes the manifest, /goal-verify runs Warden
• /goal protocol — manifest schema, six check types (test, command, file_exists, file_contains, diff_constraint, human_review), three sign-off states (true, false, "pending"), full Stop-hook contract documented in .claude/docs/GOAL_PROTOCOL.md
• Reference Stop-hook config — .claude/settings.example.json blocks worker termination until signed_off === true
• Bash installer — --minimal, --yes, --help flags; idempotent; backed by CI install test

The closed loop

/goal → manifest written → Argent dispatches role-typed worker →
worker delivers → /goal-verify → Warden → proof.json →
Stop hook reads proof → releases iff signed_off === true

Install

curl -fsSL https://raw.githubusercontent.com/frontier-infra/claude-layers/main/install.sh | bash

Or clone and run ./install.sh /path/to/your/project.

Failure modes addressed

• Wrong assumptions run with silently → Layer 1 §2 (surface confusion)
• Sycophantic capitulation → Layer 1 §3 (hold position)
• Bloated abstractions → Layer 1 §4 (simplicity default)
• Scope creep into adjacent code → Layer 1 §5 (surgical edits)
• Builder making architecture decisions → Forge "what you do not own"
• Worker self-assessing "done" without verification → Warden + /goal manifest + Stop hook
• Orchestrator dispatching generic workers → Argent dispatch contract (role + project + manifest required)

Acknowledgments

Base discipline draws on Andrej Karpathy's late-2025 Claude Code notes. Layered architecture is informed by years of building multi-agent systems where flat configurations consistently failed at scale.

🤖 Generated with Claude Code