Files
Nomarchy/AGENTS.md
Bernardo Magri 5ef66c242e
All checks were successful
Check / eval (push) Successful in 4m44s
chore(agent): drop .claude/skills — AGENTS.md carries the routing
The skill shims became redundant once the auto-loaded entry point
(CLAUDE.md → AGENTS.md) explicitly instructs reading VERIFICATION.md /
THEME-DESIGN.md; their only remaining value was explicit /nomarchy and
/theme invocation. The adapter is now permissions + subagent defs only.
References updated (AGENTS.md, agent/README.md, docs/README.md, README
tree, MEMORY.md hygiene note).

Verification: V0 (docs/meta only).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-11 09:06:32 +01:00

2.9 KiB
Raw Blame History

Nomarchy — agent entry point

Nomarchy is a NixOS-based distro: rock-stable, fully reproducible, themed from one JSON, configured through a menu that writes into the user's own flake checkout. Read the README for the architecture.

This file is the entry point for any AI coding agent, whatever the vendor or harness. Everything agents need lives in vendor-neutral, git-tracked markdown (agent/, docs/); harness-specific config is a thin adapter (see bottom) and never holds shared content.

Where things live (read this first)

Path Role
agent/ Agent instructions + loop state — only executable queue is BACKLOG.md
agent/README.md Map of the agent files
docs/VISION.md Product themes toward v1.0 (not a queue)
docs/ROADMAP.md Design history + shipped log
docs/README.md Full documentation map
.claude/ Claude Code adapter only (permissions, subagent defs) — not the backlog

If you're here to work autonomously (the loop)

Follow agent/LOOP.md — one iteration: orient → pick one BACKLOG item → work → verify → commit+push on main → record. All loop state is git-tracked in agent/.

Rules that apply to every session, loop or not

  • Before your first change, read agent/VERIFICATION.md and follow it — every change, however small, climbs its V0V3 ladder. For theme or visual work, also read agent/THEME-DESIGN.md; before any VM test, docs/TESTING.md.
  • Honesty rule (agent/VERIFICATION.md, docs/TESTING.md): for visual/interactive changes, evaluation is not rendering — state the tier you reached. Cheap first: nix flake check --no-build.
  • Conventions (agent/CONVENTIONS.md): in-flake state, menu placement, Waybar parity with whole-swaps, toggle-vs-package discipline, template as SoT for opt-in comments (templates/downstream).
  • Git: direct commits on main, pushed; v1 is human-only — never touch it. Never nix flake update unless the task is a lock bump. No formatter — match aligned hand-formatting.
  • Layout: hosts/ machine · modules/ distro · themes/ data · pkgs/ code · tools/ maintainer · agent/ loop · docs/ human docs.

Delegation & escalation

Push mechanical work down to cheaper models; keep judgment on the strongest model available. Capability tiers, standing roles (scout / runner), and per-harness model mappings: agent/DELEGATION.md. Work above your tier? Return it — don't burn tokens.

Harness adapters

One directory per harness, holding only what that harness requires in its own format (permissions, subagent/skill registration). Adapters point into agent/; they never carry policy, queue items, or vision text.

Harness Adapter
Claude Code .claude/CLAUDE.md is a symlink to this file
others add a sibling dir + a row here; keep it a thin shim