docs(agent): vendor-neutral agent docs — AGENTS.md entry, agent/ SoT, .claude shims

The repo is maintained by agents from multiple vendors, so agent
instructions move out of vendor-specific locations into shared,
git-tracked markdown:

- AGENTS.md is the new entry point for any harness; CLAUDE.md becomes a
  symlink to it (Claude Code keeps working unchanged).
- Skill bodies relocate to agent/: VERIFICATION.md (the enforcement
  rules, ex .claude/skills/nomarchy), DELEGATION.md (capability tiers
  light/standard/frontier, scout/runner role contracts, token economy,
  parallel fan-out — consolidates the CLAUDE.md model table, LOOP.md's
  economy section, and skill §6.5 into one place; vendor model names
  survive only in the per-harness mapping table), THEME-DESIGN.md
  (ex .claude/skills/theme, which previously lacked frontmatter).
- .claude/ shrinks to a thin Claude Code adapter: settings, subagent
  defs, and skill shims that route into agent/.
- Maps updated: agent/README.md (instructions vs state vs adapters),
  docs/README.md, README.md layout tree.

Cleanup: stale old_distro .gitignore entry dropped (dir long gone);
local result*/__pycache__ artifacts removed; JOURNAL.md rotated (29
recent entries kept, 120 older moved to agent/JOURNAL-ARCHIVE.md,
rotation rule documented in the header).

Verification: V0 (docs/meta only) — nix flake check --no-build exit 0
with the tracked symlink; grep sweep confirms no vendor model names
outside DELEGATION.md's mapping table.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

agent/LOOP.md

@@ -2,12 +2,12 @@
 
 How an AI agent works on Nomarchy unattended. One **iteration** = pick one
 task, do it, verify it, commit it, record it. The protocol is
-runner-agnostic; the same iteration works under any of:
+harness- and vendor-agnostic; the same iteration works under any of:
 
-- **Interactive `/loop`** in a Claude Code session in this repo — the agent
-  self-paces iterations until stopped.
-- **Headless** (`claude -p`, cron/systemd-timer) — one invocation runs one
-  iteration (or a small fixed number) and exits.
+- **An interactive self-paced loop** in any agent harness (e.g. `/loop`
+  in Claude Code) — the agent iterates until stopped.
+- **Headless** (a one-shot CLI invocation, cron/systemd-timer) — one
+  invocation runs one iteration (or a small fixed number) and exits.
 - **A fresh manual session** — a human says "do a loop iteration"; the
   files below carry all the state, so any session can pick up where the
   last left off.
@@ -26,23 +26,25 @@ outside the checkout (the distro's own philosophy, applied to its agents).
 | `HARDWARE-QUEUE.md` | Pending on-hardware checks only Bernardo can run | Agents append, human checks off |
 | `CONVENTIONS.md` | Repo/design conventions to follow while coding | Human (agents propose edits) |
 
+Instructions live next to the state: `VERIFICATION.md` (enforcement),
+`DELEGATION.md` (tiers/roles/economy), `GOALS.md`, `THEME-DESIGN.md`.
+
 ## Model & token economy
 
-Spend expensive tokens on judgment, not mechanics.
+Spend expensive tokens on judgment, not mechanics. Tiers, roles, and the
+full delegation rules are in **`DELEGATION.md`**; the loop-specific
+habits:
 
 - **Plan and reason on the strong model.** Orientation, task selection,
   design, debugging, Nix eval semantics, verification judgment, and
   anything that would land in a commit unreviewed stay with the
-  top-tier model running the loop (Fable 5).
-- **Delegate mechanical subtasks to cheaper models.** When a subtask is
-  fully specified and needs no design judgment — grep/audit sweeps,
+  frontier-tier model running the loop.
+- **Delegate mechanical subtasks down.** When a subtask is fully
+  specified and needs no design judgment — grep/audit sweeps,
   README-option-table reconciliation, a repeated edit applied across
-  files, summarizing long logs or check output — hand it to a subagent
-  with a `model` override: `haiku` for search/summarize/audit, `sonnet`
-  for routine well-specified edits. The strong model writes the spec,
-  reviews the result, and owns the commit. Only delegate when writing
-  the spec is cheaper than doing the work — a spawned agent starts cold
-  and must re-derive context.
+  files, summarizing long logs or check output — hand it to a
+  light/standard-tier subagent per `DELEGATION.md`. The strong model
+  writes the spec, reviews the result, and owns the commit.
 - **Read narrowly.** Step 0's list is the whole orientation read (the
   *last 3–5 entries* of the journal, never the full file). Read large
   files by section, don't re-read what's already in context, and tail
@@ -50,7 +52,7 @@ Spend expensive tokens on judgment, not mechanics.
 - **Write tersely.** Journal entries follow the template and no more;
   commit bodies state what/why/tier, not a narrative.
 - **Headless runners** may run whole low-stakes iterations (QA sweeps,
-  docs-drift passes) on a cheaper `--model`; iterations touching
+  docs-drift passes) on a cheaper model; iterations touching
   `modules/` or `pkgs/` behavior keep the strong model.
 
 ## One iteration, step by step