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/DELEGATION.md

@@ -0,0 +1,112 @@
+# Delegation — capability tiers, roles, token economy
+
+How to spend model capacity in this repo, for **any** agent harness.
+Tasks are matched to capability *tiers*, not vendor model names; each
+harness maps tiers to its own models (table at the bottom). GOALS says
+what to build, CONVENTIONS how to write it — this says who does which
+part.
+
+## The dividing line: evidence vs judgment
+
+Cheap models gather evidence; they never make verification claims or
+design decisions. The following always stay on the **frontier** tier and
+are never delegated downward:
+
+- deciding what to test and the regression scope (VERIFICATION.md)
+- interpreting an ambiguous or flaky failure
+- viewing screenshots and judging visual quality — aesthetic judgment is
+  exactly what small models do badly, and it's load-bearing here
+- writing non-trivial Nix (module structure, overlays, cross-cutting
+  refactors)
+- the final diff review and report
+
+Product calls ("finish vs quarantine", promoting PROPOSED items) sit
+above even that: they belong to the human.
+
+## Tiers
+
+| Tier | Best for | Delegate to it? |
+|------|----------|-----------------|
+| **light** | bulk mechanical: search, summarize, audit sweeps, running the harness | freely — never for judgment |
+| **standard** | well-specified scoped edits, routine research | when the spec is already written |
+| **frontier** | design, novel code, ambiguous failures, taste | this is the loop's own tier |
+
+Reasoning effort: default moderate; go maximum only for the hardest
+calls. A frontier parent may spawn a frontier child for one hard call.
+Work above your tier gets returned, not attempted.
+
+## Standing roles
+
+Two mechanical roles exist for any harness that supports subagents
+(Claude Code implementations: `.claude/agents/`; other harnesses
+implement the same contracts in their own format):
+
+- **scout** (light, read-only): locate where things are defined, map
+  which files touch a subsystem, scan build logs / serial output for
+  error lines, docs-vs-code drift sweeps. Reports facts with paths and
+  line numbers, quotes the minimum snippet, says "not found" plainly —
+  never guesses, never recommends.
+- **runner** (light, executes): builds, VM boots, screenshot capture,
+  the scripted `tools/` checks. Headless and unattended, every wait
+  bounded by a timeout. Returns commands, exit codes, wall time, and
+  artifact paths — never marks anything passed or verified; the caller
+  makes the verification claim.
+
+Use them for pure information-gathering or pure execution instead of
+pulling bulk (log files, wide scans) into the main context. When a
+result surprises you, spot-check it yourself before building on it —
+cheap models are allowed to be wrong about hard things, which is
+precisely why they're not allowed to make claims.
+
+## Economy rules
+
+- **Only delegate when writing the spec is cheaper than doing the
+  work** — a spawned agent starts cold and must re-derive context. A
+  one-file read is cheaper done directly.
+- **Brief every child cold; point at the spec, don't restate it.** "The
+  spec is in `agent/BACKLOG.md` #NN — implement it" plus only the
+  *constraints* (scope files, branch, no-VM, no-push).
+- **Match the tier to the task, not the prestige.** An item whose spec
+  is already written (exact files, exact fixes) is standard-tier work;
+  reserve frontier children for genuine multi-step reasoning. This is
+  the single biggest saving.
+- The strong model writes the spec, reviews the result, and owns the
+  commit.
+
+## Fanning out parallel work (V0/V1, no VM)
+
+When several NEXT items are independent and don't need the VM, spread
+them across worktree-isolated subagents in parallel:
+
+- **Disjoint file lanes.** Partition items so no two agents touch the
+  same file (map the touched files first). If two items must share a
+  file (README, flake.nix, rofi.nix), give both to one agent or keep
+  one for yourself.
+- **Isolation + you own landing.** Each agent works in an isolated
+  worktree, commits to its own branch, and **never pushes or touches
+  `main`/`v1`**. You review each diff, cherry-pick onto `main`, and do
+  the bookkeeping — a single landing agent can't race itself. Clean up
+  worktrees and branches after landing.
+- **Lean on scriptable checks as primary evidence.** Where a
+  deterministic `tools/` check or `checks.*` guard already proves the
+  property, that near-free run *is* the V0/V1 evidence.
+- **Batch V2 at the end, once.** Delegated visual/behavioural items come
+  back "V2 pending"; collect the landed changes and do **one** VM pass
+  covering all of them — the VM render + screenshot review is the most
+  expensive step in the loop; amortise it.
+- **Re-verify on `main`, but leanly.** After landing, confirm the
+  agent's V0/V1 on the merged tree with a targeted build, not a full
+  re-run. Trust-but-spot-check scales; blind re-running doesn't.
+
+The judgment list above still holds: *you* review every diff before it
+lands.
+
+## Per-harness model mapping
+
+| Tier | Claude Code |
+|------|-------------|
+| light | `haiku` |
+| standard | `sonnet` |
+| frontier | the session's top model (`opus` and up) |
+
+Other harnesses: add a column when one is actually used on this repo.