docs(agent): model & token economy rules for the loop

Plan/reason/review on the strong model (Fable 5); delegate mechanical,
fully-specified subtasks (grep sweeps, table reconciliation, repeated
edits, log summarization) to cheaper models (haiku/sonnet) via subagent
model overrides — the strong model writes the spec and owns the commit.
Plus narrow-reading and terse-writing rules, and a cheaper --model
allowance for low-stakes headless iterations.

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

agent/LOOP.md

@@ -26,6 +26,33 @@ 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) |
 
+## Model & token economy
+
+Spend expensive tokens on judgment, not mechanics.
+
+- **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,
+  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.
+- **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
+  build/check logs instead of dumping them.
+- **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
+  `modules/` or `pkgs/` behavior keep the strong model.
+
 ## One iteration, step by step
 
 ### 0. Orient
@@ -58,6 +85,8 @@ outside the checkout (the distro's own philosophy, applied to its agents).
 ### 2. Work
 - Keep the diff focused on the task. Unrelated fixes you trip over become
   PROPOSED/NOW entries, not scope creep.
+- Mechanical, fully-specified sub-steps go to a cheaper model
+  (see *Model & token economy* above); design and review stay here.
 - Follow `CONVENTIONS.md`. Match the surrounding hand-formatting; never
   run a formatter.
 - New gotcha discovered the hard way → one line in `MEMORY.md` now, while