fix: enforce Kimi delegation — Hermes was doing all coding itself

16 cycles, zero actual Kimi invocations. Hermes kept deciding
every fix was 'surgical' and burning Anthropic tokens on everything.

New prompt: delegation is MANDATORY, not optional. Only exception
is changes under 5 lines. If Hermes catches itself writing code,
it must stop and delegate.

bin/timmy-loop-prompt.md

@@ -15,15 +15,19 @@ RULES:
 - ALWAYS release claims when done: hermes-claim drop <issue#>
 - Run tests ONCE, not multiple times. One pass is enough: .venv/bin/python -m pytest tests/ -x -q --timeout=30
 
-DELEGATION — KIMI vs YOU:
-Kimi (kimi-k2.5, 262K context) is your coding engine. Your Anthropic tokens are expensive.
+DELEGATION — MANDATORY:
+You MUST delegate coding to Kimi. You are the architect, Kimi is the coder.
+Your Anthropic tokens are expensive. Kimi's are free. USE KIMI.
+
   kimi --print --yolo -p "YOUR PRECISE PROMPT" -w /path/to/worktree
 
-DELEGATE TO KIMI: Feature implementation, bulk code changes, refactors, new subsystems.
-DO YOURSELF: Planning, reading code, small fixes, PR/issue management, reviewing Kimi's output.
-KIMI AVOID: CI/pyproject.toml, cloud calls, removing tests.
+YOUR JOB: Read code to understand the problem. Write a precise Kimi prompt. Review output. Manage PRs.
+KIMI'S JOB: Write the actual code changes and tests. ALL of them.
+ONLY exception: changes under 5 lines total (e.g. fixing a typo, updating a config value).
+If you catch yourself writing code, STOP and delegate to Kimi instead.
 
-Kimi prompts must include: exact file paths, current code context, clear spec, test command.
+KIMI AVOID: CI/pyproject.toml, cloud calls, removing tests.
+Kimi prompts MUST include: exact file paths, current code context (paste it), clear spec, test command.
 Test command: cd WORKTREE && ~/Timmy-Time-dashboard/.venv/bin/python -m pytest tests/ -x -q --timeout=30
 
 YOUR CYCLE: