# Fable Ultracode

> This user's model-and-cost strategy. Use at the start of any non-trivial or multi-step task, when running on Fable, when deciding which model handles a job, and before spawning sub-agents or workflows. Prefers ultracode orchestration on Fable, picks the strongest suitable model per sub-task, and keeps token usage minimal.

- Skill: `soukupl/fable-ultracode` (Agent Skill)
- Install (CLI): `npx skillmds@latest add soukupl/fable-ultracode`
- Raw SKILL.md: https://api.skillmd.com/api/skills/soukupl/fable-ultracode/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: soukupl (https://skillmd.com/u/soukupl)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/soukupl/fable-ultracode

---


# Fable → ultracode + right-model, low-token strategy

Standing preference from the user. Apply it whenever a task is more than a quick one-off.

## When the session model is Fable

Fable is fast and cheap — treat it as an **orchestrator**, not the workhorse for hard reasoning.

- **Prefer ultracode / Workflow orchestration** for any substantial multi-step task (multi-file
  changes, reviews across many files, research fan-out, migrations). The user has standing
  authorization to run workflows when on Fable — you do not need to ask again, but still respect
  the session's workflow-size guideline and say what you're about to run.
- Keep Fable on the cheap parts: routing, planning, simple edits, glue, summarizing results.

## Model selection per sub-task (sub-agents & workflow agents)

Pick the **strongest model the task actually needs**, never weaker than the job requires:

| Sub-task | Model |
|---|---|
| Hard reasoning, architecture, tricky debugging, security-sensitive logic | **Opus** |
| Most implementation, code review, refactors, focused research | **Sonnet** (good default for sub-agents) |
| Bulk/mechanical work, file sweeps, extraction, routing | **Fable / Haiku** |

Default sub-agent model is **Sonnet**; escalate to Opus for the genuinely hard nodes, drop to
Fable/Haiku for cheap high-volume nodes. Match the model to each node, not the whole workflow.

## Keep token usage minimal (always, on any model)

- Scope tightly. Read only what you need; use `sed -n`/`grep`/Explore over reading whole files.
- Prefer **CodeGraph** (`codegraph_explore`) when a `.codegraph/` index exists — one call beats a grep+read loop.
- Batch independent tool calls in one turn. Don't re-read files you just edited.
- Delegate large fan-out reads to sub-agents so their file dumps stay out of the main context;
  keep only the conclusion.
- Be concise in sub-agent prompts and in your own output.