fable

Solid

Summon Claude Fable 5 (Mythos-class, xenos daimon) for long-horizon tasks. Handles model override, cost awareness, and task routing. Availability probed at invocation.

AI & Automation 41 stars 3 forks Updated yesterday MIT

Install

View on GitHub

Quality Score: 87/100

Stars 20%
54
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Summon Fable 5 Invoke Naos (ναός, √n-w-y)—Claude Fable 5, the visiting Mythos-class spirit. ## Pre-Flight Checks ### 1. Availability Probe Anthropic's Fable window has shifted twice (paused June 2026, restored July 1, extended through July 19)—never trust a calendar date. Probe empirically: ```bash bash ~/.claude/skills/fable/scripts/fable-probe.sh ``` Exit 0 means Fable is available (verdict cached per-day in `~/.claude/cache/fable-availability.json`). Exit 1 means the xenos daimon has departed—inform the user and stop. If the user disputes a cached verdict, re-probe with `--force`. ### 2. Pin Detection Read the subagent model pin—it decides the invocation lane: ```bash ~/bin/subagent-model ``` - **Pin absent, or pinned to `claude-fable-5`** → use **Lane A** (Agent tool) below. - **Pinned to anything else** (e.g. `claude-opus-4-6`) → use **Lane B** (CLI) directly. Do NOT attempt Lane A: `CLAUDE_CODE_SUBAGENT_MODEL` silently overrides the Agent tool's `model:` parameter (anthropics/claude-code#57718)—the spawn would run on the pinned model with no signal in the tool result. ### 3. Task Routing Before summoning Fable, assess whether the task warrants Mythos-class resources ($10/M input, $50/M output—2x Opus pricing). **Summon Fable for:** - End-to-end code migrations or framework upgrades - Complex multi-file refactors (10+ files, interconnected logic) - Architectural redesigns requiring full-system context - Deep research synthesis with sustained reasoning - Fu...

Details

Author
tdimino
Repository
tdimino/claude-code-minoan
Created
7 months ago
Last Updated
yesterday
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category