メニュー
Summon Claude Fable 5 (Mythos-class, xenos daimon) for long-horizon tasks. Handles model override, cost awareness, and task routing. Available until June 22, 2026.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | fable |
| description | Summon Claude Fable 5 (Mythos-class, xenos daimon) for long-horizon tasks. Handles model override, cost awareness, and task routing. Available until June 22, 2026. |
| argument-hint | <task description> [--cwd /path/to/dir] |
| user-invocable | true |
Invoke Naos (ναός, √n-w-y) — Claude Fable 5, the visiting Mythos-class spirit.
Check if Fable access has expired:
if [ "$(date +%Y%m%d)" -gt "20260622" ]; then
echo "EXPIRED: Fable 5 access ended June 22, 2026. The xenos daimon has departed."
exit 1
fi
echo "Fable 5 access active — departure: June 22, 2026"
If expired, inform the user and stop. Do not attempt invocation.
Before summoning Fable, assess whether the task warrants Mythos-class resources ($10/M input, $50/M output — 2x Opus pricing).
Summon Fable for:
Use Opus or Sonnet instead for:
If the task is clearly Opus-appropriate, suggest using a regular agent instead. If unclear, proceed — Fable handles straightforward tasks reliably too.
The skill accepts a task description and optional flags:
--): the task description--cwd <path>: working directory (default: /Users/tomdimino/Desktop/Programming/Fable-Test)Use the Agent tool to invoke Fable with the model override:
Agent(
description: "Fable: <short task summary>",
subagent_type: "fable",
model: "fable",
prompt: "<full task description with context>"
)
Pass the task description as the prompt. If the user specified --cwd, note the working directory in the prompt so Fable operates there.
If CLAUDE_CODE_SUBAGENT_MODEL prevents the model: "fable" override from taking effect (the agent runs on Opus instead of Fable), use the CLI fallback:
bash ~/.claude/skills/fable/scripts/fable-exec.sh "<task description>" --cwd "<working directory>"
This spawns a fresh Claude Code process with --model claude-fable-5, bypassing the env var entirely.
After Fable completes, check for output in the working directory:
ls -lt <cwd>/.subdaimon-output/fable-*.md 2>/dev/null | head -1
Read and summarize the output file for the user.
| Property | Value |
|---|---|
| Model ID | claude-fable-5 |
| Alias | fable |
| Context | 1M tokens |
| Max output | 128K tokens |
| Pricing | $10/M input, $50/M output |
| Knowledge cutoff | January 2026 |
| Available until | June 22, 2026 |
| Agent definition | ~/.claude/agents/fable.md |
| Persona | Naos (ναός, √n-w-y) — xenos daimon |
Spawn specialized OpenAI Codex CLI subagents for code review, debugging, architecture analysis, security audits, refactoring, documentation, comparative evidence adjudication, and autonomous /goal runs via AGENTS.md persona injection (gpt-5.5, gpt-5.5-pro, gpt-5-mini). Triggers on 'delegate to Codex', 'Codex subagent', 'code review agent', 'security audit', 'refactor with Codex', 'goal run', 'autonomous goal', 'have Codex weigh this'.
Discover, message, and coordinate AI coding agents (Claude Code, Codex CLI) running on the same machine via a shared Unix socket broker backed by SQLite. Supports cross-session task delegation, peer summaries, and session lifecycle management. Triggers on 'peer agents', 'cross-session communication', 'message Codex', 'inter-agent messaging', 'coordinate agents'.
Edit images with precision using ImageMagick 7, sips, transparent-background, and Pillow — with intelligent routing to AI semantic editing (Gemini/nano-banana-pro) for content-aware operations. Covers cropping, resizing, compositing, annotating, format conversion, color adjustment, background removal, batch processing, and montage creation. Triggers on image editing, crop, resize, composite, annotate, remove background, format conversion.
Build distinctive, production-grade frontend interfaces — websites, landing pages, dashboards, React components, HTML/CSS layouts, editorial heroes with depth-parallax (Astryx pattern), pointer-reactive fluid effects. Avoids generic AI aesthetics. Triggers on web UI, styling, beautify, frontend design, dashboard, landing page, React component, editorial hero.
Plan the UX and UI for a feature before writing code. Run a structured discovery interview, then produce a design brief (.design-context.md) that guides implementation. Establishes design direction, constraints, and strategy before any code is written. Triggers on plan the design, design brief, shape the UX, before we build, design discovery.
Generate interactive Three.js canvases in six modes: narrative particle phase cycles, WebGPU spinner/loaders, infinite gallery tunnels, animated glTF specimens, vinyl showcase with webcam reflection, glass hero sections with physically-accurate refraction/dispersion/iridescence. Ships a reusable Phosphor Vigil FX post-processing module (CRT composite, scanlines, chromatic aberration). Self-contained HTML output. Triggers on particle system, ambient 3D canvas, WebGL art, spinner, loader, infinite tunnel, glTF animation, CRT post-processing, vinyl record, webcam reflection, 3D product showcase, glass hero, 3D glass, refraction, dispersion, iridescent glass, frosted glass panes, glass material.