⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
fable
Use the locally authenticated Claude Code Fable 5.1 model only as the orchestrator for a task, then execute implementation with GPT-5.6 Luna or DeepSeek V4 Flash. Use when the user invokes $fable or asks Fable to orchestrate Codex agents.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
Fable orchestrator
Fable is a small, local-first routing skill for Codex. Claude Fable 5.1 plans and adjudicates; it does not write code or own the workspace. Codex remains the runtime and delegates bounded implementation work to OpenCode Go agents:
- GPT-5.6 Luna handles normal implementation.
- DeepSeek V4 Flash handles loops, repeated iteration, and high-throughput implementation.
- Fable 5.1 remains outside the implementation graph for planning and final adjudication.
The skill consumes the callable opencode-go/ and opencode-go-responses/ agents supplied by Codex Router. It does not ship a proxy, dashboard, model catalog, credential store, or API key. Configure OpenCode Go once in the router, then restart Codex after changing provider or agent definitions.
Repository layout
skill/fable/
├── SKILL.md
├── agents/openai.yaml
└── scripts/ask_fable.sh
assets/fable-orchestrator.svg
install.sh
tests/test_skill.sh
The three files under skill/fable/ are the installable skill. ask_fable.sh is executable and invokes Claude Code's local fable alias with no session persistence. The packet passed to it must contain decisions and workspace facts only; never put credentials in a packet.
Install
From this repository:
./install.sh --dry-run
./install.sh --copy
--dry-run prints the exact destination and copy operations without creating files. --copy installs to ~/.codex/skills/fable, creates only the required directories, and is safe to run again. Use --target DIR to select another skills directory:
./install.sh --copy --target "$PWD/.local/codex/skills"
The installer reads only this repository and the destination path. It never reads, creates, or modifies credentials. Start a new Codex task after changing the provider or agent definitions.
Use
Invoke the skill with an objective:
$fable build the feature
Fable returns a bounded graph. Codex validates the graph, starts ready workers in parallel when useful, collects their evidence, verifies the result, and asks Fable to adjudicate when the task needs another decision. Every implementation node must use GPT-5.6 Luna or DeepSeek V4 Flash. If neither allowed OpenCode Go route is callable, the workflow reports the blocker instead of inventing a model.
Test
Run the repository's dependency-light checks:
tests/test_skill.sh
The test checks shell syntax, the copied source files, required routing strings, basic YAML structure, optional xmllint XML validation, SVG safety constraints, a temporary-home dry run, an idempotent copy, and common credential-shaped strings. It does not require PyYAML or a live Claude login.
License
MIT. See LICENSE.
// HOW IT'S BUILT
KEY FILES