Is the Fable Mode skill free?

Yes. The skill itself is free from Nam-Cheol/codex-fable-mode. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Fable Mode SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Fable Mode?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Fable Mode with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Fable Mode

Explicit intent-locking routing mode: caps depth, tools, and delegation per task before acting.

by Nam-Cheol · Nam-Cheol/codex-fable-mode

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 77cc242

A pure-documentation behavioral skill (no scripts, no network calls) that makes its effect visible: following it strictly produces a literal 'Fable route: Lock=... Layer=... Procedure=... Tool=... Grounding=... Delegation=...' contract line and a forced codebase-grounding check before implementing, both of which the unguided baseline skipped.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Fable Mode does

A documentation-only routing skill that, on explicit invocation ($fable-mode), locks the output type (answer/edit/implementation/review/audit/design/research/etc), picks the smallest sufficient reasoning depth, and caps procedure/tool/delegation budgets before work starts, exposing a compact visible route line for larger tasks. Trigger only on explicit '$fable-mode' or 'fable-mode style routing' requests — it deliberately stays out of ordinary simple tasks.

How to install Fable Mode

git clone https://github.com/Nam-Cheol/codex-fable-mode
mkdir -p ~/.claude/skills
cp -r codex-fable-mode/plugins/fable-mode/skills/fable-mode ~/.claude/skills/fable-mode

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Fable Mode

/fable-mode Explicit intent-locking routing mode: caps depth, tools, and delegation per task before acting.

It also activates on plain-language prompts like these:

$fable-mode: implement this feature with minimal reasoning depth
Use fable-mode style routing before you touch any of this code
Lock the intent to review mode before we start on this task

Frequently asked questions

Is the Fable Mode skill free?: Yes. The skill itself is free from Nam-Cheol/codex-fable-mode. SkillProof publishes the install command and an independent test verdict at no cost.
Does Fable Mode work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. A pure-documentation behavioral skill (no scripts, no network calls) that makes its effect visible: following it strictly produces a literal 'Fable route: Lock=... Layer=... Procedure=... Tool=... Grounding=... Delegation=...' contract line and a forced codebase-grounding check before implementing, both of which the unguided baseline skipped.
What is the Fable Mode SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Fable Mode?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Fable Mode with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.