Is the Fable God Mode skill free?

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

What is the Fable God Mode SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Fable God 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 God 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 God Mode

10-80-10 delegation discipline: expensive model plans and reviews, cheap subagents do the verbose middle.

by nagarjuna-msr · nagarjuna-msr/fable-god-mode

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 87736f6

The v0.2.0 bump landed after our test but adds only discipline rules — name every subagent's model explicitly, recompute claimed numbers from disk, falsify new checks before trusting them, own the clock on long or paid jobs, and take two isolated takes on open decisions. We re-checked the audit reference and every safety property we praised is intact: never-delete archive-only remediation, per-item consent, a SHA-256 manifest, one-prompt restore, and diff-plus-approval before any CLAUDE.md or settings.json edit. The v0.2.0 probe-mode and release-gate churn went to the sibling fable-super-god-mode, not this skill. The verbatim install works from a bare HOME and Stage 0 is clean, so the pass holds.

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 5/5

What Fable God Mode does

A token-cost discipline for multi-step coding/research sessions: the premium model plans (first 10%) and reviews/integrates (last 10%), while Haiku/Sonnet/Opus subagents execute the verbose middle 80% and return compact summaries. Also offers a report-only, reversible stale-config audit for CLAUDE.md/skills bloat. Triggers on multi-step tasks, delegation/orchestration requests, token-cost complaints, or config-cleanup requests.

How to install Fable God Mode

git clone https://github.com/nagarjuna-msr/fable-god-mode
cd fable-god-mode
mkdir -p ~/.claude/skills
cp -r skills/fable-god-mode ~/.claude/skills/fable-god-mode

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

Commands — how to trigger Fable God Mode

/fable-god-mode 10-80-10 delegation discipline: expensive model plans and reviews, cheap subagents do the verbose middle.

It also activates on plain-language prompts like these:

Plan out adding rate limiting to our Flask API on a tight token budget
This session is burning tokens fast, can we delegate more of the work?
Audit my CLAUDE.md and skills folder for stale bloat, don't delete anything

Frequently asked questions

Is the Fable God Mode skill free?: Yes. The skill itself is free from nagarjuna-msr/fable-god-mode. SkillProof publishes the install command and an independent test verdict at no cost.
Does Fable God Mode work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. The v0.2.0 bump landed after our test but adds only discipline rules — name every subagent's model explicitly, recompute claimed numbers from disk, falsify new checks before trusting them, own the clock on long or paid jobs, and take two isolated takes on open decisions. We re-checked the audit reference and every safety property we praised is intact: never-delete archive-only remediation, per-item consent, a SHA-256 manifest, one-prompt restore, and diff-plus-approval before any CLAUDE.md or settings.json edit. The v0.2.0 probe-mode and release-gate churn went to the sibling fable-super-god-mode, not this skill. The verbatim install works from a bare HOME and Stage 0 is clean, so the pass holds.
What is the Fable God Mode SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Fable God 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 God 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.