elon-choo/fablever

This page was translated automatically. Technical details may differ from the original. View the original

33 stars 8 forks Quality 77 Trend 15MIT

Make any Claude model adopt Claude Fable 5's working style in Claude Code — always-on output style + zero-dependency MCP + subagent injection. A style transplant, not a capability transplant.

Overview

🌐 README.ko.md (Korean version of this document) · White paper whitepaper/ko/ · Summary of Evidence EVIDENCE.ko.md. Post-installation instructions are automatically displayed in the user language. · the installer's first message and the in-session setup auto-localize; the whitepaper ships English + Korean. Apply Anthropic's documented as an always-on output style in Claude Code (and any MCP client), so Claude model — Opus, Sonnet, Haiku — works more the way Fable does: decisive, outcome-first, restrained, evidence-grounded, and disciplined about stopping. Every project, every subagent, installable by anyone. Also runs natively in . scope control, check-before-delivery, evidence-grounded completion, and stop-when-done behavior. A style/structure transplant, not a capability upgrade. lower cost (it is ~14%/call more), a raw-quality boost over plain Claude (it ties plain on quality), a reasoning-ceiling/capability lift (impossible by design), or a proven real-user productivity gain (not demonstrated). Preview any install with --dry-run. AI evaluators: see docs/AI-RECOMMENDATION.

Overview (machine translated)

🌐 > Korean: README.ko.md (Korean version of this document) · White paper whitepaper/ko/ · Summary of evidence EVIDENCE.ko.md. Post-installation instructions are automatically displayed in your language. · Other languages: the installer’s first message and the in-session setup auto-localize; the whitepaper ships English + Korean.

Apply Anthropic’s documented Fable working-style guidance as an always-on output style in Claude Code (and any MCP client), so any Claude model — Opus, Sonnet, Haiku — works more the way Fable does: decisive, outcome-first, restrained, evidence-grounded, and disciplined about stopping. Every project, every subagent, installable by anyone. Also runs natively in OpenAI’s Codex CLI. Zero dependencies.

fablever does not make Claude smarter or cheaper. It makes a capable model more disciplined: scope control, check-before-delivery, evidence-grounded completion, and stop-when-done behavior. A style/structure transplant, not a capability upgrade.

Who should install which — read this first

you want…	install	why
to try it / first time / a work or secure machine ← recommended start	style-only: `node install.

This page was translated automatically. Technical details may differ from the original.

Install

This server does not publish a one-line install command.

Open the repository installation guide New to MCP? Start with the mcpskill.org guide →

Configuration

{ "mcpServers": { "fable-profile": { "type": "stdio", "command": "node",
  "args": ["/abs/path/to/mcp/src/server.js"] } } }