蒸餾李宏毅老師的skill，結合Karpathy的LLM，Fable 5加持 以及 本人親自訪談
-
Updated
Jun 17, 2026 - HTML
#
fable5
Here are 35 public repositories matching this topic...
Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, model ceiling, per-task enforcement) for Fable-5-grade discipline: plan, self-verify, and route sub-agents, without Fable 5.
developer-tools opus ai-agents claude llm prompt-engineering anthropic agentic ai-coding agent-orchestration claude-code coding-agent subagents agent-hooks claude-skills claude-fable-5 fable-5 fable5
-
Updated
Jul 15, 2026 - Python
Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.
tokens developer-tools ai-agents claude cost-optimization llm cost-reduction anthropic claude-ai claude-opus claude-sonnet claude-code token-optimization claude-code-plugin claude-skills claude-fable-5 fable-5 fable5
-
Updated
Jul 2, 2026 - JavaScript
Proactive 5h usage guard for Claude Code (macOS). Pause before extra wallet on long batch/subagent runs. Account-level window visibility. /usage-guard skill + daemon. Not affiliated with Anthropic.
macos workflow automation skills fable opus claude anthropic claude-desktop agentic-ai claude-code claude-skills skill-md usage-limits usage-limits-watcher fable-5 fable5
-
Updated
Jul 2, 2026 - Python
AI reasoning skills distilled from 4,665 real Claude Fable 5 chain-of-thought traces. Mathematically tuned. Grade A (100%) emulation accuracy against MiniMax M3.
ai cursor minimax reasoning claude cot llm prompt-engineering chain-of-thought anthropic agent-skills claude-code coding-agent skill-md fable-5 fable5
-
Updated
Jun 16, 2026 - JavaScript
oh-my-fable — Fable 5's way of working a long task (plan first, self-correct, never lose the thread), as a model-agnostic agent harness. The run lives in one serializable RunContext, checkpointed every step, so a crash is a pause. Zero deps, deterministically testable.
agent reflection typescript planner checkpoint zero-dependency resumable reasoning mindset model-agnostic crash-recovery agent-framework self-correcting autonomous-agent ai-agent llm anthropic plan-and-execute fable-5 fable5
-
Updated
Jul 8, 2026 - TypeScript
Reverse-engineer the RL reward an LLM was trained on — from black-box agentic coding behavior alone. Tested on Opus 4.8, Fable 5, GPT-5.5.
benchmark machine-learning reinforcement-learning gpt inverse-reinforcement-learning interpretability ai-agents claude ai-alignment large-language-models llm rlhf mechanistic-interpretability llm-evaluation coding-agents agentic-ai reward-modeling swe-bench reward-hacking fable5
-
Updated
Jul 10, 2026 - Python
Fable 5가 먹은 토큰 사용량에 충격 먹은 사람이 GPT-5.5로 깎아 만든 Opus 4.8 용 CLAUDE.md.
-
Updated
Jun 13, 2026
Research analyst powered by Claude Code. Upload your research materials, run AI agents across industries, find real problems backed by primary sources. Full-stack React dashboard, fully customizable.
react python research ai knowledge-management ai-agents claude vite fastapi llm prompt-engineering research-automation anthropic claude-code sub-agents fable5
-
Updated
Jun 30, 2026 - JavaScript
Host-adaptive Rust MCP code-intelligence router with cached hybrid retrieval, index-health visibility, mutation gates, and token-lean workflows for Codex, Claude, and generic MCP clients
rust tree-sitter fable mcp developer-tools cursor semantic-search harness codex lsp code-intelligence ai-tools mcp-server claude-code token-optimization agent-harness harness-engineering fable5
-
Updated
Jul 12, 2026 - Rust
Access Claude Code and Fable 5 through this open source cross-platform desktop client.
claude-alternative claude-code- claude-code-themes claude-desktop-extentions github-claude-code claude-code-tasks everything-claude-code claude-desktop-app claude-code-source-code claude-design-free claude-code-free-helper claude-fable fable5
-
Updated
Jul 15, 2026 - C#
A pretty, playable, web-based 3D Flappy Bird game built by Claude Fable 5.
-
Updated
Jun 12, 2026 - HTML
Zero-dependency watcher that notifies you the moment Claude Fable 5 is reachable again in Claude Code (Telegram/Discord/ntfy/desktop). MIT.
notifications python cli monitoring telegram availability-monitor claude ntfy local-first anthropic claude-code model-watcher fable-5 fable5
-
Updated
Jun 25, 2026 - Python
OpenAI Codex plugin for evidence-first AI code review, audits, fact checks, ECF run contracts, and subagent workflows.
audit developer-tools code-review software-engineering fact-checking codex ecf fact-check openai-codex ai-code-review agent-skills subagents codex-plugin fable5
-
Updated
Jul 14, 2026 - PowerShell
Fable5-like evidence-first Codex skill for agent workflows, verification-first delivery, adversarial review, and portable prompts.
codex ai-agents evidence-based prompt-engineering agent-skills codex-skills adversarial-review skills-cli npx-skills verification-first fable5 portable-prompts
-
Updated
Jul 15, 2026
🎙️ Practice interviews against an AI that adapts in real time. Drop in any JD + resume → voice-only mock interview → per-answer scoring → personalized 4-week improvement plan. Autonomous agentic loop on Claude Agent SDK with a full eval harness. Open source, config-driven, one-command start.
-
Updated
Jul 9, 2026 - Python
Improve this page
Add a description, image, and links to the fable5 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the fable5 topic, visit your repo's landing page and select "manage topics."