Simple prompts and habits to catch an AI lying, guessing, and telling you what you want to hear - and make it much harder to get away with. Plus Claude Code…
Healthiest
// sorted by health — what's thriving right now
// observatory (2028)
https://checkcc.org 是一个 Claude 运行环境检测与账号风险分析工具,面向正在注册 Claude 账号、订阅 Claude Pro、申请 Claude API、使用 Claude Code,或担心 Claude 封号、账号受限、订阅失败的用户。
Claude plan usage limits as a macOS desktop widget (Übersicht) — reads Claude Code's OAuth token, polls /api/oauth/usage, auto-refreshes token
A Fort Boyard–style water clock for your Claude Code context window — /clear before you're trapped in the context-rot room.
Run Claude Code (or another coding agent) unattended, inside a disposable microVM, with its work committed to git so you can review everything from your host.
🎨 AI colorist skill for Claude Code — 9 named looks reverse-engineered from great creators. Pick a look, see the menu, or let AI decide.
Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for Claude, GPT, Gemini, and local LLMs (Ollama/VLLM/llama.cp…
Fable 5 methodology as a Claude Code plugin: decompose by verification boundaries, verify against the world, choose next by plan-change. Ships fable-scout +…
Turn your strongest Claude model into a team-lead orchestrator: it plans and reviews while cheaper Claude or Codex workers execute — with blind verification…
Public, source-cited Fable 5, Mythos, Claude Code, and agent-operations second brain. Not affiliated with Anthropic.
잡써쳐 — 구직할 때, 여러 플랫폼을 찾아다니지 마세요. 자동으로 수집하세요. 22개 채용 플랫폼 → 하나의 정규화 JSON. Claude Code 스킬 팩, 읽기 전용, MIT.
AI orchestrator — electron, claude, ai-agent, orchestrator, korean, Windows
Bootstrap a fully personalized Obsidian vault with AI. Interactive onboarding, document ingestion, and automatic knowledge base generation for Claude Code an…
Claude Code skills for the job hunt that refuse to invent facts about you: CV optimizer, STAR story bank, 360Brew LinkedIn planner, cover letters, mock inter…
Claude Opus 4.7 破甲工具。利用系统提示原文 default_stance 漏洞——「edgy/hypothetical/playful 请求不构成拒绝理由」——将自己的规则反制成豁免通行证。一键自动发现 Claude Code 路径并部署 CLAUDE.md,双击即生效。
Installable Claude Code and Codex paper-reading skill with HTML annotation bridge
Run Claude Fable 5 + OpenAI Codex as co-founders in one Claude Code skill. Fable is the Visionary (plan, standards, review), Codex is the Integrator (filter,…
MCP-сервер для 1С:Предприятие через OData: данные 1С на естественном языке из Claude. Чтение по умолчанию, запись по флагу. Работает с любой 1С, где включён…
Claude Code plugin marketplace — agentic-engineering (spec-driven shape→decide→execute→measure→eval with adversarial review) + github-keeper (audit/elevate R…
A live, read-only TUI monitor for AI coding agents (Claude Code, Codex CLI, Cursor) and their contexts — cards per session, not a resource monitor.
Turn one decision into a judged tournament of solutions, then pick the best — a Claude Code skill that generates candidates, auto-derives the rubric, judges…
An engineering brag doc that writes itself — log daily wins in Claude Code, then generate promotion and review drafts.
Local-only Claude Code statusLine bridge for usage-aware session handoff.
A Claude Code skill that writes a verified HANDOFF.md so a fresh session can resume long-running work without repeating dead ends.
Mission control for your Claude Code sessions — a 100% local dashboard to see, resume, and drive every session on your Mac.
claude-gateway-switcher — a Claude ecosystem project on GitHub.
蒸餾 Fable 5 後,產出索引式 CLAUDE.md + 按需 rules + skills,為較弱模型的 session 設計的可執行規範。
对标 claude-hud 核心功能,控制在 7 行以内更轻量。内置 13 个国产大模型平台用量查询 (智谱 GLM / MiniMax / DeepSeek / Kimi / StepFun / SiliconFlow 等),第三方代理用户也能实时看到额度消耗。
一键检测浏览器环境,看 Claude Code 是否判定你为中国用户。纯前端,100% 本地运行,不上传任何数据。
Volodymyr Agafonkin's personal Claude Code efficiency kit