Gemini Notebook (formerly Google NotebookLM) MCP Server & CLI - Provides programmatic access to Gemini Notebook (notebook.google.com) via both a Model Context Protocol server and a comprehensive command-line interface. Tested with personal/free tier accounts. May work with Google Workspace accounts but has not been tested. Python requirement: >=3.11 You only need to provide COOKIES! The CSRF token and session ID are now automatically extracted when needed. Option A - Fast (Recommended): Extract CSRF token and session ID directly from network…
This CLAUDE.md is for local development only. End users install via: Once installed as a plugin, skills/hooks/agents work natively without this file. When the user types any of these commands, read the corresponding SKILL.md file and follow its instructions exactly: Important: Do NOT use the Skill tool. Read the file with the Read tool and execute its instructions directly. Bundled agents live in src/ouroboros/agents/. When a skill references an agent (e.g., ouroboros:socratic-interviewer), read its definition from src/ouroboros/agents/{name}.md and adopt that…
Last Updated: Sun Jul 12 00:25:00 CST 2026 Root > templates Template system module providing multilingual configuration templates, AI personality styles, and workflow skill definitions for both Claude Code and Codex environments. Supports Chinese (zh-CN) and English (en) locales with comprehensive workflow coverage.
Last Updated: Mon Oct 27 19:39:26 CST 2025 Root > tests Test suite module providing comprehensive test coverage for the ZCF project, including unit tests, integration tests, edge tests, and template validation tests.
This repository is the comprehensive documentation for Claude Code (Anthropic's CLI tool). It teaches users how to use Claude Code effectively through guides, examples, and templates. Meta-note: This repo documents…
The TypeScript OpenPencil has been retired. apps/web, apps/desktop, apps/cli, and the pen-* packages (pen-types/core/engine/renderer/figma/mcp/ai-skills/sdk/react/acp) are gone. The product is now implemented in Rust (crates/) with a thin wasm-backed web SDK (packages/op-web-sdk). Historical // ported from pen- comments in the Rust sources name the retired TS as their origin — that code no longer exists in-tree; consult git history (last TS tag v0.7.5) if you need it. Detailed module docs load automatically in subdirectories: Tooling is Cargo (Rust — the product).…
Native + web editor chrome implemented in Rust against jian-skia. This is the canonical OpenPencil implementation — the original TypeScript editor (apps/web, apps/desktop, apps/cli, pen-) has been *retired*, so the Rust shell is the product, not a parity port. // ported from pen- comments below name the retired TS as historical origin; that code lives only in git history now. Phase 7.3 reorg — read before trusting paths below. The old openpencil-shell-* crates were dissolved/renamed; deeper sections in this doc…
The web SDK packages that remain after the TypeScript retirement. This directory is the npm/Bun workspace root (packages/package.json); the repository root is a pure Cargo workspace with no package.json. The pen-* packages (pen-types, pen-core, pen-engine, pen-renderer, pen-figma, pen-mcp, pen-ai-skills, pen-sdk, pen-react, pen-acp) and pen-codegen were retired along with apps/. Their functionality now lives in the Rust crates/ (see crates/CLAUDE.md). Nothing here depends on them. The agent-native Zig runtime was also *removed** — the built-in agent runtime is now the Rust…
CCG's multi-model role matrix as a DeepSeek Harness plugin. Lives in the ccg-workflow repo and ships inside its npm package. One repo, one package, one version number: dsh-ccg/ is on ccg-workflow's files list, and ccg dsh install copies it to ~/.dsh/ccg/dsh-ccg and wires it into a harness profile. Publishing it standalone is a decision that was deliberately left one line away — .github/workflows/publish-dsh-ccg.yml is complete and reduced to manual dispatch; see the repo's CLAUDE.md for how to flip it back.
AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 3경로 하네스. 번역투·영어 인용 과다·기계적 병렬·관용구·피동태 남용·접속사 남발·리듬 균일성·이모지/불릿 과다 등 10대 카테고리 85개 AI 티 패턴(A-17 hold 1건 포함)을 탐지·분류해 내용은 한 글자도 건드리지 않고 문체·리듬·표현만 재작성한다. v2.2부터 shim이 정량 점수로 산출하는 **route_hint(light | standard | heavy)** 가 디폴트 경로를 정한다(사용자 명시가 오버라이드). 글의 상태가 콜 수를 정하는 구조로, 구 "fast 1콜 / 정밀 3콜" 이분법을 대체한다. v2.3부터 verifygates.py가 문자율·진단 목표달성·대구 전멸·golden/수치의 4축을 검증한다. Codex도 같은 routehint와 결정적 게이트를 사용해…
This project uses Ultracite, a zero-config Biome preset that enforces strict code quality standards through automated formatting and linting. Biome (the underlying engine) provides extremely fast Rust-based linting and formatting.…
When available, first read: ~/.claude/skills/expression-skill/SKILL.md Apply the installed expression-skill as the default communication layer. Before answering any non-trivial user request, use it to shape the response: Claude Scholar is a semi-automated research assistant for academic research and software development. Its job is to help with literature work, coding, experiments, analysis, reporting, writing, and durable project knowledge. It does not replace the researcher's judgment. Keep human decisions at the center. Produce artifacts that the user can reuse directly: plans, notes, experiment…
Core conventions live here; topic-specific rules are in .claude/rules/ (loaded automatically): schema-driven-panels.md, translation.md, dialog-design.md, webview-patterns.md. Reference material that is not a rule lives in docs/ (e.g. docs/architecture.md for the main…
Mirror notice. Source for generated AGENTS.md. Edit this file, then run make generate-agent-guides; CI rejects drift. Root guide for AI agents in the router/ subproject. Covers cross-cutting design + the layer model. First read for any task: README, then this file. Then read the CLAUDE.md inside the package you're editing — each subpackage has its own with focused recipes + invariants. Three concentric layers. Imports flow inward only.
Mirror notice. Source for generated AGENTS.md. Edit this file, then run make generate-agent-guides; CI rejects drift. Composition root. Only place that constructs concrete adapters + wires them together. Read root CLAUDE.md first. ROUTERDEPLOYMENTMODE is read at boot: Provider registration: Single source of truth for provider→env-var mapping = providers.APIKeyEnvVars in ../internal/providers/provider.go. Admin /config view reads it so it can't drift from actual wiring.
Mirror notice. Source for generated AGENTS.md. Edit this file, then run make generate-agent-guides; CI rejects drift. Migrations + SQLC query sources. Read root CLAUDE.md first. Adapter that consumes these lives in ../internal/postgres — see its CLAUDE.md. After touching anything in queries/, run make generate and commit the regenerated ../internal/sqlc/ alongside the query change. CI fails if generated code drifts from sources.
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
jacob-bdCLAUDE.md
