How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
vstorm-coCLAUDE.mdvstorm-co/full-stack-ai-agent-template/CLAUDE.md
upload - Sync sources: configurable connectors (Google Drive, S3) with scheduled sync - 3 PDF parsers: PyMuPDF, LiteParse, LlamaParse (runtime selection via env var) - Image description via LLM vision API (optional
trailofbitsCLAUDE.mdtrailofbits/publications/CLAUDE.md
Announcement links should point to company announcements about the audit, not to the audit PDF itself ### Presentation Directory Standards #### Directory naming - Directory name should be the **talk title only
No other project uses it yet
qcadCLAUDE.mdqcad/qcad/CLAUDE.md
Main window, graphics views, custom Qt widgets - `io` — File I/O (DXF, DWG, PDF, SVG) - `scripting` — ECMAScript execution engine (Qt Script / QJSEngine) - `snap` — Snap logic - `spatialindex` — Spatial index for entity lookup
Steady3 mentions in 2 weeks
No other project uses it yet
meganzCLAUDE.mdmeganz/android/navigation/CLAUDE.md
catalog of concrete destinations** (the `NavKey`s for cloud drive, auth, settings, transfers, media, PDF, device center, etc.). Most interfaces here are implemented in the `:app` module; this module intentionally
LibPDF-jsCLAUDE.mdLibPDF-js/core/CLAUDE.md
tests later" is not acceptable. ## Project Overview **@libpdf/core** is a modern PDF library for TypeScript focused on both parsing and generation. It aims to combine the robust parsing of Mozilla
Steady6 mentions in 2 weeks
No other project uses it yet
qusong0627Reads credentialsCLAUDE.mdqusong0627/QuantMind/CLAUDE.md
backend/services/engine/routers/alpha_agent.py` - Alpha Agent API（含 /markets、带 market 参数的 /evolve） - `backend/services/engine/routers/report_archive.py` - 报告归档 API（files/list、pdf、upload、move、delete、文件夹） - `scripts/alpha_agent/run_rd_agent.py` - RD-Agent 多市场运行脚本（子进程入口） - `backend/services/engine/data_platform/` - 多市场数据平台 - `backend/services/engine/data_platform/quantdb_hub.py` - QuantDB 数据中枢
No other project uses it yet
KlotzketteCLAUDE.mdKlotzkette/claude-fuer-deutsches-recht/CLAUDE.md
jede Testakte gilt der unveränderte zweisprachige Hinweis aus [`AGENTS.md`](./AGENTS.md) und [`testakten/QUALITAETSSTANDARD.md`](./testakten/QUALITAETSSTANDARD.md). Gesamt-PDF und Einzel-PDFs enthalten weder eine Hinweisseite noch diesen Warntext. Stattdessen steht der vollständige Hinweis
Steady8 mentions in 2 weeks
No other project uses it yet
KlotzketteCLAUDE.mdKlotzkette/claude-fuer-deutsches-recht/vergaberecht-werkstatt/CLAUDE.md
für alle bestehenden und künftigen Testakten) Jede Testakte liegt in drei Formen vor: Gesamt-PDF, Einzel-PDFs und ein flaches Release-ZIP. Für das ZIP gilt: - **Arbeitsdateien nur DOCX, XLSX
Steady8 mentions in 2 weeks
No other project uses it yet
kotaro-kinoshitaCLAUDE.mdkotaro-kinoshita/yomitoku/CLAUDE.md
estimation** (`reading_order.py`) — DFS-based graph algorithm 5. **Export** — JSON, CSV, HTML, Markdown, or searchable PDF Each component can be used independently (e.g., `OCR` alone for text extraction). ### Key Design Patterns
joypad-aiCLAUDE.mdjoypad-ai/joypad-os/CLAUDE.md
Generated -- edit generate.py, not this └── fab/ # Orderable gerber zip, BOM, 1:1 fit-check PDF ``` Boards are generated, never hand-drawn: `generate.py` asserts the netlist against the app's wiring
hyperbrowseraiReads credentialsCLAUDE.mdhyperbrowserai/HyperAgent/CLAUDE.md
Anthropic provider | | `GEMINI_API_KEY` / `GOOGLE_API_KEY` | Gemini provider; also enables PDF action | | `DEEPSEEK_API_KEY` | DeepSeek provider | | `HYPERBROWSER_API_KEY` | Cloud browser provider | | `HYPERAGENT_TRACE_WAIT` | Enable
amdReads credentialsCLAUDE.mdamd/gaia/CLAUDE.md
lone flip before trusting it. **#1030 (the Gemma-4 RAG-PDF timeout) is the canonical example of what happens when this rule is skipped:** a prompt change passed every unit
Steady6 mentions in 2 weeks
No other project uses it yet
NanoNetsReads credentialsCLAUDE.mdNanoNets/docstrange/CLAUDE.md
chunking based on token limits - Document search and section extraction ## Dependencies ### Core Dependencies - `pdf2image`: PDF to image conversion - `python-docx`, `python-pptx`, `openpyxl`: Office formats - `beautifulsoup4`, `markdownify`: HTML/Markdown conversion - `Pillow
robocorpCLAUDE.mdrobocorp/rpaframework/CLAUDE.md
Salesforce, Browser, etc. ├── windows/ # Windows UI automation (UIAutomation, PyWinAuto) ├── assistant/ # RPA Assistant UI functionality ├── pdf/ # PDF processing ├── recognition/# Image recognition and OCR (support package) ├── aws/ # AWS cloud integration ├── google/ # Google
Open-Source-LegalCLAUDE.mdOpen-Source-Legal/OpenContracts/CLAUDE.md
reactive vars, never touch URLs directly - Deep linking and canonical redirects handled automatically 3. **PDF Annotation System** (see `.cursor/rules/pdf-viewer-and-annotator-architecture.mdc`): - **Virtualized rendering**: Only visible pages (+overscan) rendered for performance - Binary search
daymadePipes a download into a shellCLAUDE.mddaymade/claude-code-skills/CLAUDE.md
delivery identity](daymade-skill/skill-creator/references/delivery-identity.md). For a Chinese illustrated recipient guide from a manufacturer PDF, enter [docs-router](daymade-docs/docs-router/SKILL.md) and its [manual workflow](daymade-docs/pdf-creator/references/illustrated-manual.md). For relative
JakubMelkaCLAUDE.mdJakubMelka/PDF4QT/CLAUDE.md
when working with code in this repository. PDF4QT is a C++20 / Qt 6 PDF library plus a family of desktop applications (editor, viewer, page master, diff, launch
rmusser01Reads credentialsCLAUDE.mdrmusser01/tldw_server/CLAUDE.md
Project_Guidelines.md # Development philosophy ``` ## Core Features ### Implemented Features 1. **Media Ingestion & Processing** - Supports: Video, Audio, PDF, EPUB, DOCX, HTML, Markdown, XML, MediaWiki dumps - yt-dlp for video/audio downloads from 1000+ sites
Muesli-HQCLAUDE.mdMuesli-HQ/muesli/CLAUDE.md
chunking → speaker diarization → AI-powered meeting notes - **Meeting export:** Export notes or transcript as PDF (paginated US Letter) or Markdown via `MeetingExporter.swift` - **Screen context:** Accessibility API captures app name + text
Steady13 mentions in 2 weeks
1 project uses a version of this
YACReaderCLAUDE.mdYACReader/yacreader/CLAUDE.md
Build options: - `DECOMPRESSION_BACKEND`: `unarr` | `7zip` | `libarchive` (default: 7zip on Windows/macOS, libarchive on Linux) - `PDF_BACKEND`: `pdfium` | `poppler` | `pdfkit` | `no_pdf` (default: pdfium on Windows, pdfkit on macOS, poppler
No other project uses it yet
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
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 Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
