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.
lovesegfaultDeletes or force-pushesCLAUDE.mdlovesegfault/rio-build/CLAUDE.md
design Render with `/nixbuild .#docs` (native typst HTML bundle + pagefind, `result/index.html`) or `/nixbuild .#docs-pdf` (stitched PDF). Dev loop: `typst watch --features bundle,html --format bundle --root docs --input
iurykriegerCLAUDE.mdiurykrieger/claude-bedrock/CLAUDE.md
GitHub repositories, remote URLs, and any file format supported by docling — DOCX, PPTX, XLSX, PDF, HTML, EPUB, images, and more) — extracts entities — delegates to `/bedrock:preserve` | | `/bedrock:preserve` | Single write
sderosiauxCLAUDE.mdsderosiaux/chrome-agent/CLAUDE.md
goto, click, dblclick, fill, inspect, eval, text, read, extract, diff, network, console, wait, screenshot, pdf, download, download_click, tabs, frame, batch, assert, assert_args, record, history, webmcp. `select`/`check`/`upload
ShipWithAIReads credentialsCLAUDE.mdShipWithAI/claude-code-mastery/CLAUDE.md
prefer Mermaid (renders everywhere). Fallback to ASCII art - Max line width: 100 characters (for PDF rendering) ### Length Guidelines - Module total: **800-1500 words** (sweet spot for 20-40 min reading
IlyaGusevReads credentialsCLAUDE.mdIlyaGusev/academia_mcp/CLAUDE.md
citation graphs - Hugging Face datasets search - Web search and page crawling - LaTeX compilation and PDF reading - LLM-powered document QA and research proposal workflows **Tech Stack:** - Python 3.12+ with type
capitalparserCLAUDE.mdcapitalparser/notebooklm-wiki-pipeline/CLAUDE.md
Obsidian 노트로 자동 변환하는 토큰-효율 파이프라인. ## 핵심 문제 Drive MCP로 PDF를 직접 읽으면 PDF 전체 텍스트가 Claude 컨텍스트를 지나가 토큰 소모가 과다. NotebookLM이 내부에서 PDF를 처리하고 Claude는 분석 결과
wiseria-ai-labsCLAUDE.mdwiseria-ai-labs/pie-ai-agent/CLAUDE.md
read/write tool 分类) - `src/lib/agent/tools/` — `keyboard.ts` (CDP) / `skill-meta.ts` (skill CRUD) / `tabs.ts` (cross-tab) / `pdf.ts` (`read_pdf` / `search_pdf` / `get_pdf_outline` tools, all read-class) - `src/lib/pdf/` — PDF tab detection (`isPdfTab`) + page
zcagReads credentialsCLAUDE.mdzcag/tela/CLAUDE.md
module scripts. That is exactly how pdf.js ships its worker (`pdf.worker.min-*.mjs`), so every PDF preview ran without one in production while vite's dev server typed it correctly — invisible
54xzhCLAUDE.md54xzh/LastChat/CLAUDE.md
Brave, Firecrawl, BochaAI, etc.) - `tts/` - Text-to-Speech (SystemTTS, OpenAI, Gemini, ElevenLabs, MiniMax) - `document/` - PDF and DOCX parsing ### Key Wiring (DI) Koin modules in `app/src/main/java/me/rerere/rikkahub/di/`: - **AppModule** - Singletons: `ChatService`, `TemplateTransformer`, `TTSManager
laurent512CLAUDE.mdlaurent512/opencalque/CLAUDE.md
entries, `listedAsModel`). Do not show the user the difference again. - Exports (SVG, DXF, PDF) draw from primitives through `paintOrder`; a new kind of primitive or style needs handling in `svg.ts
ForceInjectionCLAUDE.mdForceInjection/awesome-skills/CLAUDE.md
directories use **noun/doer form** in kebab-case: `agent-skill-reviewer` not `agent-skill-review`, `pdf-translator` not `translate-pdf`. - This aligns with skills being "personified" agent roles. ### Key design principle
agammCLAUDE.mdagamm/batchata/CLAUDE.md
python -m examples.spam_detection` - Run example - `bachata-example` - Run spam detection example - `bachata-pdf-example` - Run PDF extraction example ## Documentation - Generate docs on each version ```bash uv run pdoc
NameetPCLAUDE.mdNameetP/pdfmux/CLAUDE.md
pdfmux — Agent Instructions ## Project PDF extraction that checks its own work. Multi-pass pipeline: fast extract → audit → selective OCR → merge. - **Language**: Python 3.11+ - **Build**: hatchling (pyproject.toml) - **Lint**: ruff - **Test**: pytest
timothywarner-orgReads credentialsCLAUDE.mdtimothywarner-org/claude-architect/CLAUDE.md
that script generates a smaller scaffold cut and would overwrite the shipped file). No PDF is committed; export fresh from the `.pptx` if a cohort needs one. - `images/social-preview.png` - the GitHub
Circuit-OvertimeCLAUDE.mdCircuit-Overtime/elixpo_chapter/sketch.elixpo/CLAUDE.md
Features (from project files) - Save/load sketches (localStorage/IndexedDB/server) - Real-time collaboration (WebSocket) - Export (PNG, SVG, PDF) - Zen/focus mode - Command palette / help system - Canvas lock - Text-to-diagram conversion - Shape properties panel
fabio-rovaiCLAUDE.mdfabio-rovai/brain-in-the-fish/CLAUDE.md
ontologies` as a dependency. ## Module Overview | Module | Purpose | |------------------|--------------------------------------------------------------| | `types` | Core evaluation domain types | | `ingest` | PDF ingestion and document ontology generation | | `criteria` | Evaluation criteria ontology loading/generation | | `agent` | Agent cognitive model
LambenthanReads credentialsCLAUDE.mdLambenthan/empiricalwiki/CLAUDE.md
原语、命题/定理、解概念、可检验推论，再写通用概念或 idea。形式化陈述逐字引用，禁止释义改写成立条件。 - **双向链接**：写正向链接时同步写反向链接。 - **tex 优先**：.tex > .pdf，fallback 链：tex 失败 → PDF 解析，PDF 失败 → vision API。 - **index.md 每次 ingest 立即更新**，log.md
selfishprimateCLAUDE.mdselfishprimate/seekter/CLAUDE.md
receive, printed from the master in `resume/json/resume.json`), `documents/` (files the candidate brings: a resume PDF when there is no `resume.json`, a portfolio PDF, cover letters), `interviews/` (the story bank
shorin-nikitaReads credentialsCLAUDE.mdshorin-nikita/lisa/CLAUDE.md
автозагрузкой файлов: - File trigger на `/data/shared` — автоматическая индексация новых файлов - Поддержка CSV, Excel, TXT, PDF - pgvector для векторного поиска, SQL для табличных данных - Оптимизированные настройки: `chunkSize=1000`, `chunkOverlap=100` - **Telegram
jananthan30CLAUDE.mdjananthan30/Resume-Builder/CLAUDE.md
system's behaviour. ## Project Structure ``` Resume Builder/ ├── {master_resume from config.json} # Master resume (DOCX, PDF, or Markdown) ├── SUPPLEMENTAL_EXPERIENCE.md # Selective-use experience entries (NOT in master resume) ├── evidence_match.py # Evidence match
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.
