stripe-python
stripe/stripe-python/.claude/CLAUDE.md
format` calls to use f-strings. ### Comments - Comments MUST only be used to: 1. Document a function 2. Explain the WHY of a piece of code 3. Explain a particularly
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
stripe/stripe-python/.claude/CLAUDE.md
format` calls to use f-strings. ### Comments - Comments MUST only be used to: 1. Document a function 2. Explain the WHY of a piece of code 3. Explain a particularly
vercel-labs/lat.md/CLAUDE.md
search "natural language" # semantic search across all sections lat check # run full graph and documentation validation ``` Run `lat --help` when in doubt about available commands or options. If `lat search
deusyu/translate-book/CLAUDE.md
skip logic is intentionally simple (existence check). Metadata/template changes require manual cleanup. This is documented in the README
microsoft/PowerApps-Samples/CLAUDE.md
Sample files and images used across multiple samples - **component-framework/resources/**: PCF control templates ## Documentation Links - [Power Apps Component Framework docs](https://learn.microsoft.com/power-apps/developer/component-framework/overview) - [Dataverse developer docs](https://learn.microsoft.com/power-apps/developer/data-platform/)
doobidoo/mcp-memory-service/CLAUDE.md
never tags** (see "Source Control & Hosting"). 2. **Never manually bump versions.** Follow the documented release workflow for every version bump and release. 3. **Run `bash scripts/pr/pre_pr_check.sh` before every
WorldFlowAI/everything-claude-code/examples/CLAUDE.md
feature/domain, not by type ### 2. Code Style - No emojis in code, comments, or documentation - Immutability always - never mutate objects or arrays - No console.log in production code - Proper error handling with
eneskirca/nodeterm/CLAUDE.md
# CLAUDE.md This is the deep-reference for working in this repo: the invariants, why
vstorm-co/full-stack-ai-agent-template/CLAUDE.md
backends: Milvus, Qdrant, ChromaDB, pgvector - 4 embedding providers: OpenAI, Voyage, Gemini (multimodal), SentenceTransformers - RAG document sources: local files (CLI), Google Drive, S3/MinIO - Document ingestion via CLI and API upload - Sync
zzet/gortex/CLAUDE.md
review itself. - **Multimodal + broad ingest** — image files (`KindImage` assets with format/dimensions/sha256) and PDF documents (per-page searchable `KindDoc` nodes) are graph nodes; new first-class extractors cover Terraform/HCL cross-block
nimbalyst/nimbalyst/CLAUDE.md
shared database.** Customer data (team metadata, member roles, key envelopes, tracker items, documents, sessions) must live in Durable Objects where each entity gets its own isolated SQLite instance
supabase/postgres/CLAUDE.md
project is mid-migration from a pure Dockerfile-based extension build (what `CONTRIBUTING.md` still documents) to a Nix-based one (what `README.md` and `nix/docs/` describe as current). When
standardagents/dmux/.dmux-hooks/CLAUDE.md
dmux Hooks System - Agent Reference **Auto-generated documentation for AI agents** This document contains everything an AI agent needs to create, modify, and understand dmux hooks. It is automatically generated
happier-dev/happier/.claude/CLAUDE.md
root constitution and repository skills rather than copying a private operating manual. Plan-local documents contain only product decisions, seam ownership, acceptance criteria, and evidence specific to that program
microsoft/rnx-kit/incubator/fork-sync/CLAUDE.md
modules have a Microsoft copyright header followed by a JSDoc module comment 2. **Module documentation**: Include a comprehensive JSDoc block with: - One-line description - "This module provides:" section listing
relaticle/relaticle/CLAUDE.md
assistant answering "that field isn't supported" is a bug, not a limitation to document. - Every tool registered on `CrmAssistant` needs a label in the `toolLabels` map (`packages/Chat/resources/views/livewire/chat/chat-interface.blade.php
lahfir/agent-desktop/CLAUDE.md
version bump) - `feat!:` or `BREAKING CHANGE:` footer — breaking change (triggers major version bump) - `docs:` — documentation only - `style:` — formatting, no code change - `refactor:` — code change that neither fixes
skyllwt/AutoSci/CLAUDE.md
repo state. If the user omitted one, use a default only when the skill documents omission behavior; otherwise ask. ## Where to look | Need | Source | |---|---| | Page frontmatter fields, enums, defaults, lifecycle
lst97/claude-code-sub-agents/CLAUDE.md
Break work into 3–5 cross-stack stages (front-end, back-end, database, integration). Document in `IMPLEMENTATION_PLAN.md`: ```markdown ## Stage N: [Name] **Goal**: [Specific deliverable across the stack] **Success Criteria**: [User
manzaltu/claude-code-ide.el/CLAUDE.md
this file that are incorrect, outdated, or could be improved, you should update this document immediately. Keep this file accurate and helpful for future Claude instances. ## Architecture and File Structure
Lynpoint/CyberVerse/claude.md
user claim, assumption, diagnosis, or plan as unverified until checked against evidence, logic, code, documentation, or constraints. - Correctness comes before agreement. Default Behavior: - Do not say “yes,” “correct,” “exactly
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.