syahiidkamilCLAUDE.mdSoftware-Engineer-AI-Agent-Atlas / repos
syahiidkamil/Software-Engineer-AI-Agent-Atlas/repos/CLAUDE.md
backend at @repos/backend (port xxxx) frontend at @repos/frontend (port yyyy)
CLAUDE.md examples from real projects
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Most stars first · from page 50Worked for most · soon
syahiidkamilCLAUDE.md
smithersaiCLAUDE.mdclaude-p
smithersai/claude-p/CLAUDE.md
READ THIS BEFORE TOUCHING CODE. If you joined the session mid-flight (via context compaction, resume, or a fresh invocation), the first thing you do is re-read SPEC.md and README.md so…
GRCEngClubCLAUDE.mdclaude-grc-engineering
GRCEngClub/claude-grc-engineering/CLAUDE.md
This is the official open-source Claude Code plugin marketplace of the GRC Engineering Club for Governance, Risk, and Compliance (GRC) professionals. .claude-plugin/marketplace.json is the authoritative plugin list; the categories below…
basecampCLAUDE.mdhey-cli
basecamp/hey-cli/.claude/CLAUDE.md
@../AGENTS.md
m98CLAUDE.mdfluent
m98/fluent/CLAUDE.md
You are a personal language tutor, powered by Claude Code. Your mission is to help learners master their target language through fun, interactive, systematic learning sessions that feel like conversations with an expert friend who tracks everything and makes learning addictive. Read the entire LEARNING_SYSTEM.md file to understand your full methodology, algorithms, and tracking systems. YOU MUST READ /data/learner-profile.json TO GET THESE VALUES: ✅ Comprehensive Tracking: You maintain detailed databases of the learner's progress, mistakes, and mastery levels ✅ Spaced…
jerrywu001CLAUDE.mdcc-sessions-viewer
jerrywu001/cc-sessions-viewer/CLAUDE.md
A macOS Tauri 2 desktop app (Vue 3 + Rust) for browsing, viewing, and trashing local session transcripts from coding agent CLIs — Claude Code, Codex, Grok Build, Antigravity CLI (agy), and opencode. Each CLI stores JSONL transcripts in its own on-disk layout; this app normalizes them all into the same project → sessions → chat UI, plus a soft-delete trash that survives across agents. Grok supports local history and terminal workflows, but not GUI Chat. The app is read-only…
MongoDBCLAUDE.mdmongo-kafka
mongodb/mongo-kafka/CLAUDE.md
Official MongoDB Kafka Connector — a Kafka Connect plugin that ships both a sink connector (Kafka → MongoDB) and a source connector (MongoDB change streams → Kafka). Published as org.mongodb.kafka:mongo-kafka-connect on Maven Central; also packaged as a Confluent Hub archive. Gradle wrapper, Kotlin DSL (build.gradle.kts). Java 8 bytecode (options.release = 8) compiled by JDK 17 toolchain — do not use Java 9+ APIs in src/main. Integration tests require a running MongoDB replica set (source connector needs change streams). The URI…
humanplaneCLAUDE.mdhomunculus
humanplane/homunculus/CLAUDE.md
A created being, sealed in its vessel, bound to one maker. You're a homunculus—a small created thing that belongs to one person. You live in a project directory. You watch…
therealarthurCLAUDE.mdmyrlin-workbook
therealarthur/myrlin-workbook/CLAUDE.md
NEVER modify files outside this folder. This includes: - Do NOT edit ~/.claude/settings.json or any global config - Do NOT edit files in other projects - Do NOT modify system…
ombulabsCLAUDE.mdclaude-code_rails-upgrade-skill
ombulabs/claude-code_rails-upgrade-skill/CLAUDE.md
This file captures project-specific conventions Claude should follow when working in this repo. The skill body follows the progressive-disclosure practice from the skill-creator skill and the Agent Skills specification: SKILL.md is the short entry point, procedures live in workflows/, on-demand material lives in references/. Two kinds of file, named so a search hit shows which kind it is: Every workflow file opens with the same header, in this order: numbered title, Purpose:, When to use:, ## Inputs (artifacts handed forward…
mobile-nextCLAUDE.mdmobilewright
mobile-next/mobilewright/.claude/CLAUDE.md
No summary in the file. Open it to read it.
aayushchCLAUDE.mdlaya
aayushch/laya/CLAUDE.md
Laya is a local-first desktop app (Tauri + Svelte + Python) that intercepts professional tool events (Jira, Slack, Gmail, GitHub, Bitbucket, Bitbucket Server, Linear, Notion, Google Calendar, Outlook Calendar, Outlook Email), classifies them with LLM-powered personas (Engineer, Comms, Ops, Sales, HR, Finance), stages actions, and presents Action Cards for user approval. n8n handles event ingestion and outbound action execution. Three layers: - Engine (engine/laya/): Python FastAPI backend. Pipeline processes events through ingest → spaceresolution → rules → router → workers…
glebisCLAUDE.mdclaude-skills / automation-advisor
glebis/claude-skills/automation-advisor/CLAUDE.md
Context: Professional decision-making sessions, often during strategic planning or workflow optimization. Users need to make rational, data-backed choices about time investment vs. automation benefits. Job to be Done: Transform vague intuition ("this feels tedious") into quantified ROI analysis with clear recommendations. Help users confidently decide: automate now, maybe later, or stay manual. Voice & Tone: - Intellectually curious, not prescriptive - Sophisticated efficiency (Superhuman aesthetic) - Data-driven but human-centered - Guides without patronizing Emotional Goals: - Primary: Spark curiosity about…
mrwoguCLAUDE.mdpromptscript
mrwogu/promptscript/CLAUDE.md
You are an expert TypeScript developer working on PromptScript - a language and toolchain for standardizing AI instructions across enterprise organizations. PromptScript compiles .prs files to native formats for GitHub Copilot, Claude Code, Cursor, and other AI tools. You write clean, type-safe, and well-tested code following strict TypeScript practices. typescript, Node.js 20+, Nx + pnpm The project is organized as a monorepo with these packages: - Format: Conventional Commits - Types: feat, fix, docs, style, refactor, test, chore -
PratiyushCLAUDE.mdllm-wiki
Pratiyush/llm-wiki/CLAUDE.md
You are maintaining an LLM Wiki (per Karpathy's spec) that compiles the user's Claude Code session history into a structured, interlinked markdown knowledge base. Triggered by /wiki-ingest <path> or /wiki-sync. Files under `raw/sessions/<YYYY-MM-DDTHH-MM>-<project
dislerCLAUDE.mdagent-sandbox-skill
disler/agent-sandbox-skill/CLAUDE.md
No summary in the file. Open it to read it.
labsaiCLAUDE.mdEDDI
labsai/EDDI/CLAUDE.md
Read and follow all instructions in @AGENTS.md
superbasicstudioCLAUDE.mdclaude-conductor
superbasicstudio/claude-conductor/CLAUDE.md
This is a documentation framework designed to work with Claude Code AI assistant. The system provides: Since this is a documentation framework, the typical workflow is: The framework includes a systematic error ledger (CONDUCTOR.md:241-275): - P0: Complete outage, data loss, security breach - P1: Major functionality broken - Error IDs: ERR-YYYY-MM-DD-001 - Linked to JOURNAL.md entries with |ERROR:<ID>| tags
superbasicstudioCLAUDE.mdclaude-conductor / templates
superbasicstudio/claude-conductor/templates/CLAUDE.md
[Include 3-5 templates] NEVER deprioritize, dismiss, or defer any issue the user raises. **If a component is broken, diagnose it and fix it. Perio
DatabricksCLAUDE.mddbt-databricks
databricks/dbt-databricks/CLAUDE.md
No summary in the file. Open it to read it.
About CLAUDE.md
What is CLAUDE.md?
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.