Project facts live in AGENTS.md. This file only covers Claude Code runtime adaptation. Five project-recommended sub-agents live under .claude/agents/*.md. Claude Code loads them automatically; the main agent should dispatch by task boundary: The main repo has no frontend stack, so no frontend-dev is provided; TypeScript sub-projects under apps/ use their own AI configuration. Before starting a task, run ls docs/. docs/openapi.json is the source of truth for the API contract; after touching src/memos/api/, run make openapi to regenerate it.
This is a monorepo containing two distinct but interconnected project groups: Project 1: HumanLayer SDK & Platform - The core product providing human-in-the-loop capabilities for AI agents Project 2: Local…
This is the humanlayer Daemon (HLD) that powers the WUI (humanlayer-wui) You cannot run this process, you cannot restart it. If you make changes, you must ask the user to…
This is the HumanLayer Web UI (WUI) - a desktop application for managing AI agent approvals and sessions. The WUI connects to the HumanLayer daemon (hld) to provide a graphical…
This file governs Claude's behavior when working on the claude-skills repository. Skills follow the Agent Skills specification. This section covers project-specific conventions that go beyond the base spec. Critical: Never put process steps or workflow sequences in descriptions. When descriptions contain step-by-step instructions, agents follow the brief description instead of reading the full skill content. This defeats the purpose of detailed skills. Brief capability statements (what it does) and trigger conditions (when to use it) are both appropriate. Process steps…
A GEO-SEO analysis toolkit distributed as a suite of Claude Code skills + subagents + Python scripts. "GEO" = Generative Engine Optimization — optimizing websites for AI search engines (ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews) rather than only traditional search. Philosophy: GEO-first, SEO-supported. This repo is the source. Users install it into ~/.claude/ (see install), then invoke /geo <command> <url> inside Claude Code. Audits are run from the user's own working directory and deliverables land there — never in…
This project uses Declarative Automation Bundles for deployment. Install the Databricks CLI 0.292.0 or newer and verify with databricks -v. Read the databricks-core skill for CLI, authentication, and deployment workflow. Read the databricks-jobs skill for job-specific guidance.
Guidance for Claude Code when working with IdeaVim. Essential commands: - ./gradlew runIde - Start dev IntelliJ with IdeaVim - ./gradlew test -x :tests:property-tests:test -x :tests:long-running-tests:test - Run standard tests Avoid running all tests, this takes too long. It's preferred to run specific test. When running gradle tasks, use --console=plain for cleaner output without progress bars. See CONTRIBUTING.md for architecture details and a complete command list. This project uses YouTrack for issue tracking, NOT GitHub Issues. - Tickets are prefixed…
For issues against anthropics/claude-code. When I ask you to file one: - Draft it to a temp file and open it in VS Code (code <file>) for me to review…
A game that teaches JavaScript and TypeScript through interactive coding challenges. Players write code to control a warrior navigating through towers full of enemies. Run a single package's tests: npx vitest run apps/cli/ pnpm monorepo with Turborepo. Code is organized into three top-level directories: Dependency flow: spatial → abilities → units → towers, spatial → core → scoring → cli. Each package compiles with tsc to dist/.
User-specific configuration for this plugin lives at a version-independent path that survives plugin updates: ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md Rules for every skill, command, and agent in this plugin: 1. READ configuration from that path. Not from this file. 2. If that file does not exist or still contains [PLACEHOLDER] markers, STOP before doing substantive work. Say: "This plugin needs setup before it can give you useful output. Run /ai-governance-legal:cold-start-interview — it takes about 10-15 minutes and every command in this plugin depends on…
Guidance for working on this repo. claude-for-legal is a Claude Code plugin marketplace — twelve first-party legal plugins, one vendor plugin, and five managed-agent cookbooks. Most work here is editing prompt content (skills, agents, hooks), plugin metadata, or cookbook config — not application code. This repo follows the same conventions anthropics/claude-plugins-official enforces in CI. Run the equivalent checks locally: claude-plugins-official layers these on top of the schema check. They apply here too — the ones most likely to trip a…
User-specific configuration for this plugin lives at a version-independent path that survives plugin updates: ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md Rules for every skill, command, and agent in this plugin: 1. READ configuration from that path. Not from this file. 2. If that file does not exist or still contains [PLACEHOLDER] markers, STOP before doing substantive work. Say: "This plugin needs setup before it can give you useful output. Run /commercial-legal:cold-start-interview — it takes about 10-15 minutes and every command in this plugin depends on…
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.
MemTensorCLAUDE.md
