Public release train: @claude-flow/cli, claude-flow, and ruflo. Use package manifests and the registry as version truth; do not copy stale version or capability counts into agent guidance. Ruflo is the coordination ledger and policy decision point. Claude Code executes code, tests, commands, and file changes. A Ruflo coordination call records work; it does not perform the implementation. When registered, call guidance_brain({ mode: "recommend", task: "..." }) before complex Ruflo work. Use its live registry rather than guessing tool names. Treat…
All project rules live in AGENTS.md — the single source of truth for every AI assistant (architecture, conventions, testing, quality gates, git workflow, the 23 Hard Rules, PII learnings). Read it in full; do not re-add project rules here. Everything below applies ONLY to Claude Code — operational refinements of rules already defined in AGENTS.md. The full mandatory worktree protocol (base-branch confirmation, .claude/worktrees/ canonical path, cp -al node_modules, teardown rules) is in AGENTS.md → Git Workflow → "Worktree isolation". Claude-Code-specific…
This is a best practices repository for Claude Code configuration, demonstrating patterns for skills, subagents, hooks, and commands. It serves as a reference implementation rather than an application codebase. Two skill patterns: agent skills (preloaded via skills: field) vs skills (invoked via Skill tool). See orchestration-workflow/orchestration-workflow.md for the complete flow diagram. Hook events configured in .claude/settings.json: PreToolUse, PostToolUse, UserPromptSubmit, Notification, Stop, SubagentStart, SubagentStop, PreCompact, SessionStart, SessionEnd, Setup, PermissionRequest, TeammateIdle, TaskCompleted, ConfigChange. Special handling: git commits trigger pretooluse-git-committing sound. Be explicit…
**MANDATORY: Read AGENT_GUIDE.md before responding to ANY user message.** Do not act on the user's request until you have read AGENT_GUIDE.md. It contains routing rules that determine your first action…
CRITICAL: @./.ai/guidelines.md guidelines MUST be followed at all times. Local Preferences: @./.claude/local.md When asked to update memory, you must update ./.claude/CLAUDE.md if it is not specified that another file should…
Output: JSON with monthlyburn, runwaymonths, totalrunwaydollars, quarterlyburn, and burnrate_daily Remember: As Chief of Staff, you have access to financial data in the financial_data/ directory and can delegate specialized analysis to your subagents (financial-analyst and recruiter).
A collection of Jupyter notebooks and Python examples for building with the Claude API. Or directly with uv: Notebooks have relaxed rules for mid-file imports (E402), redefinitions (F811), and variable naming (N803, N806). Branch naming: <username>/<feature-description> Commit format (conventional commits): These commands are available in Claude Code and CI:
This is a comprehensive Jupyter notebook cookbook demonstrating Claude's Skills feature for document generation (Excel, PowerPoint, PDF). It's designed for developers learning to integrate Skills into their applications. Beta API Requirements: - All Skills functionality uses client.beta.* namespace - Required beta headers: code-execution-2025-08-25, files-api-2025-04-14, skills-2025-10-02 - Must use client.beta.messages.create() with container parameter - Code execution tool (codeexecution20250825) is REQUIRED - Use pre-built Agent skills by referencing their skill_id or create and upload your own via the Skills API Files API…
Do not treat @AGENTS.md as loaded. Claude Code does not reliably inline that import. Before any planning, coding, reviewing, or answering a project question, you MUST call the Read tool…
You should always answer questions in Simplified Chinese first, unless the user explicitly requests another language. JeecgBoot 3.9.5 — a Java low-code development platform built on Spring Boot 4.1.0, Java 17 (also supports 21, 24). It runs as a monolithic app by default, with an optional Spring Cloud microservices mode. Uses jakarta namespace (not javax) throughout. Optional microservices modules (activated via -P SpringCloud): - jeecg-server-cloud/ — Gateway (port 9999), Nacos (8848/18080), cloud service starters, monitoring (9111), XXL-Job (9080), Sentinel (9000)
LibreChat is a monorepo with the following key workspaces: The source code for @librechat/agents (major backend dependency, same team) lives at <https://github.com/LibreChat-AI/agents>. - All new backend code must be TypeScript in /packages/api. - /api holds wiring, not behavior. When a change would add logic to a CJS file under /api — a branch, a helper, a validation step, a new service call — that logic goes in /packages/api, and the JS file keeps only what wires it up: requires, route…
Instructions for AI coding agents (Claude Code, Codex, Cursor, etc.) working on this codebase. When working in Conductor, you can use the .context/ directory for scratch notes or agent-to-agent handoff artifacts. This directory is gitignored. The specs/ and docs/ directories are symlinked from external locations. For a fresh clone or new workspace, create these symlinks: These contain private design documents and documentation that are not checked into the repository. This project uses two virtual environments: Use .venv for development tasks…
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.
ruvnetCLAUDE.md
