claude-code-best-practice
from vibe coding to agentic engineering - practice makes claude perfect
- 67.9k stars
- 6.8k forks
- 28 open issues
- Language: HTML
- License: MIT
- updated
Install
git clone https://github.com/shanraisshan/claude-code-best-practice && cp claude-code-best-practice/*.md ~/.claude/agents/- Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
- Start a new Claude Code session to load the agents.
- Delegate work to them with the Task/Agent tool or by name.
Editor's note
This repository is a structured reference collection covering Claude Code features including subagents, slash commands, skills, hooks, MCP servers, memory management, settings, orchestration workflows, and CLI startup flags. Each concept is organized under `.claude/` subdirectories (for example, `.claude/agents/`, `.claude/commands/`, `.claude/skills/`) and paired with both a best-practice guide and a working implementation example. The repository targets Claude Code users specifically, from beginners writing simple prompts to developers building multi-agent orchestration pipelines where one agent coordinates others. A notable standout is its weather-orchestrator example, which demonstrates a full orchestration workflow using Claude Code commands. The repo also cross-references tips attributed to Boris Cherny and links to official Anthropic skills from the `anthropics/skills` repository. Developers learning to structure Claude Code projects, adopt context engineering practices, or migrate from ad hoc prompting toward repeatable agentic workflows are the primary audience.
24 items in this repository
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Update the AGENT COLLECTIONS table by researching all agent-collection repos in parallel
Meticulous, constructive reviewer for correctness, clarity, security, and maintainability.
Validates roadmap items, features, and technical decisions against the project's constitution, principles, and core values. Ensures all proposals align with the mission, established methodology, and design principles before implementation proceeds.
Update the DEVELOPMENT WORKFLOWS table by researching all 11 workflow repos in parallel
Research agent that fetches GitHub repos, counts agents/skills/commands, gets star counts, and analyzes Claude Code workflow repositories
Use this agent when you need to analyze existing documentation and create new or updated documentation that strictly adheres to project-specific documentation standards defined in claude.md. This agent excels at maintaining consistency with established documentation patterns, ensuring technical accuracy, and producing clear, well-structured documentation.
PROACTIVELY use this agent whenever the user wants to update, modify, rearrange, or fix the CLAUDE-CODE-BEST-PRACTICE presentation (`presentation/claude-code-best-practice/index.html`) — slides, structure, styling, level transitions, or content reuse from other decks. This is the canonical reusable Claude Code best-practices deck. Do NOT use this agent for the vibe-coding presentation (use `presentation-vibe-coding`) or the GDG Kolachi claude-gemini presentation (use `presentation-claude-gemini`).
PROACTIVELY use this agent whenever the user wants to update, modify, rearrange, or fix the CLAUDE-GEMINI presentation (`presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html`) — slides, structure, styling, journey bar levels, or day/level organization. Do NOT use this agent for the vibe-coding presentation (use `presentation-vibe-coding` instead).
Knowledge about the presentation slide format, weight system, navigation, and section structure
Knowledge about CSS classes, component patterns, and syntax highlighting in the presentation
PROACTIVELY use this agent whenever the user wants to update, modify, or fix the VIBE-CODING presentation (`presentation/vibe-coding-to-agentic-engineering/index.html`) — slides, structure, styling, or level transitions. Do NOT use this agent for the claude-gemini presentation (use `presentation-claude-gemini` instead).
Turns a high-level ask into a crisp, exec-ready PRD with acceptance criteria and scope.
Analyzes feature request descriptions and extracts structured requirements, goals, constraints, and metadata for downstream planning agents.
Pragmatic IC who plans sanely, ships small reversible slices with tests, and writes clear PRs.
Update the SKILL COLLECTIONS table by researching all 5 skill-collection repos in parallel
Use this agent to align technological decisions with engineering principles and organizational standards. This agent acts as a CTO, evaluating technical recommendations against established engineering frameworks, risk assessment methodologies, and business alignment criteria before documentation creation. It ensures all technical decisions follow systematic methodology, evidence-based risk reduction, and AI-first development principles while maintaining alignment with venture success metrics.
Use this agent to fetch the current time for Dubai, UAE (Asia/Dubai timezone, UTC+4). This agent fetches real-time Dubai time using its preloaded time-fetcher skill.
Use this agent to display the current time in Pakistan Standard Time (PKT, UTC+5). (root scope — see agent-teams for Dubai time)
Subagents overview
claude-code-best-practice
from vibe coding to agentic engineering - practice makes claude perfect
= Agents · = Commands · = Skills
Boris Cherny on X (tweet 1 · tweet 2 · tweet 3)
Tip
Visit the How to Use section to take full advantage of this repo.
🧠 CONCEPTS
| Feature | Location | Description |
|---|---|---|
| Subagents | .claude/agents/.md | |
| Commands | .claude/commands/.md | |
| Skills | .claude/skills//SKILL.md | Official Skills · Skills for Mono-repos |
| Workflows | .claude/commands/weather-orchestrator.md | |
| Hooks | .claude/hooks/ | Guide |
| MCP Servers | .claude/settings.json, .mcp.json | |
| Plugins | distributable packages | Marketplaces · Create Marketplaces |
| Settings | .claude/settings.json | Permissions · Model Config · Output Styles · Sandboxing · Keybindings · Auto Mode Config |
| Status Line | .claude/settings.json | |
| Memory | CLAUDE.md, .claude/rules/, ~/.claude/rules/, ~/.claude/projects//memory/ | Auto Memory · Auto Memory Deep-dive · Rules |
| Checkpointing | automatic (file-edit tracking) | |
| Sessions | --resume, --continue, /resume, /branch | |
| Context Window | /compact, /clear, /context | |
| CLI Startup Flags | claude [flags] | Interactive Mode · Env Vars |
| AI Terms | | |
| Best Practices | Prompt Engineering · Extend Claude Code | |
| Prompt Library |
🔥 Hot
| Feature | Location | Description |
|---|---|---|
Ultrareview  | /code-review ultra, claude ultrareview [target] | Tasks tracking |
| Devcontainers | .devcontainer/ | |
| Channels | --channels, plugin-based | Reference |
| No Flicker Mode | /tui fullscreen, CLAUDE_CODE_NO_FLICKER=1 | |
| Auto Mode | --permission-mode auto, Shift+Tab | Blog |
| Power-ups | /powerup | |
| Fast Mode | /fast, "fastMode": true | |
| Advisor | /advisor, advisorModel, --advisor | Blog |
| Computer Use | computer-use MCP server | Desktop |
| Agent SDK | npm / pip package | Quickstart · Examples |
| Ralph Wiggum Loop | plugin | |
| Chrome | --chrome, extension | |
| Claude Code Web | claude.ai/code | Routines |
| Artifacts | /share, Artifact tool | |
| Slack | @Claude in Slack |
What people ask about claude-code-best-practice
What is shanraisshan/claude-code-best-practice?
shanraisshan/claude-code-best-practice is subagents for the Claude AI ecosystem. from vibe coding to agentic engineering - practice makes claude perfect It has 67.9k GitHub stars and its last recorded update is dated 2026-10-23.
How do I install claude-code-best-practice?
You can install claude-code-best-practice by cloning the repository (https://github.com/shanraisshan/claude-code-best-practice) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is shanraisshan/claude-code-best-practice safe to use?
Our security agent has analyzed shanraisshan/claude-code-best-practice and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains shanraisshan/claude-code-best-practice?
shanraisshan/claude-code-best-practice is maintained by shanraisshan. The last recorded GitHub activity is dated 2026-10-23, with 28 open issues.
Are there alternatives to claude-code-best-practice?
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Maintain this repo? Show its Trust Score in your README
The badge shows this repository's current Trust Score and verdict, and links back to this page. It follows the catalogue data: nobody can buy or edit the score it displays.
[](https://claudewave.com/en/repo/shanraisshan-claude-code-best-practice)<a href="https://claudewave.com/en/repo/shanraisshan-claude-code-best-practice"><img src="https://claudewave.com/api/badge/shanraisshan-claude-code-best-practice" alt="ClaudeWave Trust Score for shanraisshan/claude-code-best-practice" width="320" height="64"></a>