मुख्य सामग्री पर जाएं

skills · Claude Code, Anthropic's command-line coding agent

Claude Code & Command-Line AI

Learn Claude Code on a real repo, and stay in control of it.

कोर्स के अंत तक, आप ये कर पाएँगे:

  • A first session checked against the files
  • A bug fixed test-first, its diff read
  • Permission and deny rules you chose
  • A short CLAUDE.md and a plan before a big change
  • A skill, hooks, a reviewer subagent and an MCP server
  • A planted-text test and an undo you have practiced
  • A headless script and a teammate note

$9/माह से7.5 घंटे5 अध्याय20 पाठ

कोर्स अभी अंग्रेज़ी में हैं।

“It has your permissions. Now what?”

इस कोर्स के बारे में

यह किसके लिए है

  • You write code and want to use Claude Code on a real repo, not a toy
  • You have tried an AI coding tool and want to know what it read, ran and changed
  • You want a setup you could hand to a teammate: rules, checks and limits written down

आपको क्या चाहिए

  • You write code and use git and a terminal
  • A Claude plan that includes Claude Code, or a Console account

आप कौन से कौशल अभ्यास करेंगे

  • Claude Code
  • CLAUDE.md
  • Permission rules
  • Plan mode
  • Hooks
  • Skills and subagents
  • MCP
  • Headless automation

कितना समय लगता है

कुल मिलाकर लगभग 7.5 घंटे

  1. अध्याय 1 · An agent in your terminal1.5 घंटे
  2. अध्याय 2 · Context is the job1.5 घंटे
  3. अध्याय 3 · Make it yours1.5 घंटे
  4. अध्याय 4 · What it must never do1.5 घंटे
  5. अध्याय 5 · Beyond the chat1.5 घंटे

इसमें क्या शामिल है

  • 20 पाठ
  • 78 पठन
  • 20 हल किए गए उदाहरण
  • 40 अभ्यास
  • 40 त्वरित जाँचें
  • 20 आम भ्रम
  • 20 क्विज़
  • अध्याय के अंत की 5 जाँचें

पाठ्यक्रम

5 अध्याय, 20 पाठ

पूरा कोर्स: हर अध्याय और पाठ। विस्तार के लिए अध्याय पर टैप करें। शुरू करने पर पाठ खुलेंगे।

    • CLAUDE.md: What It Reads Every Time
    • The Context Window Fills
    • Plan Before a Big Change
    • Give It a Way to Check Its Work
    • Your Own Command: A Skill
    • Hooks: Rules That Run Every Time
    • A Second Pair of Eyes: Subagents
    • Connect One Tool with MCP
    • Text It Reads Can Give It Orders
    • Secrets and the Bypass Flag
    • Plausible Is Not Correct
    • Undo: Checkpoints, Git and Worktrees
    • Run It from a Script
    • Several Sessions at Once
    • What It Costs and How to Keep It Down
    • The Note Your Teammate Needs

करियर

यह कोर्स आपको कहाँ तक ले जा सकता है

वे भूमिकाएँ जिनसे यह कोर्स जुड़ता है, और वे कौशल जिन्हें कोर्स पूरा करने के बाद आप अपने रिज़्यूमे और LinkedIn पर लिख सकते हैं।

वे कौशल जो आप बनाएँगे

कोर्स पूरा करने के बाद इन्हें अपने रिज़्यूमे या LinkedIn प्रोफ़ाइल में चिपकाएँ।

  • Running Claude Code in a repo and checking its answersUse an AI coding agent from the command line
  • Exploring an unfamiliar codebase with an AI agentOnboard to an unfamiliar repository with AI assistance
  • Test-first bug fixing with an AI coding agentWrite a failing test before a fix and review the resulting diff
  • Configuring Claude Code permissionsConfigure permission modes and allow, ask and deny rules for an AI coding agent
  • Writing and maintaining a CLAUDE.md context fileWrite project instructions for an AI coding agent
  • Managing an AI coding agent's context windowManage context across AI coding sessions
  • Planning multi-file changes with an AI coding agentReview and edit an AI-generated implementation plan before coding
  • Defining verification checks for AI-written changesDefine acceptance checks an AI coding agent can run
  • Writing reusable skills for an AI coding agentWrite reusable commands or skills for an AI coding agent
  • Enforcing repository rules with agent hooksWrite hooks that enforce rules on an AI coding agent's actions
  • Configuring subagents with scoped toolsConfigure review subagents with least-privilege tool access
  • Connecting and scoping MCP serversConnect an AI coding agent to external tools with the Model Context Protocol
  • Testing an AI coding agent against prompt injectionTest AI coding agents against prompt injection from untrusted content
  • Protecting secrets from an AI coding agentConfigure deny rules that keep credentials away from AI coding tools
  • Reviewing AI-written code against requirementsReview AI-generated code changes against the cases a request describes
  • Recovering from unwanted agent changesRecover from unwanted AI agent changes with checkpoints and git
  • Running an AI coding agent from scriptsAutomate code review checks with a headless AI coding agent and scoped tools
  • Running parallel AI coding sessions with git worktreesRun parallel AI agent sessions in isolated git worktrees
  • Managing AI coding tool usage and costMeasure and reduce token usage of AI coding tools
  • Documenting a team's AI coding agent setupWrite team guidelines for AI coding agent use backed by tested configuration

प्रश्न

प्रतिबद्ध होने से पहले

You already write code, use git and a terminal, and want to run Claude Code on a real repo of your own without losing track of what it reads, runs and changes.

Claude Code needs a Pro plan or above, or an Anthropic Console account billed per token; the free Claude plan does not include it (as of November 2026). Without one you can still read the lessons, run the sample repo's tests and keep the Session Log.

The course makes no speed claim. A 2025 randomized study found experienced developers slower with the AI tools of early 2025 while believing they were faster, and its authors now call that result out of date. You measure your own work and check every change.

No. The sample repo is Python because it is short and easy to run, but each lesson's required step is on your own repo, in any language.

Your own repo makes the course worth more, and each lesson has one required step on it. If you have none you may use, take the invented sample repo, which has a path through each lesson.

आज ही शुरू करें