agentleFS
Sign inStart free
IndrajeetPatilIndrajeetPatil/effective-claude-code-usage/llms.txt

effective-claude-code-usage

llms.txt1 starsChanged 11 days agoCC0-1.0View on GitHub

A Quarto RevealJS presentation by Indrajeet Patil about using Claude Code effectively as a CLI agent for software engineering work. This presentation explains how to use Claude Code as an agentic coding partner rather than a terminal chatbot. It covers tools, skills (using and writing them), workflows, context management, CLAUDE.md files, auto memory, subagents, background agents, planning mode, hooks, prompting strategies, MCP, Git worktrees, and non-interactive automation with claude -p. Reviewed against Claude Code v2.1.318 on 5 November 2026. Command…

The file

Create a free account to mount
Files
llms.txt
# Effective Claude Code Usage

> A Quarto RevealJS presentation by Indrajeet Patil about using Claude Code effectively as a CLI agent for software engineering work.

This presentation explains how to use Claude Code as an agentic coding partner rather than a terminal chatbot. It covers tools, skills (using and writing them), workflows, context management, CLAUDE.md files, auto memory, subagents, background agents, planning mode, hooks, prompting strategies, MCP, Git worktrees, and non-interactive automation with `claude -p`.

Reviewed against Claude Code v2.1.318 on 5 November 2026. Command availability depends on the installed version and configuration.

## Primary URL

- [Slides](https://www.indrapatil.com/effective-claude-code-usage/)

## Source

- [GitHub repository](https://github.com/IndrajeetPatil/effective-claude-code-usage/)

## Topics

- Claude Code
- Agentic coding
- CLI-based AI agents
- Tool use and slash commands
- Permission modes and Bash sandboxing
- Skills (reusable prompt playbooks) and writing your own SKILL.md
- Background agents, workflows, and multi-agent orchestration
- Context window management
- CLAUDE.md and AGENTS.md durable instructions and per-repository auto memory
- Subagents and planning mode
- Goals and rewind checkpoints
- Hooks and validation workflows
- Model Context Protocol
- Git worktrees for parallel agent sessions
- Non-interactive runs with `claude -p` in scripts and CI

## Machine-readable companion

- [Full agent summary](https://www.indrapatil.com/effective-claude-code-usage/llms-full.txt)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free