{"repo":"shareAI-lab/learn-claude-code","free":true,"listed":false,"github":"https://github.com/shareAI-lab/learn-claude-code","clone":"git clone https://github.com/shareAI-lab/learn-claude-code.git","description":"Bash is all you need -  A nano claude code–like 「agent harness」, built from 0 to 1","language":"Python","stars":74377,"topics":["agent","agent-development","ai-agent","claude","claude-code","educational","llm","python","teaching","tutorial"],"license":"MIT","category":"llm_orchestration","readme_excerpt":"[English](./README.md) | [中文](./README-zh.md) | [日本語](./README-ja.md)\n\n<a href=\"https://trendshift.io/repositories/19746\" target=\"_blank\"><img src=\"https://trendshift.io/api/badge/repositories/19746\" alt=\"shareAI-lab%2Flearn-claude-code | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"/></a>\n\n# Learn Claude Code -- Harness Engineering for Real Agents\n\n## Agency Comes from the Model. An Agent Product = Model + Harness.\n\nBefore we write any code, one thing needs to be clear.\n\n**Agency -- the capacity to perceive, reason, and act -- comes from model training, not from external code orchestration.** But a working agent product needs both the model and the harness. The model is the driver. The harness is the vehicle. This repository teaches you how to build the vehicle.\n\n### Where Agency Comes From\n\nAt the core of every agent is a neural network -- a Transformer, an RNN, a trained function -- shaped by billions of gradient updates on sequences of perception, reasoning, and action. Agency was never bestowed by the surrounding code. It was learned during training.\n\nHumans are the original proof. A biological neural network, refined by millions of years of evolutionary pressure, perceives the world through senses, reasons through a brain, and acts through a body. When DeepMind, OpenAI, or Anthropic say \"agent,\" they all mean the same core thing: **a model that learned to act through training, plus the infrastructure that lets it operate in a specific environment.**\n\nThe historical record is unambiguous:\n\n- **2013 -- DeepMind DQN plays Atari.** A single neural network, receiving only raw pixels and game scores, learned 7 Atari 2600 games -- surpassing prior algorithms and beating human experts in 3 of them. By 2015, scaled to [49 games at professional tester level](https://www.nature.com/articles/nature14236), published in *Nature*. No game-specific rules. One model, learning from experience.\n\n- **2019 -- OpenAI Five conquers Dota 2.** Five neural networks played [45,000 years of Dota 2 against themselves](https://openai.com/index/openai-five-defeats-dota-2-world-champions/) over 10 months, then defeated **OG** -- the TI8 world champions -- 2-0 in a live match. In the public arena, the AI won 99.4% of 42,729 games. No scripted strategies. Models learned teamwork through self-play.\n\n- **2019 -- DeepMind AlphaStar masters StarCraft II.** AlphaStar [beat a professional player 10-1](https://deepmind.google/blog/alphastar-mastering-the-real-time-strategy-game-starcraft-ii/) in closed matches, then reached [Grandmaster rank](https://www.nature.com/articles/d41586-019-03298-6) on the European server -- top 0.15% of 90,000 players. An incomplete-information, real-time game with a combinatorial action space far exceeding chess or Go.\n\n- **2019 -- Tencent Jueyu dominates Honor of Kings.** Tencent AI Lab's \"Jueyu\" system [defeated KPL professional players in full 5v5](https://www.jiemian.com/article/3371171.html) at the World Champion Cup semifinal. In 1v1 mode, pros [won just 1 out of 15 matches, lasting under 8 minutes at best](https://developer.aliyun.com/article/851058). Training intensity: one day equaled 440 human years. A model that learned the entire game from scratch through self-play.\n\n- **2024-2025 -- LLM agents reshape software engineering.** Claude, GPT, Gemini -- large language models trained on the full breadth of human code and reasoning -- are deployed as coding agents. They read codebases, write implementations, debug failures, and coordinate as teams. The architecture is identical to every previous agent: a trained model, placed in an environment, given tools for perception and action.\n\nEvery milestone points to the same fact: **Agency -- the ability to perceive, reason, and act -- is trained, not coded.** But every agent also needs an environment to operate in: an Atari emulator, the Dota 2 client, the StarCraft II engine, an IDE and a terminal. The model supplies the intelligence. The environment supplies the action space. Together they form a complete agent.\n\n### What an Agent Is NOT\n\nThe word \"agent\" has been hijacked by an entire prompt-plumbing industry.\n\nDrag-and-drop workflow builders. No-code \"AI Agent\" platforms. Prompt-chain orchestration libraries. They share a single delusion: that stringing LLM API calls together with if-else branches, node graphs, and hardcoded routing logic constitutes \"building an agent.\"\n\nIt does not. What they produce are Rube Goldberg machines -- over-engineered, brittle, procedural rule pipelines with an LLM wedged in as a glorified text-completion node. That is not an agent. That is a shell script with grandiose pretensions.\n\nYou cannot brute-force intelligence by stacking procedural logic -- sprawling rule trees, node graphs, chained prompt waterfalls -- and praying that enough glue code will spontaneously produce autonomous behavior. It will not. You cannot engineer agency into existence. Agency is learned, not coded.\n\n### The Mindshift: From \"Building Agents\" to Building Harnesses\n\nWhen someone says \"I am building an agent,\" they can only mean one of two things:\n\n**1. Training a model.** Adjusting weights through reinforcement learning, fine-tuning, RLHF, or another gradient-based method. Collecting trajectory data -- real-world sequences of perception, reasoning, and action in a target domain -- and using it to shape the model's behavior. This is what DeepMind, OpenAI, Tencent AI Lab, and Anthropic do.\n\n**2. Building a harness.** Writing the code that gives a model an operational environment. This is what most of us do, and it is the core of this repository.\n\nA harness is everything an agent needs to work in a specific domain:\n\n```\nHarness = Tools + Knowledge + Observation + Action Interfaces + Permissions\n\n    Tools:          file I/O, shell, network, database, browser\n    Knowledge:      product docs, domain references, API specs, style guides\n    Observation:    git diff, error logs, browser state, sensor data\n    Action:         CLI commands, API calls, UI interactions\n    Permissions:    sandbox isolation, approval workflows, trust boundaries\n```\n\nThe model decides. The harness executes. The model reasons. The harness provides context. The model is the driver. The harness is the vehicle.\n\nThis repository teaches you to build the vehicle. A vehicle for coding. But the design patterns generalize to any domain.\n\n### What Harness Engineers Actually Do\n\nIf you are reading this repository, you are most likely a harness engineer. Here is what the job actually entails:\n\n- **Implement tools.** Give the agent hands. File read/write, shell execution, API calls, browser control, database queries. Each tool is one action the agent can take in its environment. Design them atomic, composable, and clearly described.\n\n- **Curate knowledge.** Give the agent domain expertise. Product documentation, architecture decision records, style guides, compliance requirements. Load on demand, not upfront.\n\n- **Manage context.** Subagents keep focused work in a separate message list. Context compaction shortens older history. Task systems let goals persist beyond a single conversation.\n\n- **Control permissions.** Give the agent boundaries. Sandbox file access. Require approval for destructive operations. Enforce trust boundaries between the agent and external systems.\n\n- **Collect trajectory data.** Every action sequence the agent executes in your harness is training signal. Real deployment trajectories are the raw material for fine-tuning the next generation of agent models.\n\nYou are not writing intelligence. You are building the world that intelligence inhabits. The quality of that world directly determines how effectively the intelligence can express itself.\n\n**Build the harness well. The model will do the rest.**\n\n### Why Claude Code\n\nBecause Claude Code is the most elegant, most complete agent harness implementation we have seen. Not because of any clever trick, but because of what it *does not* do: it does not try to be the agent. It does not impose rigid workflows. It does not substitute hand-crafted decision trees for the model's own judgment. It gives the model tools, knowledge, context management, and permission boundaries -- then gets out of the way.\n\nStrip Claude Code down to its essence:\n\n```\nClaude Code = one agent loop\n            + tools (bash, read, write, edit, glob, grep, browser...)\n            + on-demand skill loading\n            + context compaction\n            + subagent spawning\n            + task system with dependency graphs\n            + async mailbox team coordination\n            + task-bound worktrees for parallel edits\n            + permission governance\n            + hooks extension system\n            + memory persistence\n            + MCP external capability routing\n```\n\nThat is it. The agent itself? Claude. A model. Trained by Anthropic on the full breadth of human reasoning and code. The harness did not make Claude smart. Claude was already smart. The harness gave Claude hands, eyes, and a workspace.\n\nThe takeaway is not \"copy Claude Code.\" The takeaway is: **the best agent products come from engineers who understand that their job is the harness, not the intelligence.**\n\n---\n\n```\n                    THE AGENT PATTERN\n                    =================\n\n    User --> messages[] --> LLM --> response\n                                      |\n                              contains tool_use block?\n                           /                          \\\n                         yes                           no\n                          |                             |\n                    execute tools                    return text\n                    append results\n                    loop back -----------------> messages[]\n\n\n    The model decides when to call tools and when to stop.\n    The code just executes what the model asks for.\n    This repo teaches you to build everything around this loop --\n    the harness that makes the agent eff","default_branch":"main","files":411,"tree":[".env.example",".github/workflows/ci.yml",".github/workflows/test.yml",".gitignore","CONTRIBUTING.md","LICENSE","README-ja.md","README-zh.md","README.md","agents/__init__.py","agents/s01_agent_loop.py","agents/s02_tool_use.py","agents/s03_todo_write.py","agents/s04_subagent.py","agents/s05_skill_loading.py","agents/s06_context_compact.py","agents/s07_task_system.py","agents/s08_background_tasks.py","agents/s09_agent_teams.py","agents/s10_team_protocols.py","agents/s11_autonomous_agents.py","agents/s12_worktree_task_isolation.py","agents/s_full.py","docs/en/s01-the-agent-loop.md","docs/en/s02-tool-use.md","docs/en/s03-todo-write.md","docs/en/s04-subagent.md","docs/en/s05-skill-loading.md","docs/en/s06-context-compact.md","docs/en/s07-task-system.md","docs/en/s08-background-tasks.md","docs/en/s09-agent-teams.md","docs/en/s10-team-protocols.md","docs/en/s11-autonomous-agents.md","docs/en/s12-worktree-task-isolation.md","docs/ja/s01-the-agent-loop.md","docs/ja/s02-tool-use.md","docs/ja/s03-todo-write.md","docs/ja/s04-subagent.md","docs/ja/s05-skill-loading.md","docs/ja/s06-context-compact.md","docs/ja/s07-task-system.md","docs/ja/s08-background-tasks.md","docs/ja/s09-agent-teams.md","docs/ja/s10-team-protocols.md","docs/ja/s11-autonomous-agents.md","docs/ja/s12-worktree-task-isolation.md","docs/zh/s01-the-agent-loop.md","docs/zh/s02-tool-use.md","docs/zh/s03-todo-write.md","docs/zh/s04-subagent.md","docs/zh/s05-skill-loading.md","docs/zh/s06-context-compact.md","docs/zh/s07-task-system.md","docs/zh/s08-background-tasks.md","docs/zh/s09-agent-teams.md","docs/zh/s10-team-protocols.md","docs/zh/s11-autonomous-agents.md","docs/zh/s12-worktree-task-isolation.md","requirements.txt","s01_agent_loop/README.ja.md","s01_agent_loop/README.md","s01_agent_loop/README.zh.md","s01_agent_loop/code.py","s01_agent_loop/images/agent-loop.en.svg","s01_agent_loop/images/agent-loop.ja.svg","s01_agent_loop/images/agent-loop.svg","s02_tool_use/README.ja.md","s02_tool_use/README.md","s02_tool_use/README.zh.md","s02_tool_use/code.py","s02_tool_use/images/tool-dispatch.en.svg","s02_tool_use/images/tool-dispatch.ja.svg","s02_tool_use/images/tool-dispatch.svg","s03_permission/README.ja.md","s03_permission/README.md","s03_permission/README.zh.md","s03_permission/code.py","s03_permission/images/permission-overview.en.svg","s03_permission/images/permission-overview.ja.svg","s03_permission/images/permission-overview.svg","s03_permission/images/permission-pipeline.en.svg","s03_permission/images/permission-pipeline.ja.svg","s03_permission/images/permission-pipeline.svg","s04_hooks/README.ja.md","s04_hooks/README.md","s04_hooks/README.zh.md","s04_hooks/code.py","s04_hooks/images/hooks-overview.en.svg","s04_hooks/images/hooks-overview.ja.svg","s04_hooks/images/hooks-overview.svg","s05_todo_write/README.ja.md","s05_todo_write/README.md","s05_todo_write/README.zh.md","s05_todo_write/code.py","s05_todo_write/example/hello.py","s05_todo_write/images/todo-overview.en.svg","s05_todo_write/images/todo-overview.ja.svg","s05_todo_write/images/todo-overview.svg","s06_subagent/README.ja.md","s06_subagent/README.md","s06_subagent/README.zh.md","s06_subagent/code.py","s06_subagent/images/subagent-overview.en.svg","s06_subagent/images/subagent-overview.ja.svg","s06_subagent/images/subagent-overview.svg","s07_skill_loading/README.ja.md","s07_skill_loading/README.md","s07_skill_loading/README.zh.md","s07_skill_loading/code.py","s07_skill_loading/images/skill-overview.en.svg","s07_skill_loading/images/skill-overview.ja.svg","s07_skill_loading/images/skill-overview.svg","s08_context_compact/README.ja.md","s08_context_compact/README.md","s08_context_compact/README.zh.md","s08_context_compact/code.py","s08_context_compact/images/auto-compact.en.svg","s08_context_compact/images/auto-compact.ja.svg","s08_context_compact/images/auto-compact.svg","s08_context_compact/images/compact-overview.en.svg","s08_context_compact/images/compact-overview.ja.svg","s08_context_compact/images/compact-overview.svg","s08_context_compact/images/compaction-layers.en.svg","s08_context_compact/images/compaction-layers.ja.svg","s08_context_compact/images/compaction-layers.svg","s08_context_compact/images/layer1-budget.en.svg","s08_context_compact/images/layer1-budget.ja.svg","s08_context_compact/images/layer1-budget.svg","s08_context_compact/images/micro-compact.en.svg","s08_context_compact/images/micro-compact.ja.svg","s08_context_compact/images/micro-compact.svg","s09_memory/README.ja.md","s09_memory/README.md","s09_memory/README.zh.md","s09_memory/code.py","s09_memory/images/memory-overview.en.svg","s09_memory/images/memory-overview.ja.svg","s09_memory/images/memory-overview.svg","s09_memory/images/memory-subsystems.en.svg","s09_memory/images/memory-subsystems.ja.svg","s09_memory/images/memory-subsystems.svg","s10_task_system/README.ja.md","s10_task_system/README.md","s10_task_system/README.zh.md","s10_task_system/code.py","s10_task_system/images/task-dag.en.svg","s10_task_system/images/task-dag.ja.svg","s10_task_system/images/task-dag.svg","s10_task_system/images/task-system-overview.en.svg","s10_task_system/images/task-system-overview.ja.svg","s10_task_system/images/task-system-overview.svg","s11_background_tasks/README.ja.md","s11_background_tasks/README.md","s11_background_tasks/README.zh.md","s11_background_tasks/code.py","s11_background_tasks/images/background-tasks-overview.en.svg","s11_background_tasks/images/background-tasks-overview.ja.svg","s11_background_tasks/images/background-tasks-overview.svg","s12_cron_scheduler/README.ja.md","s12_cron_scheduler/README.md","s12_cron_scheduler/README.zh.md","s12_cron_scheduler/code.py","s12_cron_scheduler/images/cron-scheduler-overview.en.svg","s12_cron_scheduler/images/cron-scheduler-overview.ja.svg","s12_cron_scheduler/images/cron-scheduler-overview.svg","s13_agent_teams/README.ja.md","s13_agent_teams/README.md","s13_agent_teams/README.zh.md","s13_agent_teams/code.py","s13_agent_teams/images/agent-teams-overview.en.svg","s13_agent_teams/images/agent-teams-overview.ja.svg","s13_agent_teams/images/agent-teams-overview.svg","s13_agent_teams/images/team-protocols-overview.en.svg","s13_agent_teams/images/team-protocols-overview.ja.svg","s13_agent_teams/images/team-protocols-overview.svg","s13_agent_teams/images/team-topology.en.svg","s13_agent_teams/images/team-topology.ja.svg","s13_agent_teams/images/team-topology.svg","s14_mcp_plugin/README.ja.md","s14_mcp_plugin/README.md","s14_mcp_plugin/README.zh.md","s14_mcp_plugin/code.py","s14_mcp_plugin/images/mcp-architecture.en.svg","s14_mcp_plugin/images/mcp-architecture.ja.svg","s14_mcp_plugin/images/mcp-architecture.svg","s15_integrated_harness/README.ja.md","s15_integrated_harness/README.md","s15_integrated_harness/README.zh.md","s15_integrated_harness/code.py","s15_integrated_harness/images/system-architecture.en.svg","s15_integrated_harness/images/system-architecture.ja.svg","s15_integrated_harness/images/system-architecture.svg","s16_workflow_runtime/README.ja.md","s16_workflow_runtime/README.md","s16_workflow_runtime/README.zh.md","s16_workflow_runtime/code.py","s16_workflow_runtime/images/workflow-runtime-overview.svg","s17_goal_loop/README.ja.md","s17_goal_loop/README.md","s17_goal_loop/README.zh.md","s17_goal_loop/code.py","s17_goal_loop/images/goal-loop-overview.svg","skills/agent-builder/SKILL.md","skills/agent-builder/references/agent-philosophy.md","skills/agent-builder/references/minimal-agent.py","skills/agent-builder/references/subagent-pattern.py","skills/agent-builder/references/tool-templates.py","skills/agent-builder/scripts/init_agent.py","skills/code-review/SKILL.md","skills/mcp-builder/SKILL.md","skills/pdf/SKILL.md","tests/test_agent_loop_boundaries.py","tests/test_agent_teams_runtime.py","tests/test_agents_smoke.py","tests/test_background_tasks.py","tests/test_chapter_readmes.py","tests/test_compaction_tool_pairs.py","tests/test_cron_scheduler.py","tests/test_goal_loop.py","tests/test_s06_subagent.py","tests/test_s_full_background.py","tests/test_skill_loading.py","tests/test_task_system.py","tests/test_todo_write_string_input.py","tests/test_web_scenarios.py","tests/test_workflow_goal_lessons.py","web/.gitignore","web/README.md","web/next.config.ts","web/package-lock.json","web/package.json","web/postcss.config.mjs","web/public/course-assets/s01_agent_loop/agent-loop.en.svg","web/public/course-assets/s01_agent_loop/agent-loop.ja.svg","web/public/course-assets/s01_agent_loop/agent-loop.svg","web/public/course-assets/s02_tool_use/tool-dispatch.en.svg","web/public/course-assets/s02_tool_use/tool-dispatch.ja.svg","web/public/course-assets/s02_tool_use/tool-dispatch.svg","web/public/course-assets/s03_permission/permission-overview.en.svg","web/public/course-assets/s03_permission/permission-overview.ja.svg","web/public/course-assets/s03_permission/permission-overview.svg","web/public/course-assets/s03_permission/permission-pipeline.en.svg","web/public/course-assets/s03_permission/permission-pipeline.ja.svg","web/public/course-assets/s03_permission/permission-pipeline.svg","web/public/course-assets/s04_hooks/hooks-overview.en.svg","web/public/course-assets/s04_hooks/hooks-overview.ja.svg","web/public/course-assets/s04_hooks/hooks-overview.svg","web/public/course-assets/s05_todo_write/todo-overview.en.svg","web/public/course-assets/s05_todo_write/todo-overview.ja.svg","web/public/course-assets/s05_todo_write/todo-overview.svg","web/public/course-assets/s06_subagent/subagent-overview.en.svg","web/public/course-assets/s06_subagent/subagent-overview.ja.svg","web/public/course-assets/s06_subagent/subagent-overview.svg","web/public/course-assets/s07_skill_loading/skill-overview.en.svg","web/public/course-assets/s07_skill_loading/skill-overview.ja.svg","web/public/course-assets/s07_skill_loading/skill-overview.svg","web/public/course-assets/s08_context_compact/auto-compact.en.svg","web/public/course-assets/s08_context_compact/auto-compact.ja.svg","web/public/course-assets/s08_context_compact/auto-compact.svg","web/public/course-assets/s08_context_compact/compact-overview.en.svg","web/public/course-assets/s08_context_compact/compact-overview.ja.svg","web/public/course-assets/s08_context_compact/compact-overview.svg","web/public/course-assets/s08_context_compact/compaction-layers.en.svg","web/public/course-assets/s08_context_compact/compaction-layers.ja.svg","web/public/course-assets/s08_context_compact/compaction-layers.svg","web/public/course-assets/s08_context_compact/layer1-budget.en.svg","web/public/course-assets/s08_context_compact/layer1-budget.ja.svg","web/public/course-assets/s08_context_compact/layer1-budget.svg","web/public/course-assets/s08_context_compact/micro-compact.en.svg","web/public/course-assets/s08_context_compact/micro-compact.ja.svg","web/public/course-assets/s08_context_compact/micro-compact.svg","web/public/course-assets/s09_memory/memory-overview.en.svg","web/public/course-assets/s09_memory/memory-overview.ja.svg","web/public/course-assets/s09_memory/memory-overview.svg","web/public/course-assets/s09_memory/memory-subsystems.en.svg","web/public/course-assets/s09_memory/memory-subsystems.ja.svg","web/public/course-assets/s09_memory/memory-subsystems.svg","web/public/course-assets/s10_task_system/task-dag.en.svg","web/public/course-assets/s10_task_system/task-dag.ja.svg","web/public/course-assets/s10_task_system/task-dag.svg","web/public/course-assets/s10_task_system/task-system-overview.en.svg","web/public/course-assets/s10_task_system/task-system-overview.ja.svg","web/public/course-assets/s10_task_system/task-system-overview.svg","web/public/course-assets/s11_background_tasks/background-tasks-overview.en.svg","web/public/course-assets/s11_background_tasks/background-tasks-overview.ja.svg","web/public/course-assets/s11_background_tasks/background-tasks-overview.svg","web/public/course-assets/s12_cron_scheduler/cron-scheduler-overview.en.svg","web/public/course-assets/s12_cron_scheduler/cron-scheduler-overview.ja.svg","web/public/course-assets/s12_cron_scheduler/cron-scheduler-overview.svg","web/public/course-assets/s13_agent_teams/agent-teams-overview.en.svg","web/public/course-assets/s13_agent_teams/agent-teams-overview.ja.svg","web/public/course-assets/s13_agent_teams/agent-teams-overview.svg","web/public/course-assets/s13_agent_teams/team-protocols-overview.en.svg","web/public/course-assets/s13_agent_teams/team-protocols-overview.ja.svg","web/public/course-assets/s13_agent_teams/team-protocols-overview.svg","web/public/course-assets/s13_agent_teams/team-topology.en.svg","web/public/course-assets/s13_agent_teams/team-topology.ja.svg","web/public/course-assets/s13_agent_teams/team-topology.svg","web/public/course-assets/s14_mcp_plugin/mcp-architecture.en.svg","web/public/course-assets/s14_mcp_plugin/mcp-architecture.ja.svg","web/public/course-assets/s14_mcp_plugin/mcp-architecture.svg","web/public/course-assets/s15_integrated_harness/system-architecture.en.svg","web/public/course-assets/s15_integrated_harness/system-architecture.ja.svg","web/public/course-assets/s15_integrated_harness/system-architecture.svg","web/public/course-assets/s16_workflow_runtime/workflow-runtime-overview.svg","web/public/course-assets/s17_goal_loop/goal-loop-overview.svg","web/public/file.svg","web/public/globe.svg","web/public/next.svg","web/public/vercel.svg","web/public/window.svg","web/scripts/extract-content.ts","web/src/app/[locale]/(learn)/[version]/client.tsx","web/src/app/[locale]/(learn)/[version]/diff/diff-content.tsx","web/src/app/[locale]/(learn)/[version]/diff/page.tsx","web/src/app/[locale]/(learn)/[version]/page.tsx","web/src/app/[locale]/(learn)/compare/page.tsx","web/src/app/[locale]/(learn)/layers/page.tsx","web/src/app/[locale]/(learn)/layout.tsx","web/src/app/[locale]/(learn)/timeline/page.tsx","web/src/app/[locale]/layout.tsx","web/src/app/[locale]/page.tsx","web/src/app/favicon.ico","web/src/app/globals.css","web/src/app/page.tsx","web/src/components/architecture/arch-diagram.tsx","web/src/components/architecture/design-decisions.tsx","web/src/components/architecture/execution-flow.tsx","web/src/components/architecture/message-flow.tsx","web/src/components/code/source-viewer.tsx","web/src/components/diff/code-diff.tsx","web/src/components/diff/whats-new.tsx","web/src/components/docs/doc-renderer.tsx","web/src/components/layout/header.tsx","web/src/components/layout/sidebar.tsx","web/src/components/simulator/agent-loop-simulator.tsx","web/src/components/simulator/simulator-controls.tsx","web/src/components/simulator/simulator-message.tsx","web/src/components/timeline/timeline.tsx","web/src/components/ui/badge.tsx","web/src/components/ui/card.tsx","web/src/components/ui/tabs.tsx","web/src/components/visualizations/index.tsx","web/src/components/visualizations/s01-agent-loop.tsx","web/src/components/visualizations/s02-tool-dispatch.tsx","web/src/components/visualizations/s03-permission.tsx","web/src/components/visualizations/s03-todo-write.tsx","web/src/components/visualizations/s04-hooks.tsx","web/src/components/visualizations/s06-subagent.tsx","web/src/components/visualizations/s07-skill-loading.tsx","web/src/components/visualizations/s08-context-compact.tsx","web/src/components/visualizations/s09-memory.tsx","web/src/components/visualizations/s10-task-system.tsx","web/src/components/visualizations/s11-background-tasks.tsx","web/src/components/visualizations/s12-cron-scheduler.tsx","web/src/components/visualizations/s13-team-runtime.tsx","web/src/components/visualizations/s14-mcp-tools.tsx","web/src/components/visualizations/s15-integrated-harness.tsx","web/src/components/visualizations/shared/mechanism-flow.tsx","web/src/components/visualizations/shared/step-controls.tsx","web/src/data/annotations/s01.json","web/src/data/annotations/s02.json","web/src/data/annotations/s03.json","web/src/data/annotations/s04.json","web/src/data/annotations/s05.json","web/src/data/annotations/s06.json","web/src/data/annotations/s07.json","web/src/data/annotations/s08.json","web/src/data/annotations/s09.json","web/src/data/annotations/s10.json","web/src/data/annotations/s11.json","web/src/data/annotations/s12.json","web/src/data/annotations/s13.json","web/src/data/annotations/s14.json","web/src/data/annotations/s15.json","web/src/data/annotations/s16.json","web/src/data/annotations/s17.json","web/src/data/execution-flows.ts","web/src/data/generated/docs.json","web/src/data/generated/versions.json","web/src/data/scenarios/s01.json","web/src/data/scenarios/s02.json","web/src/data/scenarios/s03.json","web/src/data/scenarios/s04.json","web/src/data/scenarios/s05.json","web/src/data/scenarios/s06.json","web/src/data/scenarios/s07.json","web/src/data/scenarios/s08.json","web/src/data/scenarios/s09.json","web/src/data/scenarios/s10.json","web/src/data/scenarios/s11.json","web/src/data/scenarios/s12.json","web/src/data/scenarios/s13.json","web/src/data/scenarios/s14.json","web/src/data/scenarios/s15.json","web/src/data/scenarios/s16.json","web/src/data/scenarios/s17.json","web/src/hooks/useDarkMode.ts","web/src/hooks/useSimulator.ts"],"storefront":"/r/shareAI-lab","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/shareAI-lab/learn-claude-code/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}