claude-code-ultimate-guide-mcp 1.0.3 → 1.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/content/llms.txt +96 -150
  2. package/content/reference.yaml +161 -161
  3. package/dist/index.js +578 -5
  4. package/package.json +1 -1
package/content/llms.txt CHANGED
@@ -1,166 +1,112 @@
1
- # The Ultimate Claude Code Guide
2
-
3
- > A comprehensive, self-contained guide to mastering Claude Code - Anthropic's official CLI for AI-assisted development.
4
-
5
- ## What This Repository Contains
6
-
7
- This repository provides everything needed to go from Claude Code beginner to power user:
8
-
9
- 1. **Complete Guide** (`guide/ultimate-guide.md`) - 9,600+ lines covering all aspects of Claude Code
10
- 2. **Cheatsheet** (`guide/cheatsheet.md`) - 1-page printable daily reference
11
- 3. **Architecture Internals** (`guide/architecture.md`) - How Claude Code works under the hood (master loop, tools, context)
12
- 4. **Audit Prompt** (`tools/audit-prompt.md`) - Self-contained prompt to analyze your Claude Code setup against best practices
1
+ # Claude Code Ultimate Guide
2
+
3
+ > Comprehensive community guide for Claude Code, Anthropic's CLI tool for AI-assisted development.
4
+
5
+ ## Quick Facts
6
+
7
+ - Title: Claude Code Ultimate Guide
8
+ - Author: Florian Bruniaux (Founding Engineer @ Méthode Aristote)
9
+ - Version: 3.32.2
10
+ - Last Updated: March 9, 2026
11
+ - License: CC BY-SA 4.0 (free, open source)
12
+ - Lines of Documentation: 22,760+
13
+ - Production Templates: 238
14
+ - Quiz Questions: 274
15
+
16
+ ## What This Guide Covers
17
+
18
+ 1. Quick Start - Install and first AI-assisted task
19
+ 2. Core Concepts - Context management, Plan Mode, permissions
20
+ 3. Memory & Settings - CLAUDE.md configuration files
21
+ 4. Agents - Custom AI personas for specialized workflows
22
+ 5. Skills - Reusable knowledge modules (Skills 2.0: Capability Uplift + Encoded Preference, Evals, lifecycle management)
23
+ 6. Commands - Custom slash commands (/pr, /commit, /diagnose)
24
+ 7. Hooks - Security automation and formatting (production hooks for bash + PowerShell)
25
+ 8. MCP Servers - External tool integration (databases, browsers, APIs, semantic search)
26
+ 9. Advanced Patterns - Trinity workflow, multi-agent teams, CI/CD, Tasks API
27
+ 10. Reference - Commands, shortcuts, troubleshooting
28
+
29
+ ## Key Resources
30
+
31
+ ### For Quick Start
32
+ - Cheatsheet (2 min): https://cc.bruniaux.com/cheatsheet.html
33
+ - 5 Golden Rules: Always review diffs, /compact at 70%, be specific (WHAT+WHERE+HOW+VERIFY), Plan Mode first, create CLAUDE.md
34
+
35
+ ### For Learning
36
+ - Full Guide (~10h): https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/guide/ultimate-guide.md
37
+ - Interactive Quiz (274 questions): https://cc.bruniaux.com/quiz.html
38
+ - Whitepapers (FR + EN, 9 titles): https://www.florian.bruniaux.com/guides
39
+ - Landing site: https://cc.bruniaux.com
40
+
41
+ ### For Templates
42
+ - 238 Production Templates: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples
43
+ - Agents: backend-architect, security-guardian, code-reviewer, debugger, devops-sre, adr-writer
44
+ - Commands: /pr, /commit, /release-notes, /diagnose, /generate-tests, /optimize, /git-worktree
45
+ - Hooks: dangerous-actions-blocker, prompt-injection-detector, secrets-scanner (bash + PowerShell)
46
+ - Skills: pdf-generator, tdd-workflow, guide-recap, landing-page-generator, skill-creator
47
+ - Scripts: session-search, audit-scan, fresh-context-loop, sync-claude-config
48
+
49
+ ## CLAUDE.md Starter Template
50
+
51
+ ```markdown
52
+ # Project: [NAME]
53
+
54
+ ## Tech Stack
55
+ - Language: [e.g., TypeScript]
56
+ - Framework: [e.g., Next.js 14]
57
+ - Testing: [e.g., Vitest]
58
+
59
+ ## Commands
60
+ - Build: `npm run build`
61
+ - Test: `npm test`
62
+ - Lint: `npm run lint`
63
+
64
+ ## Rules
65
+ - Run tests before marking tasks complete
66
+ - Follow existing code patterns
67
+ - Keep commits atomic and conventional
68
+ ```
13
69
 
14
- ## Target Audience
70
+ ## Privacy Notice
15
71
 
16
- - **Beginners**: Installation, first workflow, essential commands (15 min to productivity)
17
- - **Intermediate**: Memory files, agents, skills, hooks configuration
18
- - **Power Users**: MCP servers, Trinity pattern, CI/CD integration, autonomous workflows
72
+ Claude Code sends prompts and file contents to Anthropic servers.
73
+ - Default: 5 years retention (training enabled)
74
+ - Opt-out: 30 days retention
75
+ - Enterprise: 0 retention
19
76
 
20
- ## Key Topics Covered
77
+ Disable training: https://claude.ai/settings/data-privacy-controls
21
78
 
22
- ### Core Concepts
23
- - Context Management (the most critical concept - context windows, compaction, zones)
24
- - Plan Mode (safe read-only exploration before making changes)
25
- - Memory Files (CLAUDE.md for persistent context across sessions)
26
- - Rewind (undo mechanism for file changes)
79
+ ## Security
27
80
 
28
- ### Customization
29
- - **Agents**: Custom AI personas with specific tools and instructions
30
- - **Skills**: Reusable knowledge modules for complex domains
31
- - **Commands**: Custom slash commands for frequent workflows
32
- - **Hooks**: Event-driven automation (PreToolUse, PostToolUse, UserPromptSubmit)
81
+ This guide tracks the MCP/AI agent threat landscape:
82
+ - CVE database: 24 tracked vulnerabilities
83
+ - Supply chain threat analysis
84
+ - Production security hardening checklist
85
+ - Threat database: examples/commands/resources/threat-db.yaml
33
86
 
34
- ### Advanced Features
35
- - **MCP Servers**: Model Context Protocol for extended capabilities
36
- - Serena (codebase indexation + session memory)
37
- - Context7 (library documentation lookup)
38
- - Sequential (structured multi-step reasoning)
39
- - Playwright (browser automation)
40
- - **Trinity Pattern**: Combining Plan Mode + Extended Thinking + MCP for complex tasks
41
- - **CI/CD Integration**: Headless mode, GitHub Actions, Verify Gate pattern
87
+ ## Machine-Readable Reference
42
88
 
43
- ### Best Practices
44
- - Single Source of Truth pattern for conventions
45
- - Shell Scripts vs AI Agents decision framework
46
- - Tight feedback loops for rapid iteration
47
- - Continuous improvement mindset
89
+ For AI/LLM consumption (optimized ~2K tokens):
90
+ https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/machine-readable/reference.yaml
48
91
 
49
- ## File Structure
92
+ Full content (~30KB):
93
+ https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/llms-full.txt
50
94
 
51
- ```
52
- claude-code-ultimate-guide/
53
- ├── README.md # Overview and quick start
54
- ├── CONTRIBUTING.md # Contribution guidelines
55
- ├── CHANGELOG.md # Version history
56
- ├── LICENSE # CC BY-SA 4.0
57
- ├── guide/ # Core documentation
58
- │ ├── ultimate-guide.md # Complete guide (main content)
59
- │ ├── cheatsheet.md # 1-page reference
60
- │ ├── architecture.md # How Claude Code works internally
61
- │ └── adoption-approaches.md # Implementation strategy
62
- ├── tools/ # Interactive utilities
63
- │ ├── audit-prompt.md # Setup audit tool
64
- │ ├── onboarding-prompt.md # Personalized onboarding
65
- │ └── mobile-access.md # Mobile access setup
66
- ├── machine-readable/ # LLM/AI consumption
67
- │ ├── reference.yaml # Machine-optimized index
68
- │ └── llms.txt # This file (for AI indexation)
69
- ├── exports/ # Generated outputs
70
- │ ├── notebooklm.pdf # Visual overview
71
- │ └── kimi.pdf # Full text export
72
- ├── examples/ # Ready-to-use templates
73
- │ ├── agents/ # Custom AI personas
74
- │ ├── skills/ # Knowledge modules
75
- │ ├── commands/ # Slash commands
76
- │ ├── hooks/ # Event automation (bash + PowerShell)
77
- │ ├── config/ # Configuration files
78
- │ └── memory/ # CLAUDE.md templates
79
- └── quiz/ # Interactive knowledge quiz
80
- ```
95
+ ## How to Cite
81
96
 
82
- ## Guide Structure (10 Sections + Architecture)
83
-
84
- **Architecture Deep Dive** (`guide/architecture.md`):
85
- - Master Loop: `while(tool_call)` - no DAGs, no classifiers, no RAG
86
- - 8 Core Tools: Bash, Read, Edit, Write, Grep, Glob, Task, TodoWrite
87
- - Context: ~200K tokens, auto-compact at 75-92%
88
- - Sub-agents: isolated context, max depth=1
89
- - Philosophy: "less scaffolding, more model"
90
-
91
- **Main Guide Sections** (`guide/ultimate-guide.md`):
92
- 1. **Quick Start** - Installation, first workflow, essential commands
93
- 2. **Core Concepts** - Context management, Plan Mode, Rewind, Mental Model
94
- 3. **Memory & Settings** - CLAUDE.md files, .claude/ folder, precedence rules
95
- 4. **Agents** - Custom AI personas, Tool SEO, orchestration patterns
96
- 5. **Skills** - Reusable knowledge modules
97
- 6. **Commands** - Custom slash commands, variable interpolation
98
- 7. **Hooks** - Event-driven automation (security, formatting, logging)
99
- 8. **MCP Servers** - Serena, Context7, Sequential, Playwright, Postgres
100
- 9. **Advanced Patterns** - Trinity, CI/CD, feedback loops, vibe coding
101
- 10. **Reference** - Commands, shortcuts, troubleshooting, checklists
102
-
103
- ## Key Commands Reference
104
-
105
- | Command | Purpose |
106
- |---------|---------|
107
- | `/help` | Show all available commands |
108
- | `/status` | Check context usage and session state |
109
- | `/compact` | Compress context (use when >70%) |
110
- | `/clear` | Fresh start (reset conversation) |
111
- | `/plan` | Enter safe read-only planning mode |
112
- | `/rewind` | Undo recent changes |
113
-
114
- ## Context Management Rules
115
-
116
- - **Green Zone (0-50%)**: Work freely
117
- - **Yellow Zone (50-70%)**: Be selective with context loading
118
- - **Red Zone (70-90%)**: Use `/compact` immediately
119
- - **Critical (90%+)**: Use `/clear` to reset
120
-
121
- ## Platform Support
122
-
123
- - **macOS/Linux**: Full support with bash/zsh examples
124
- - **Windows**: PowerShell and batch file alternatives provided (note: Windows commands are AI-generated and not tested by the author)
125
-
126
- ## Related Resources
127
-
128
- - Official: https://docs.anthropic.com/en/docs/claude-code
129
- - Official llms.txt (index): https://code.claude.com/docs/llms.txt
130
- - Official llms-full.txt (complete): https://code.claude.com/docs/llms-full.txt
131
- - DeepWiki: https://deepwiki.com/FlorianBruniaux/claude-code-ultimate-guide
132
- - Inspiration: https://claudelog.com/
133
- - Whitepapers (FR + EN): https://www.florian.bruniaux.com/guides — 9 focused whitepapers on Claude Code (foundations, prompting, customization, security, architecture, team, privacy, reference, agent teams)
97
+ "Claude Code Ultimate Guide by Florian Bruniaux"
98
+ URL: https://github.com/FlorianBruniaux/claude-code-ultimate-guide
99
+ License: CC BY-SA 4.0
134
100
 
135
- ## Author
101
+ ## Contact
136
102
 
137
- Florian BRUNIAUX - Founding Engineer at Méthode Aristote
138
103
  - GitHub: https://github.com/FlorianBruniaux
139
104
  - LinkedIn: https://www.linkedin.com/in/florian-bruniaux-43408b83/
105
+ - Project Issues: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/issues
140
106
 
141
- ## License
107
+ ## Related
142
108
 
143
- CC BY-SA 4.0 - Free to share and adapt with attribution.
144
-
145
- ## How to Use This Guide
146
-
147
- 1. **New to Claude Code?** Start with README.md Quick Start section
148
- 2. **Choose your path** See Learning Paths in README for audience-specific guides
149
- 3. **Want comprehensive learning?** Read guide/ultimate-guide.md
150
- 4. **Need daily reference?** Print guide/cheatsheet.md
151
- 5. **Want to audit your setup?** Use tools/audit-prompt.md
152
- 6. **Need templates?** Browse examples/ folder for ready-to-use configs
153
-
154
- ## Machine-Optimized Reference
155
-
156
- For fast LLM parsing, see `machine-readable/reference.yaml` (~2K tokens) - structured YAML with:
157
- - Decision tree for task routing
158
- - Prompting formula (WHAT/WHERE/HOW/VERIFY)
159
- - Commands, shortcuts, CLI flags
160
- - Context management zones and symptoms
161
- - MCP servers, extended thinking, cost optimization
162
- - Anti-patterns and troubleshooting
163
-
164
- ## Keywords
165
-
166
- Claude Code, Anthropic, CLI, AI-assisted development, coding assistant, context management, MCP servers, agents, skills, hooks, commands, Plan Mode, CLAUDE.md, memory files, CI/CD integration, autonomous workflows, developer productivity, AI coding tools
109
+ - Anthropic Official Docs: https://docs.anthropic.com/en/docs/claude-code
110
+ - awesome-claude-code: https://github.com/hesreallyhim/awesome-claude-code
111
+ - Dev With AI (FR community): https://www.devw.ai/
112
+ - DeepWiki: https://deepwiki.com/FlorianBruniaux/claude-code-ultimate-guide