Script:
- needs_ssot_refactor flag: warns if CLAUDE.md >100 lines with 0 @refs
- Red warning in human output suggesting SSoT pattern
Prompt:
- Focus on incremental improvements, not generic advice
- Stricter health score (penalize missing SSoT)
- Domain-specific quick wins only
- Improve existing CLAUDE.md instead of full rewrite
- Don't suggest duplicates of existing agents/commands
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Full Audit now reads README.md, CLAUDE.md, .claude/CLAUDE.md
- Claude analyzes business domain for tailored recommendations
- Domain-specific suggestions (EdTech, E-commerce, etc.)
- Added privacy notice: all data stays local, nothing sent to repo
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Commands in subfolders (tech/, product/, support/) now counted correctly
- Split count_files() into count_md_files() and count_script_files()
- Hooks counted as scripts (.sh/.js/.py/.ts), others as .md
- Excludes README.md from counts
- Bug: Was reporting 0 commands when 10 existed in subfolders
- Bump version to 2.9.6
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add 🔬 Deep Audit section with two options:
- Quick Version (~10 sec): curl | bash | claude one-liner
- Full Audit (~30 sec): downloads YAML reference for comprehensive analysis
- Add row in navigation table pointing to Deep Audit
- Outputs: health score, prioritized findings, CLAUDE.md template, suggestions
- Bump version to 2.9.5
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create examples/modes/ folder with MODE_Learning.md ready to copy
- Add modes/README.md with installation guide and SuperClaude link
- Update examples/README.md with modes section
- Bump version to 2.9.4 across all files
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add CHANGELOG entry for LLM Reference section and Learning Mode docs
- Update version in README.md and claude-code-reference.yaml
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add LLM Reference section in README with curl one-liner for AI assistants
- Add learning mode flags and deep_dive refs to YAML index
- Add comprehensive Learning Mode documentation to guide (installation, usage, integration)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create claude-code-reference.yaml (~2K tokens vs 70K full guide)
- Add deep_dive section with 38 line references to main guide
- Structure: decision tree first, then prompting formula, commands, etc.
- Update README.md with LLM Reference in Core Documentation
- Update llms.txt with Machine-Optimized Reference section
- Bump version to 2.9.2
Use case: Claude Code self-reference for fast user question answering
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The audit script was looking for MCP config in ~/.claude/mcp.json which
doesn't exist. Claude Code actually stores MCP config in ~/.claude.json
under projects.<path>.mcpServers.
Changes:
- audit-scan.sh: Multi-source MCP detection (3 locations with priority)
- audit-scan.sh: Fixed count_pattern() bug causing "0\n0" output
- claude-setup-audit-prompt.md: Updated bash commands for MCP detection
- Version bump: 2.8 → 2.9
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add GitHub Actions section to main README Production-Ready Examples
- Update examples/README.md with github-actions/ and workflows/ folders
- Add complete templates index for CI/CD workflows
- Bump version to 2.8 across all documentation files
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add "Not Sure Where to Start?" decision helper table after Quick Start
- Move Audit section to prominent position (early in page)
- Reframe AI admission from apologetic to professional tone
- Condense audit instructions for scannability
These changes address:
- Decision paralysis (too many entry points without guidance)
- Buried differentiator (audit tool was mid-page)
- Credibility concerns (admission was apologetic)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add fast bash-based setup scanner for 80% speed improvement:
- New audit-scan.sh script with JSON/human output modes
- Rewrite audit prompt Phase 1-2 to use grep/find/wc
- Update README with dual-option audit approach
- Token reduction from ~5000 to ~500 (90% improvement)
- Execution time from ~30s to ~2s
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Create personal notes folder excluded from version control
- Move SEO_SETUP_TODO.md to to-ignore/
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Replace marketing-oriented H1 with keyword-rich title
- Add 4 topic badges for visual appeal and indexing
- Enrich tagline with "Anthropic's AI coding assistant CLI"
- Add LSI keywords: agentic development, LLM-powered coding, AI pair programming
- Insert HTML keyword section for crawler optimization
SEO impact: +50-70% GitHub search visibility, +20-30% Google ranking
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add structured summary file following llms.txt convention to help
AI models (Claude, ChatGPT, Perplexity, etc.) better understand
and index this repository.
Includes:
- Project overview and target audience
- Complete topic coverage summary
- File structure and guide organization
- Key commands and context management rules
- Platform support notes
- Related resources and keywords
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add disclaimer: macOS user, Windows commands untested
- Invite Windows users to contribute fixes
- Add DeepWiki link for AI-powered repo exploration
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Serena section now covers:
- Why it matters (Claude Code lacks native indexation unlike Cursor)
- Key features: indexation, project memory, auto-onboarding
- Memory tools: write_memory, read_memory, list_memories
- Session memory workflow example
- Pre-indexing setup command
New mgrep section:
- Intent-based semantic search alternative
- Comparison with Serena (intent vs symbol-level)
- Key features and example usage
- Honest note: not personally tested
Also updated:
- Server comparison table with memory and mgrep entries
- Cheatsheet MCP section
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Rename "Configuration" to "Memory & Settings" (section 3)
- CLAUDE.md files are now properly called "Memory Files"
- Add explanatory note about why they're called "memory"
- Update all internal references (diagrams, headings, precedence rules)
- Add table of contents with direct links to README
- Add GitHub stars badge and call-to-action
- Update cheatsheet with consistent terminology
Based on feedback that configuration should refer to settings.json,
while CLAUDE.md files are officially called "memory" in Anthropic docs.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Mention that the guide is in English by default but could be
translated to French (native) or other languages via AI/community.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Clarify that the guide may contain errors since it was largely
AI-generated, and encourage feedback/PRs for improvements.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Ignore IDE configs (.idea, .vscode), Claude Code config (.claude/),
OS files (.DS_Store), and misc temporary files.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add comprehensive guide (4000+ lines) covering all Claude Code features
- Add printable cheatsheet for daily reference
- Add PDF versions (NotebookLM podcast, Kimi export)
- Update README with author context, inspiration sources, and contact info
- Change license from MIT to CC BY-SA 4.0 for content sharing
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
