Phase 0 - Foundation work for visibility campaign:
- Add TL;DR Quick Start section in README with CLAUDE.md template
- Rewrite CONTRIBUTING.md with welcome message, contribution types, PR process
- Add CODE_OF_CONDUCT.md (Contributor Covenant v2.1)
- Document French whitepapers series (8 docs, ~185 pages) in README
- Add distribution playbooks in claudedocs/ (gitignored)
- Add prominent badges (version, license, Claude Code support)
TTFV (Time-to-First-Value) optimized from ~10min to < 5min.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- French-speaking community for developers (~1500 on Slack)
- Meetups in Paris, Bordeaux, Lyon
- Placed near top of README for visibility
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add "Performance vs Traditional Tools" section with timing comparison
- Update decision tree with "Know exact pattern?" branch
- Update Server Comparison table with exact match recommendation
- Document key insight: grepai finds what pattern-based tools cannot
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add communication tone preference (pedagogical/direct/coaching/adaptive)
- Extend style preference to all goals at 15min threshold
- Add "reset" option for mid-journey preference changes
- Add "skip" shows what's being skipped
- Add fallback roadmap when reference.yaml fetch fails
- Add multi-LLM compatibility footnote (works on ChatGPT, Gemini, etc.)
- Update reference.yaml with tone question and question_flow
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add new section 8 with IP disclaimer and key considerations table
- Cover: ownership, license contamination, vendor indemnification, sector compliance
- Bump version to 3.7.1
- Update .gitignore to exclude .grepai/
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add new section based on Addy Osmani's analysis of 2,500+ agent configs:
- Six essential components for specs (commands, testing, structure, style, git, boundaries)
- Permission tiers system (Always/Ask/Never)
- Curse of Instructions warning (more rules = worse adherence)
- Monolithic vs Modular decision table
Source: https://addyosmani.com/blog/good-spec/
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Bug fixes on top of v2.0:
- json_escape() function: proper backslash/quote escaping
- Preview cleanup: strip XML tags (<local-command-caveat>)
- Filter non-printable unicode characters
Quality score: 8/10 → 9.3/10
Tested with 239 sessions, all features validated.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Phase 4 wrap-up now provides:
- Direct GitHub links for quiz, cheatsheet, full guide
- Section-specific link format with line anchors (#L{line})
- Privacy guide link updated
Improves UX for users running onboarding via one-liner (no local repo)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
User has Perplexity Pro license - Claude can request advanced
searches for reliable sources on Claude Code, Anthropic updates,
and AI-assisted development best practices.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
README.md:
- Added security-hardening.md to Core Documentation table
- Added to "Not Sure Where to Start?" section
- Added to Power User learning path
machine-readable/reference.yaml:
- Added onboarding_matrix for personalized learning paths
- Added onboarding_questions structure for interactive profiling
tools/onboarding-prompt.md:
- Restructured for goal-based profiling (2 questions → tailored content)
- Simplified from assessment-heavy to action-oriented flow
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create VERSION file (3.6.0) as the canonical version source
- Add scripts/sync-version.sh for automated version synchronization
- Fix version inconsistencies in cheatsheet.md and ultimate-guide.md
- Script supports --check mode for CI validation
Usage: ./scripts/sync-version.sh [--check]
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- README.md: add to Core Documentation, Not Sure Where to Start?, Power User path
- guide/README.md: add to Contents table
- CHANGELOG.md: update Unreleased section
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Repository Structure: add guide/workflows/, examples/modes/, config/, memory/
- Core Documentation: add methodologies.md, workflows/, data-privacy.md, observability.md
- Slash Commands: add generate-tests, review-pr, git-worktree, validate-changes
- Security Hooks: add 2 hooks + link to complete catalog
- Not Sure Where to Start?: add 5 navigation entries
- By Role Paths: enhance all 4 paths with new resources
- SEO Keywords: add 9 keywords for discoverability
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add guide/methodologies.md: index of 15 methodologies with decision tree
- Add guide/workflows/: 4 practical workflow guides
- tdd-with-claude.md: TDD with Claude-specific patterns
- spec-first.md: SDD adapted for CLAUDE.md
- plan-driven.md: effective /plan mode usage
- iterative-refinement.md: prompt→feedback→reprompt loops
- Add Section 9.14 in ultimate-guide.md linking to workflows
- Update guide/README.md with new documentation
- Bump version 3.4.0 → 3.5.0 across all files
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- IDEAS.md: Reduce from 12 to 4 actionable research topics
- Unified "MCP Security Hardening" (merged 3 overlapping topics)
- Expanded Discarded section (3 → 16 entries with justifications)
- Technical writer agent validation against reference.yaml
- Version bump: 3.3.0 → 3.3.1 across all docs
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- New mobile-access-setup.md with ToS-safe remote access solution
- ttyd exposes terminal via browser, Tailscale provides secure VPN
- Complete setup script with tmux for persistent sessions
- Marked as WIP/UNTESTED - community feedback welcome
- Added to README navigation table
- Version bump 3.0.6 → 3.0.7
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- New adoption-approaches.md (~355 lines) with decision tree, turnkey quickstart,
autonomous learning path, adoption checkpoints, anti-patterns, team guidelines
- README.md: Added to "Not Sure Where to Start?" navigation
- Addresses feedback: "turnkey setup" vs "autonomous learning" philosophies
- Aligns with claude-code-reference.yaml patterns (decision trees, line refs)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- english-ultimate-claude-code-guide.md: new "Custom Statusline Setup" section
- ccstatusline as recommended solution
- Custom script option with JSON stdin format
- cheatsheet-en.md: added statusline quick reference
- Version bump to 3.0.2 across files
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- New personalized-onboarding-prompt.md (~200 lines)
- Multilingual: user chooses language first
- 3 experience levels (Beginner/Intermediate/Power User)
- Progressive exploration with deeper/next/skip controls
- Tailored learning paths per level
- Optional practical exercises
- README.md: new row in "Not Sure Where to Start?" table
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
BREAKING: Major version release with new quiz feature
New Features:
- Interactive CLI quiz with 159 curated questions
- 4 user profiles: Junior, Senior, Power User, Product Manager
- 10 topic categories covering all guide sections
- Immediate feedback with explanations and doc references
- Session persistence to ~/.claude-quiz/
- Score tracking with category breakdown
- Optional dynamic question generation via claude -p
- Cross-platform support (Node.js): macOS, Linux, Windows
Quiz highlights:
- Profile-based question filtering and difficulty weighting
- Retry wrong questions only or new quiz options
- Visual progress bar and score visualization
- Direct documentation links for wrong answers
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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>
