marketing-shibata50/claude-code-ultimate-guide
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
240 commits 1 branch 0 tags 20 MiB
Commit graph

100 commits

Author SHA1 Message Date
Florian BRUNIAUX
d5375e32a5 docs: add 2 resource evaluations (Osmani LinkedIn + Beyond Vibe Coding) 
Added:
- Resource Evaluation: Addy Osmani LinkedIn Post (scored 2/5, Marginal)
  - Post about Anthropic study (17% comprehension gap)
  - 100% overlap with Shen & Tamkin 2026 already documented
  - Decision: Tracking mention only (mainstream diffusion timeline)
  - New criterion: "Influencer Amplification" pattern documented

- Resource Evaluation: "Beyond Vibe Coding" Book (scored 3/5, Pertinent)
  - Comprehensive O'Reilly book by Addy Osmani
  - 90% overlap analysis (10/14 topics covered 100%)
  - Decision: Minimal integration (tracking mention + cross-refs)
  - Cross-validation with 2 Osmani articles already integrated

Updated:
- CHANGELOG.md: [Unreleased] section with detailed entries
- README.md: Resource evaluations count (36 → 38 assessments)

Files created:
- docs/resource-evaluations/addy-osmani-linkedin-anthropic-study.md
- docs/resource-evaluations/beyond-vibe-coding.md
- docs/resource-evaluations/nick-tune-feedback-loops.md

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-01 23:30:03 +01:00
Florian BRUNIAUX
fdee3305c5 docs: RTK documentation update - upstream + fork integration 
- Update guide/ultimate-guide.md: RTK section (l.11084-11174)
  - Two repositories: upstream (stable) + fork (extended features)
  - Fork features: vitest, pnpm, prisma, gain, discover
  - Bug fixes documented (grep/ls fixed in fork)
  - Installation options: cargo, fork, binary

- Add guide/third-party-tools.md: RTK card (l.86)
  - Comparison upstream vs fork
  - Token savings: 70-90% depending on stack
  - Cross-reference to ultimate-guide Section 9

- Update machine-readable/reference.yaml:
  - rtk_upstream + rtk_fork_extended (two repos)
  - third_party_tools_rtk entry added
  - Line numbers updated

- Update docs/resource-evaluations/rtk-evaluation.md:
  - UPDATE 2026-02-01 section with fork comparison
  - Fork features table (JS/TS stack support)
  - Installation instructions for fork

Total: 4 files, ~320 lines modified

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-01 22:20:43 +01:00
Florian BRUNIAUX
9f9f735436 release: v3.20.7 - Addy Osmani spec-writing integration 
Version Bump:
- VERSION: 3.20.6 → 3.20.7
- CHANGELOG.md: New [3.20.7] section with Osmani integration details
- Synced across: README.md, cheatsheet.md, ultimate-guide.md, reference.yaml

Release Highlights:
- Addy Osmani spec-writing evaluation (4/5, High Value)
- 4 new sections in spec-first.md (Modular Design, Operational Boundaries, Command Templates, Anti-Monolithic)
- 180 lines added to spec-first.md (327 → 507)
- 8 new reference.yaml entries
- 1 new resource evaluation (36 total)

Integration Details (see CHANGELOG.md):
- Modular spec design pattern (split >200 line CLAUDE.md files)
- Always/Ask First/Never operational boundaries framework
- Command spec templates with error handling
- Anti-pattern: monolithic CLAUDE.md context pollution

Landing Sync: Ready for deployment (version updated in separate commit)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-01 21:48:29 +01:00
Florian BRUNIAUX
a5942f1c53 docs: add Addy Osmani spec-writing evaluation (4/5) + spec-first.md sections 
Integration of "How to write a good spec for AI agents" by Addy Osmani:

Evaluation (docs/resource-evaluations/addy-osmani-good-spec.md):
- Score: 4/5 (High Value - Integrate within 1 week)
- Fills gaps: modular design, operational boundaries, command specs
- Fact-checked: credentials verified via Perplexity, all claims sourced
- Challenge phase: technical-writer agent corrected initial 3/5 → 4/5

Spec-First Workflow Updates (guide/workflows/spec-first.md):
- NEW: "Modular Spec Design" section (~50 lines, line 322)
  Pattern: Split large specs into focused files (CLAUDE-[domain].md)
- NEW: "Operational Boundaries" section (~60 lines, line 372)
  Three-tier system: Always/Ask First/Never → maps to Claude Code modes
- NEW: "Command Spec Template" section (~40 lines, line 432)
  Executable command specs with expected outputs & error handling
- NEW: "Anti-Pattern: Monolithic CLAUDE.md" section (~30 lines, line 472)
  Explains cognitive load problem (>200 lines = context pollution)

Reference Index (machine-readable/reference.yaml):
- 8 new entries: spec_first_workflow → spec_osmani_score
- Links to new spec-first.md sections with line numbers
- Source attribution: https://addyosmani.com/blog/good-spec/

Public Facing (README.md):
- Incremented resource evaluations count: 35 → 36

File growth: spec-first.md 327 → 507 lines (+180)
Source: Addy Osmani (former Chrome team, 14y), published Jan 13, 2026

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-01 21:30:34 +01:00
Florian BRUNIAUX
bc86c8ed7f release: v3.20.6 - agentskills.io integration + 4 resource evaluations 
- agentskills.io open standard: frontmatter table, skills-ref CLI, portability section
- Agent Skills supply chain risks (security-hardening.md §1.2)
- anthropics/skills (60K+★) added to complementary resources
- 16 new reference.yaml entries
- Resource evaluations: agentskills.io (4/5), Skill Doctor (2/5), dclaude (new), paddo (new)
- Sandbox isolation + README updates

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-02-01 16:49:33 +01:00
Florian BRUNIAUX
59ba1ae174 release: v3.20.5 - 4 new ASCII diagrams (visual-reference.md) 
- Add visual-reference.md with 20 ASCII diagrams (16 existing + 4 new)
  - #17 TDD Red-Green-Refactor Cycle
  - #18 UVAL Protocol Flow
  - #19 Security 3-Layer Defense
  - #20 Secret Exposure Timeline
- Add Visual Reference to README Core Documentation table
- Version sync: 3.20.4 → 3.20.5

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-31 23:14:41 +01:00
Florian BRUNIAUX
a7962d5560 release: v3.20.4 - 30 new quiz questions (227 → 257) 
Add 30 questions across 11 categories covering recent guide content:
Advanced Patterns (+8), MCP Servers (+3), Architecture (+3),
Reference (+3), Hooks (+2), Learning (+2), Security (+2),
AI Ecosystem (+3), Memory (+2), Agents (+1), Privacy (+1).

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-31 22:17:32 +01:00
Florian BRUNIAUX
2fcc65e222 release: v3.20.3 - Competitive Analysis Gaps (claudelog.com) 
9 gaps filled from claudelog.com competitive analysis (313 pages):
- Section 9.19: Permutation Frameworks (CLAUDE.md-driven variation testing)
- Skeleton Projects workflow (guide/workflows/skeleton-projects.md)
- Task Lists as Diagnostic Tool (instruction clarity mirror)
- Rev the Engine + Mechanic Stacking (multi-round planning patterns)
- Split-Role Sub-Agents (multi-perspective analysis)
- "You Are the Main Thread" mental model (CPU scheduler analogy)
- Continuous Context Update (proactive CLAUDE.md enrichment)
- Smart Hook Dispatching (single entry point routing to handlers)

Guide: 15,771 → 16,293 lines (+522)
New workflow: skeleton-projects.md (208 lines)
Reference: +17 new entries in reference.yaml

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-31 21:55:12 +01:00
Florian BRUNIAUX
950370e81b release: v3.20.2 - Sandbox Isolation for Coding Agents 
New guide file covering Docker Sandboxes (microVM isolation),
cloud alternatives (Fly.io Sprites, E2B, Vercel, Cloudflare),
safe autonomy workflows, and comparison matrix.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-31 19:08:25 +01:00
Florian BRUNIAUX
3ab6fe3ef5 docs: track Claude Code v2.1.27 release 
--from-pr flag for PR-linked sessions, auto PR linking via gh pr create,
Bedrock/Vertex gateway fixes.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-31 16:19:51 +01:00
Florian BRUNIAUX
22f2b91b83 docs: integrate Contribution Metrics blog (4/5) - Anthropic Jan 2026 data 
New subsection in ultimate-guide.md with +67% PRs merged and 70-90%
AI-assisted code metrics. Separate from Aug 2025 study (different
methodology: PR-based vs self-reported). ROI cross-reference added.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-30 23:34:15 +01:00
Florian BRUNIAUX
26ee4ef894 release: v3.20.1 - Vercel AGENTS.md vs Skills evaluation 
- New resource evaluation (025): Vercel blog on eager context vs lazy
  skill invocation (Gao, Jan 2026). Score 3/5, 13/13 fact-checked.
- Guide: added 8KB compression benchmark to CLAUDE.md sizing (line 3527)
- Guide: added 56% skill invocation warning to Memory Loading (line 4082)
- Guide: added invocation reliability caveat to skills.sh trade-offs
- Version sync 3.20.0 → 3.20.1

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-30 21:45:14 +01:00
Florian BRUNIAUX
fd4550cbd3 release: v3.20.0 - Multi-Agent Code Review Automation 
Integration of production-grade PR review patterns from Pat Cullen + Méthode Aristote.

New Features:
- Resource evaluation: Pat Cullen Final Review (5/5 - Critical)
- Enhanced /review-pr: +150 lines with Advanced Multi-Agent Review section
- Enhanced code-reviewer agent: +219 lines with anti-hallucination rules
- New workflow: Review Auto-Correction Loop in iterative-refinement.md
- Production example: Multi-Agent Code Review in ultimate-guide.md
- Reference updates: +3 entries (review_pr_advanced, review_anti_hallucination, review_auto_fix_loop)

Key Patterns:
- 3 specialized agents: Consistency, SOLID, Defensive Code Auditor
- Pre-flight check: git log Co-Authored-By detection
- Anti-hallucination: Grep/Glob verification before suggestions
- Severity classification: 🔴 Must Fix / 🟡 Should Fix / 🟢 Can Skip
- Convergence loop: review → fix → re-review (max 3 iterations)
- Conditional context loading: stack-agnostic decision table

Design Principles:
- Enrich existing files (no fragmentation)
- No breaking changes (review-pr.md template simple preserved)
- Complete attribution (Pat Cullen + Méthode Aristote with links)
- Audience-aware (beginner → advanced progression)

Files Modified:
- CHANGELOG.md, VERSION: bumped to 3.20.0
- docs/resource-evaluations/017-pat-cullen-final-review.md: NEW (120 lines)
- examples/commands/review-pr.md: 80 → 230 lines (+150)
- examples/agents/code-reviewer.md: 72 → 291 lines (+219)
- guide/workflows/iterative-refinement.md: 389 → 522 lines (+133)
- guide/ultimate-guide.md: +28 lines (Production Example section)
- machine-readable/reference.yaml: +3 entries
- README.md, guide/cheatsheet.md: version sync

Total: +537 insertions, 0 deletions (no breaking changes)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-30 16:07:09 +01:00
Florian BRUNIAUX
8b58f014e7 docs: add Addy Osmani 80% problem to Practitioner Insights 
Add Addy Osmani (Google Chrome Team) article "The 80% Problem in
Agentic Coding" to AI Ecosystem Practitioner Insights section.

Changes:
- guide/ai-ecosystem.md: Add 32-line entry after Steinberger (~line 2024)
  * "80% problem" framework and comprehension debt concept
  * Three new failure modes (overengineering, assumption propagation, sycophantic)
  * Productivity paradox data (+98% PRs, +91% review time)
  * Alignment table mapping to existing guide sections
  * Transparent note: "secondary synthesis, primary sources documented"

- machine-readable/reference.yaml: Add 4 new references
  * practitioner_addy_osmani, practitioner_osmani_source
  * eighty_percent_problem, comprehension_debt_secondary

- docs/resource-evaluations/024-addy-osmani-80-percent-problem.md: Complete evaluation
  * Score: 3/5 (Pertinent) - downgraded from initial 4/5 after technical-writer challenge
  * Minimal integration (32 lines vs rejected 250 lines)
  * Fact-check: 6 stats verified, 1 Stack Overflow stat incorrect
  * Rationale: 90% overlap with existing content (Vibe Coding Trap, Trust Calibration)

- CHANGELOG.md: Document addition in v3.19.0

Decision: Minimal integration approach chosen to avoid duplication while
recognizing value of synthesis from respected author. Article aggregates
existing research already cited in guide with primary sources.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-30 12:32:38 +01:00
Florian BRUNIAUX
7df11b224f release: v3.18.2 - Steinberger Practitioner Insight 
Add Peter Steinberger (PSPDFKit Founder, Moltbot Creator) to Practitioner
Insights with model-agnostic workflow patterns.

Changes:
- Add Steinberger entry in guide/ai-ecosystem.md (stream monitoring,
  multi-project juggling, fresh context validation, iterative exploration)
- Complete evaluation in docs/resource-evaluations/steinberger-inference-speed.md
  (score 3/5, fact-checked GPT-5.2, validated credentials)
- Update docs/resource-evaluations/README.md (15→16 evaluations)
- Add practitioner_steinberger references in machine-readable/reference.yaml
- Version bump 3.18.1 → 3.18.2 (VERSION + sync all docs)
- Update CHANGELOG.md with detailed v3.18.2 entry
- Update README.md evaluations count (22→25)

Scope: Model-agnostic patterns only, zero model comparisons.
Source: https://steipete.me/posts/2025/shipping-at-inference-speed

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-30 09:49:55 +01:00
Florian BRUNIAUX
c844f74c8f docs: update Claude Code releases to v2.1.25 
- Add v2.1.25: Fixed beta header validation for Bedrock/Vertex
- Add v2.1.23: Customizable spinner verbs, mTLS/proxy fixes, terminal performance

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-30 08:48:25 +01:00
Florian BRUNIAUX
97c4c7e5ae release: v3.18.0 - Known Issues Tracker & RTK Integration 
MAJOR ADDITIONS:

1. Known Issues Tracker (guide/known-issues.md, 285 lines)
   - GitHub issue auto-creation bug (Issue #13797, v2.0.65+, ACTIVE)
   - Excessive token consumption (Issue #16856, v2.1.1+, Jan 2026)
   - Model quality degradation (Aug-Sep 2025, RESOLVED)
   - Verified: 17+ accidental public disclosures, 20+ token reports
   - Fact-checked: Perplexity Pro + GitHub API direct queries
   - Impact: Critical security awareness, actionable workarounds

2. RTK (Rust Token Killer) Integration
   - 72.6% average token reduction for git operations
   - Benchmarks: git log (92.3%), git status (76.0%), find (76.3%)
   - Templates: CLAUDE.md, skill, PreToolUse hook
   - Limitations documented: grep broken, ls worse, early-stage

FIXES:
- Corrected "mgrep" misattribution in Everything Claude Code evaluation

VERSION UPDATES:
- VERSION: 3.17.1 → 3.18.0
- Synced across README.md, cheatsheet.md, ultimate-guide.md, reference.yaml

FILES MODIFIED: 6 (CHANGELOG, VERSION, README, cheatsheet, guide, reference)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-28 18:20:05 +01:00
Florian BRUNIAUX
940caf3f1e docs: add verified critical bugs tracker (known-issues.md) 
NEW: guide/known-issues.md (285 lines)
- GitHub issue auto-creation bug (Issue #13797, v2.0.65+, ACTIVE)
  * 17+ confirmed accidental public disclosures
  * Security/privacy risk documented
  * Workarounds: explicit repo, manual approval, pre-execution verification
- Excessive token consumption (Issue #16856, v2.1.1+, Jan 2026)
  * 20+ reports of 4x+ faster consumption
  * Anthropic: "Not officially confirmed as bug" (investigating)
  * Workarounds: /context monitoring, shorter sessions, disable auto-compact
- Model quality degradation (Aug-Sep 2025, RESOLVED)
  * Anthropic official postmortem: 3 infrastructure bugs
  * Community theories (quantization) debunked

FACT-CHECKED: Perplexity Pro + GitHub API direct queries
- Verified: 5,702 open issues (not 4,697), 527 invalid labels
- Corrected: v2.1.1 token bug (not non-existent v2.0.61)
- Sources: GitHub Issues, Anthropic postmortem, The Register

UPDATED:
- guide/README.md: Added known-issues.md to docs table
- machine-readable/reference.yaml: 4 new entries for issue tracking
- CHANGELOG.md: Documented integration process

NEW: docs/resource-evaluations/023-community-discussions-report-jan2026.md
- Full evaluation process documented
- Fact-check methodology: Perplexity + GitHub API
- Score: 2/5 (Marginal - partial integration only)
- Lesson: Always verify community reports with primary sources

Impact: Critical security awareness for users, actionable workarounds

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-28 17:59:16 +01:00
Florian BRUNIAUX
a75c66a890 docs: update Claude Code releases to v2.1.22 
Added tracking for latest releases:
- v2.1.22: Task UI improvements, Vim fixes, LSP enhancements
- v2.1.21: Version requirements, TaskCreate enhancements, auto-update checks

Updated in both YAML (machine-readable) and Markdown (human-readable) formats.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-28 15:00:18 +01:00
Florian BRUNIAUX
4dc380efd2 docs: integrate RTK (Rust Token Killer) for command output optimization 
- Added Section 9.13 'Command Output Optimization with RTK' (guide/ultimate-guide.md:10478)
- Benchmarks: 72.6% avg token reduction (git log 92.3%, git status 76.0%, find 76.3%)
- Integration templates: CLAUDE.md, Skill, PreToolUse hook
- Evaluation: docs/resource-evaluations/rtk-evaluation.md (score 4/5)
- Limitations: grep broken (v0.2.0), ls worse (-274%), low adoption (8 stars)
- Updated CHANGELOG.md and machine-readable/reference.yaml
- Source: https://github.com/pszymkowiak/rtk v0.2.0
 2026-01-28 12:20:48 +01:00
Florian BRUNIAUX
34b7376408 fix: correct mgrep misattribution in Everything Claude Code evaluation 
Issue:
- Incorrectly claimed Everything Claude Code contained "mgrep (50% token reduction)" tool
- No such tool exists in affaan-m/everything-claude-code (verified via WebFetch + repo search)
- Confused mgrep (mixedbread-ai semantic search) with non-existent token reduction tool

Files corrected:
- docs/resource-evaluations/015-everything-claude-code-github-repo.md (14 occurrences removed)
- machine-readable/reference.yaml:724 (unique patterns list updated)
- guide/ultimate-guide.md:14821 (replaced with verified patterns)
- CHANGELOG.md (v3.17.0 and v3.15.0 entries updated)

Verified patterns now documented:
- hookify (conversational hooks)
- pass@k metrics (formal verification)
- sandboxed subagents (tool restrictions)
- strategic compaction skills (context management)

Impact: Maintains guide accuracy, prevents user confusion

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-28 09:50:07 +01:00
Florian BRUNIAUX
7957dda29c release: version 3.17.1 - README V3 with Repository Structure diagram 
### Added
- Repository Structure diagram (Mermaid + ASCII collapsible)
- 4 missing guides in Core Documentation table
- Quiz online link (landing site)

### Changed
- README V3: merged best of both versions (WHY/HOW positioning + complete sections)
- Ecosystem positioning: complementary instead of competitive
- Core Documentation: added AI Ecosystem, AI Traceability, Search Tools, Learning with AI

### Removed
- README-new.md (merged into README.md)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-27 18:30:18 +01:00
Florian BRUNIAUX
9055c31ee7 release: version 3.17.0 - Tasks API limitations documentation 
Version bump from 3.16.0 to 3.17.0 with Tasks API field visibility
limitations integration.

Changes:
- VERSION: 3.16.0 → 3.17.0
- CHANGELOG.md: Moved [Unreleased] to [3.17.0] - 2026-01-27
- README.md: Updated version footer, resource evaluations count (22)
- guide/cheatsheet.md: Updated version headers
- guide/ultimate-guide.md: Updated version
- machine-readable/reference.yaml: Updated version + date

Release highlights:
- 🚨 CRITICAL: Tasks API limitations documented (Gang Rui analysis)
  * TaskList field visibility constraints
  * 11x-51x cost overhead for N tasks
  * 3 workaround patterns provided
  * Prevents user frustration, maintains guide credibility

- 📊 Stats: 22 resource evaluations, 493 lines added
- 🎯 Impact: All Tasks API users (v2.1.16+) benefit from transparency

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-27 16:21:05 +01:00
Florian BRUNIAUX
3a5012eef7 docs: document Tasks API field visibility limitations (Gang Rui analysis) 
Integration of community practitioner feedback on Tasks API (v2.1.16+)
field visibility constraints discovered through real-world usage.

Changes:
- guide/ultimate-guide.md:
  * Added 3 rows to comparison table (field visibility, metadata, overhead)
  * New subsection "⚠️ Tasks API Limitations (Critical)" (~40 lines)
  * Field visibility constraint table, cost examples, 3 workaround patterns

- guide/workflows/task-management.md:
  * New subsection "⚠️ Field Visibility Limitations" (~35 lines)
  * Workflow adjustments, cost awareness, mitigation strategies

- guide/cheatsheet.md:
  * Added limitation note with actionable tip (~3 lines)

- machine-readable/reference.yaml:
  * 4 new entries: limitations, field_visibility, cost_overhead, workarounds
  * Updated resource_evaluations_count: 16 → 22

- docs/resource-evaluations/016-gang-rui-tasks-api-limitations.md:
  * New comprehensive evaluation (score 5/5 CRITICAL)
  * Fact-check, challenge phase, integration details

- README.md:
  * Updated resource evaluations count: 15 → 22 assessments

Score: 5/5 (CRITICAL) - Breaks recommended workflow, 11x-51x cost
overhead, prevents user frustration, maintains guide credibility.

Source: https://www.linkedin.com/posts/limgangrui_i-explored-the-new-claude-codes-task-system-activity-7420651412881268736-Hpd6
Date: 2026-01-24

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-27 16:16:49 +01:00
Florian BRUNIAUX
87423c5546 release: version 3.16.0 - TeammateTool + Myths vs Reality 
- TeammateTool: Experimental multi-agent coordination docs
- Appendix D: Myths vs Reality (debunk misinformation)
- Cheatsheet: Features Méconnues section
- Resource evaluation: Rejected social media post (score 1/5)
- Version bump: 3.15.0 → 3.16.0
- Landing sync: 15,400+ lines (vs 14,900+)
 2026-01-27 10:15:39 +01:00
Florian BRUNIAUX
6e621806a4 docs: add Myths vs Reality appendix + TeammateTool documentation 
- Appendix D: Myths vs Reality
  - Myth: Hidden features with secret flags
  - Myth: Tasks API = autonomous agents
  - Myth: 100x faster claims
  - Reality: Documented strengths of Claude Code
  - How to spot reliable vs unreliable sources

- New: TeammateTool experimental feature documentation
  - Multi-agent orchestration capabilities
  - Execution backends (in-process, tmux, iTerm2)
  - Usage patterns (parallel specialists, swarm)
  - Clear warnings about experimental status
  - Community sources cited

- Cheatsheet: Features Méconnues (But Official!) section
  - Tasks API, Background Agents, TeammateTool
  - Session Forking, LSP Tool
  - Pro tip: Read the CHANGELOG

- Reference.yaml: Added line numbers for new sections

- Resource evaluation: Rejected low-quality social media post
  (docs/resource-evaluations/2026-01-27-claude-code-hidden-feature-social-post.md)

Addresses community misinformation while documenting real experimental features with proper sourcing.
 2026-01-27 09:45:06 +01:00
Florian BRUNIAUX
db5c761d13 docs: track Claude Code v2.1.20 release 2026-01-27 09:02:45 +01:00
Florian BRUNIAUX
a8d0f0273d release: version 3.15.0 - MCP Apps integration 
Bump version to 3.15.0 with comprehensive MCP Apps documentation.

Version updates:
- VERSION: 3.14.0 → 3.15.0
- Synced across: README.md, cheatsheet.md, ultimate-guide.md, reference.yaml
- Updated date: reference.yaml (2026-01-27)

CHANGELOG.md:
- Added MCP Apps (SEP-1865) documentation entry in [Unreleased]
- ~50 lines detailing all changes:
  - architecture.md section (~150 lines)
  - ultimate-guide.md section (~90 lines)
  - Table update (Plugin vs MCP vs MCP Apps)
  - machine-readable/reference.yaml (8 entries)
  - Resource evaluation (159 lines, score 4/5)
- Key facts: First official MCP extension, co-authored OpenAI+Anthropic
- 9 interactive tools at launch (Asana, Slack, Figma, etc.)
- Platform support: Claude Desktop, VS Code, ChatGPT, Goose
- CLI relevance: Indirect (ecosystem, dev, hybrid workflows)

README.md:
- Resource Evaluations: 14 → 15 assessments

docs/resource-evaluations/README.md:
- Added MCP Apps entry in index table
- Score: 3/5 → 4/5 (High Value)
- Updated date: 2026-01-27
- Confirmed count: 15 evaluations

Total changes:
- 2 commits (MCP Apps docs + version bump)
- ~240 lines documentation (architecture + guide)
- 15 resource evaluations tracked
- 4/5 integration score (ecosystem impact)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-27 08:24:25 +01:00
Florian BRUNIAUX
18ea240e12 docs: add MCP Apps (SEP-1865) documentation 
Integrate comprehensive documentation for MCP Apps, the first official
MCP extension enabling interactive UI delivery.

Changes:
- guide/architecture.md (656): New section "MCP Extensions: Apps"
  - Technical architecture (primitives, SDK, security)
  - Platform support (Claude Desktop, VS Code, ChatGPT, Goose)
  - Example implementations (9 production tools at launch)
  - Developer workflow and SDK usage
  - ~150 lines of technical documentation

- guide/ultimate-guide.md (6509): New section "MCP Evolution: Apps"
  - User context and use cases
  - Available interactive tools (Asana, Slack, Figma, etc.)
  - Platform support matrix
  - Hybrid workflow examples
  - ~90 lines of user-facing documentation

- guide/ultimate-guide.md (7522): Table update
  - Added "Interactive UI" row to Plugin vs. MCP Server comparison
  - Clarified MCP Apps = "What Claude can show"

- machine-readable/reference.yaml: 8 new entries
  - mcp_apps_architecture, mcp_apps_evolution
  - Links to spec, SDK, blog posts
  - CLI relevance note (indirect)

- docs/resource-evaluations/mcp-apps-announcement.md: New evaluation
  - Score: 4/5 (High Value - Integrate within 1 week)
  - Fact-checked with Perplexity searches
  - Technical review by agent

Resource evaluated:
- https://blog.modelcontextprotocol.io/posts/2026-01-26-mcp-apps/
- https://claude.com/blog/interactive-tools-in-claude

Total documentation: ~240 lines across 3 files
Score: 4/5 (High Value)
CLI relevance: Indirect (ecosystem understanding, MCP server dev, hybrid workflows)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-27 08:14:49 +01:00
Florian BRUNIAUX
08a2a4261f docs: add system prompts official sources (Anthropic + community analyses) 
- Add System Prompt Contents section in architecture.md (line 300-326)
  - Official Anthropic sources (Tier 1, 100% confidence)
  - Community analyses (Simon Willison, PromptHub)
  - Claude.ai vs API vs Code CLI distinctions

- Update reference.yaml with 4 new system prompts entries
  - system_prompts_official, willison_analysis, prompthub, architecture

- Create resource evaluation: system-prompts-official-vs-community.md
  - Score evolution: 4/5 → 3/5 → 2/5 (after Perplexity fact-check)
  - Decision: Do not integrate x1xhlol repository (redundant)
  - Use official Anthropic sources instead

- Create watchlist for non-integrated resources
  - claudedocs/resource-evaluations/watch-list.md (gitignored)
  - Re-evaluation triggers: Q2 2026 or if 10+ user requests

Related evaluation: docs/resource-evaluations/system-prompts-official-vs-community.md

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-26 17:03:42 +01:00
Florian BRUNIAUX
ab8bfcf782 docs: add Anaconda Croce evaluation (minimal integration) 
Resource evaluated: "What I Learned Challenging Claude to a Coding Competition"
by Steve Croce (Anaconda Field CTO, Jan 16, 2026)

Score: 2/5 (Marginal - Info secondaire)

Integration:
- Added "Community Experiences" section in guide/learning-with-ai.md
- 2-paragraph mention with strong caveats (N=1, non-representative context)
- Full evaluation in docs/resource-evaluations/anaconda-croce-evaluation.md
- Updated reference.yaml count (14 → 16 evaluations)

Rationale:
- Provides light empirical validation (90s vs 60min on Advent of Code)
- Highlights "collaboration cost" angle (decreased Slack engagement)
- Limitations prevent extensive integration (solo puzzles ≠ team dev)
- Commercial bias noted (Anaconda blog by Anaconda CTO)

Technical review challenged initial 4/5 score → adjusted to 2/5.
Maintains guide rigor through minimal integration + explicit caveats.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-26 16:53:48 +01:00
Florian BRUNIAUX
444ce5aa6a docs: add resource evaluation process documentation 
Added comprehensive documentation for resource evaluation methodology:

- Appendix C in ultimate-guide.md (line 15034)
  * 5-point scoring system with decision criteria
  * 14 documented assessments by category
  * Transparency on integration decisions
  * Links to full methodology

- Fixed methodologies.md GSD evaluation link
  * Corrected path: claudedocs → docs (public)

- Updated reference.yaml with resource evaluations metadata
  * Directory, count (14), methodology references
  * Appendix and README section line numbers

All resource-evaluations now properly documented and discoverable.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-26 15:10:24 +01:00
Florian BRUNIAUX
893c125fa7 release: version 3.14.0 - NotebookLM MCP integration 
Bump version from 3.13.0 to 3.14.0 with complete NotebookLM MCP documentation.

## Version Updates

- VERSION: 3.13.0 → 3.14.0
- Synced across: README.md, guide/cheatsheet.md, guide/ultimate-guide.md, machine-readable/reference.yaml

## CHANGELOG.md

- Added comprehensive v3.14.0 entry with NotebookLM MCP documentation details
- Moved previous [Unreleased] items to v3.14.0
- Updated templates count: 86 → 83 (accurate count)

## Documentation Changes

Already committed in ff3458a:
- guide/ai-ecosystem.md: +603 lines (§ 4.1-4.5)
- guide/ultimate-guide.md: +3 lines (MCP integration mention)
- Complete coverage of 16 MCP tools across 3 profiles

## Landing Site Sync

- Landing site updated: 3.13.0 → 3.14.0
- All checks passing (version, templates, quiz, guide lines)
- Verified with ./scripts/check-landing-sync.sh

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-26 15:06:46 +01:00
Florian BRUNIAUX
821c900ba0 docs: add task management workflow and update guides 
- Add guide/workflows/task-management.md (comprehensive workflow)
- Update ultimate-guide.md with task management sections
- Add task management quick reference to cheatsheet
- Update machine-readable/reference.yaml with new content
- Update .gitignore for docs/ directory

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-26 14:02:54 +01:00
Florian BRUNIAUX
6f6cd90bc1 release: version 3.13.0 - Boris Cherny mental models integration 
Major additions:
- CLAUDE.md as Compounding Memory philosophy (never correct Claude twice)
- Plan-First Discipline methodology (foundational pattern)
- Verification Loops architectural pattern (8 domains)
- Advanced Worktree Tooling section (3 independent tools validated)
- Anthropic governance resources (Constitution, Petri v2)
- Search tools mastery workflow (grep, grepai, ast-grep, Serena)

Updates:
- Boris Cherny case study enhanced with direct quotes
- Templates count: 83 → 86
- Reference YAML: new architecture diagram, search tools comparison

Resource evaluations:
- Boris Cowork video (3/5 - pertinent)
- Wooldridge productivity stack (3/5 - remote-first workflows)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-26 13:32:54 +01:00
Florian BRUNIAUX
6ed7e92e64 docs: add Anthropic governance resources 
- Add Claude's Constitution (CC0) to data-privacy guide
- Add Petri 2.0 research tool to README
- Update reference.yaml with external research section

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-26 09:31:19 +01:00
Florian BRUNIAUX
96da6ebd7e feat: add bridge script for Claude Code → LM Studio execution (v3.12.1) 
Bridge script enables local execution of Claude Code plans via LM Studio:
- Python CLI with 5 components (DoobidooReader, LMStudioClient, Validator, StepExecutor, PlanExecutor)
- JSON Schema for plan validation (bridge-plan-schema.json)
- Cost optimization: Plan with Opus (~$0.50-2), execute free locally (80-90% savings)
- 4 validation types: json, syntax_check, contains_keys, non_empty
- CLI: --health, --list, --plan ID, -v verbose mode

Documentation:
- New section "Local Execution Bridge" in ultimate-guide.md §11.2
- scripts/README.md with full usage documentation
- machine-readable/reference.yaml entries for discoverability

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-01-25 18:43:05 +01:00
Florian BRUNIAUX
ccf2b2a01e docs: add "Do I Need Worktrunk?" self-assessment section 
Added decision-making framework to help readers evaluate if they need
Worktrunk or should stick with vanilla git/aliases.

Key additions (guide/ultimate-guide.md:10762):
- 3 quick self-assessment questions (volume, multi-instance, team)
- Decision matrix: 4 user profiles (Beginner → Boris scale)
- Quick alias alternative for casual users (2 min setup, -79% typing)
- Bottom line: "80% should start with vanilla git or alias"
- YAGNI principle applied to tooling adoption

Philosophy: Prevents premature tool adoption by providing objective
criteria. Most readers (2-3 worktrees/week) don't need Worktrunk.

Updated:
- machine-readable/reference.yaml: Added worktree_tooling_self_assessment: 10762
- CHANGELOG.md: Updated Advanced Worktree Tooling entry with self-assessment details
- Total guide additions: +139 lines (self-assessment section)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-25 18:33:57 +01:00
Florian BRUNIAUX
da8dedc7f8 docs: add advanced worktree tooling section (Worktrunk + DIY alternatives) 
Added Section 9.17 "Advanced Tooling for Worktree Management (Optional)" based on
deep-dive analysis of 4 sources (Worktrunk GitHub, incident.io blog, Anthropic best
practices, GitHub issue #1052).

Key additions:
- Pattern validation: 3 independent teams created worktree wrappers
- Benchmark: Worktrunk vs vanilla git vs custom wrappers
- Option 1: Worktrunk (1.6K stars, multi-platform, CI/LLM integration)
- Option 2: DIY custom wrappers (incident.io, GitHub #1052 examples)
- Philosophy: Learn fundamentals first, add wrapper for productivity later

Updated machine-readable/reference.yaml:
- Added advanced_worktree_tooling: 10661
- Fixed line references for sections after git worktrees
- Updated Appendix references (14356, 14530, 14532, 14601)

Score: 3/5 (pertinent - complément utile)
Evaluation: claudedocs/resource-evaluations/worktrunk-evaluation.md

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-25 18:00:55 +01:00
Florian BRUNIAUX
3f923efb7e docs: add GSD methodology mention with evaluation 
- Added GSD to Tier 1: Strategic Orchestration (guide/methodologies.md:47-55)
- Meta-prompting 6-phase workflow with fresh 200k-token contexts per task
- Note: Core concepts overlap with existing patterns (Ralph Loop, Gas Town, BMAD)
- Resource evaluation saved in claudedocs/resource-evaluations/gsd-evaluation.md (score: 2/5 - marginal/redundant)
- Updated CHANGELOG.md and machine-readable/reference.yaml for LLM indexing
- Source: https://github.com/glittercowboy/get-shit-done (7.5k stars, created Dec 2025)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-25 17:49:48 +01:00
Florian BRUNIAUX
7330eacb2b chore: bump version to 3.12.0 
- Update VERSION file (3.11.7 → 3.12.0)
- Sync cheatsheet.md version references

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-01-25 13:31:15 +01:00
Florian BRUNIAUX
a858dceda0 docs: add Context Overload anti-pattern (Rusitschka) 
- Add "Context Overload" anti-pattern in §9.8 Vibe Coding (line 8746)
- Unify plan mode + fresh context + handoffs under phased strategy
- Credit Jens Rusitschka ("Vibe Coding, Level 2", Jan 2026)
- Cross-reference existing patterns (§2.2, §2.3)
- Update reference.yaml with new entries (3 keys)
- Add cross-ref in learning-with-ai.md (line 96)

Source: https://kickboost.substack.com/p/are-you-still-vibe-coding-or-are

Score: 2.5/5 (10% useful packaging, 90% rebranding)
Integration: 60 lines added (concise, no duplication)

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-01-25 13:29:02 +01:00
Florian BRUNIAUX
a39d77f97b docs: update Claude Code releases (v2.1.19, v2.1.18) 
- v2.1.19: CLAUDE_CODE_ENABLE_TASKS env var, $0/$1 argument shorthand
- v2.1.18: Customizable keyboard shortcuts with /keybindings
- Breaking: $ARGUMENTS.0 → $ARGUMENTS[0] syntax change (v2.1.19)
- Milestone: Keyboard shortcuts added to feature list
- Update both YAML and Markdown files
- Sync dates to 2026-01-25

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-25 12:45:51 +01:00
Florian BRUNIAUX
caf302107f docs: add ClawdBot vs Claude Code FAQ (v3.11.7) 
- Add Appendix B: FAQ section addressing ClawdBot confusion
- Comprehensive comparison table (9 dimensions)
- Early warning note in 'Before You Start' section
- New README section with quick explanation
- Update all version references to 3.11.7
- Index FAQ in reference.yaml

Context: Jan 2026 community buzz created confusion between
ClawdBot (chatbot for messaging apps) and Claude Code (CLI dev tool)

Total: +86 lines across 5 files

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-25 11:38:19 +01:00
Florian BRUNIAUX
b52d95a634 docs: add architecture diagrams pattern for OOP codebases 
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-25 11:18:53 +01:00
Florian BRUNIAUX
c84c56bfbd docs: add AI Traceability & Attribution guide 
Comprehensive documentation on AI code attribution and disclosure:

- New guide: guide/ai-traceability.md (~640 lines)
  - LLVM "Human-in-the-Loop" policy (Assisted-by trailer)
  - Ghostty mandatory disclosure pattern
  - Fedora contributor accountability framework
  - git-ai tool documentation
  - PromptPwnd security vulnerability
  - Four-level disclosure spectrum
  - Implementation guides (solo, team, enterprise)

- Templates: examples/config/
  - CONTRIBUTING-ai-disclosure.md
  - PULL_REQUEST_TEMPLATE-ai.md

- Cross-references added to:
  - ultimate-guide.md (after Co-Authored-By section)
  - learning-with-ai.md (after Vibe Coding Trap)
  - security-hardening.md (See Also)
  - guide/README.md (table of contents)

- reference.yaml: 14 new entries for AI traceability topics

Source: Vibe coding needs git blame (Piotr Migdał, Jan 2026)
+ Perplexity research on LLVM, Ghostty, Fedora policies

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-01-24 20:11:53 +01:00
Florian BRUNIAUX
d2362401b1 docs: update plugin system with community marketplaces and official docs 
Section 8.5 Plugin System:
- CRITICAL FIX: Correct structure (.claude-plugin/plugin.json not root)
- Add .mcp.json, .lsp.json, hooks/hooks.json to directory structure
- Add skill namespacing documentation (/plugin-name:skill)
- Add warning about common mistake (components outside .claude-plugin/)
- Link to official Anthropic docs: code.claude.com/docs/en/plugins

Community Marketplaces subsection (line 7246):
- wshobson/agents: 67 plugins, 99 agents, 107 skills
- claude-plugins.dev: 11,989 plugins, 63,065 skills indexed
- Popular plugins: Context7 (~72k), Ralph Wiggum (~57k)
- awesome-claude-code: 20k+ stars curated list

Resource evaluation: Nick Jensen article rejected (outdated stats)
- Primary sources integrated instead of blog post

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-01-24 18:32:37 +01:00
Florian BRUNIAUX
873aade097 docs: add Claude Reflect System + skill lifecycle documentation 
- Claude Reflect System: Automatic skill improvement via feedback analysis
- 8-step workflow: Monitor → Parse → Classify → Propose → Review → Backup → Apply → Commit
- Safety features: User review gate, Git backups, syntax validation, locking
- Security warnings: Feedback poisoning, memory poisoning, prompt injection mitigations
- YAML index: 10 new skill lifecycle entries (lines 113-123)
- Resource evaluation: Self-improve skill pattern (redirected to proven alternative)
- Landing sync history: v3.11.5 → v3.11.6

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-24 17:49:37 +01:00
Florian BRUNIAUX
ee5791668a docs: add SE-CoVe plugin example + resource evaluation workflow (v3.11.6) 
- First plugin example: SE-CoVe (Chain-of-Verification, Meta AI ACL 2024)
- Academic approach: cite paper metrics, not marketing claims
- Performance table: +23-112% accuracy (task-dependent, trade-offs disclosed)
- Resource evaluation template established (Perplexity fact-check workflow)
- Curation policy: Academic validation + Claims verified + Costs transparent
- Templates count: 82 → 83
- Architecture diagram added (visual overview of Claude Code internals)

Files:
- examples/plugins/se-cove.md (new plugin documentation)
- claudedocs/resource-evaluations/2026-01-24-se-cove-plugin.md (evaluation report)
- README.md, CHANGELOG.md, VERSION, reference.yaml (version bump 3.11.5 → 3.11.6)
- guide/architecture.md + image (visual overview)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-24 17:40:54 +01:00
Florian BRUNIAUX
89eefea8ac docs: add skills.sh marketplace documentation (v3.11.5) 
Added comprehensive documentation for skills.sh (Vercel Labs) marketplace:

Section 5.5 (Skills Marketplace):
- Installation instructions (npx add-skill <owner/repo>)
- Top skills by category (Frontend, Database, Auth, Testing)
- Format compatibility (100% compatible with .claude/skills/)
- Status & trade-offs (community project, early stage)

Section 11.3 (Skills Distribution Platforms):
- Comparison: skills.sh vs claude-code-templates vs SkillsMP
- When to use each platform (discovery, installation, team-specific)

Updated files:
- guide/ultimate-guide.md: New subsection Skills Marketplace (~line 5172)
- guide/ai-ecosystem.md: New section 11.3 Skills Distribution Platforms
- machine-readable/reference.yaml: Added 7 skills_marketplace_* entries
- README.md: Added skills.sh to Complementary Resources table
- CHANGELOG.md: Detailed entry for v3.11.5
- VERSION: Bumped to 3.11.5
- guide/cheatsheet.md: Version sync

Marketplace stats (Jan 23, 2026):
- 200+ skills available
- Top skill: vercel-react-best-practices (35K+ installs)
- 20+ agents supported (Claude Code, Cursor, Copilot, etc.)
- Launched: January 21, 2026 by Vercel Labs

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-23 18:21:15 +01:00