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

63 commits

Author SHA1 Message Date
Florian BRUNIAUX
5e893f3ccd docs: add Remote Control (§9.22) — mobile access feature documentation 
- New section 9.22 in ultimate-guide.md with full Remote Control coverage
- Cheatsheet: dedicated section + Features Méconnues + slash commands
- security-hardening.md: Part 7 Remote Control Security threat model
- machine-readable/reference.yaml: /rc, /remote-control, /mobile, subcommand
- Resource evaluation: 2026-02-25 (score 4/5, community feedback included)

Key original content vs official Anthropic docs:
- Slash commands (/new, /compact) broken in remote UI — undocumented
- tmux multi-session workaround for 1-session limit
- Community security analysis (RCE surface, CISO implications)

Research Preview — Pro/Max plans only (v2.1.51+)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-25 18:45:41 +01:00
Florian BRUNIAUX
97f9167a61 docs: add Kairn memory MCP + resource evaluations + guide updates 
- guide/ultimate-guide.md §10.2: Add Kairn (knowledge graph memory with biological decay)
  - Typed relationships (depends-on, resolves, causes), 18 MCP tools
  - Updated comparison table: Serena / grepai / doobidoo / Kairn
  - Added decision routing for long-term memory + causality tracking
- guide/ultimate-guide.md §5.1: Add real-world CLAUDE.md migration example (Avo, 600-line → 15 path-scoped files)
- guide/ai-ecosystem.md: Minor update
- machine-readable/reference.yaml: Add Kairn entries
- examples/config/mcp.json: Add Kairn MCP config
- docs/resource-evaluations/: Add 2 new evaluations (context-evaluator-packmind, kairn-memory-mcp)
- docs/resource-evaluations/agents-md-empirical-study: Add community reception section
- docs/resource-evaluations/2026-02-23-agentsview: Minor fix

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-25 17:39:20 +01:00
Florian BRUNIAUX
79157ac077 release: v3.29.0 
- Observability: MLflow Tracing section complète (CLI + SDK, LLM-as-judge)
- Skills §5.5: UI UX Pro Max (33.7k stars, design reasoning engine BM25)
- Diagram #41: AI Fluency High vs Low paths (Anthropic research)
- 3 callouts empiriques AI Fluency Index (Rev Engine 5.6×, CLAUDE.md 30%)
- Hooks docs v2.1.47-2.1.50: WorktreeCreate/Remove, ConfigChange, --from-pr
- CC releases tracking: v2.1.50 → v2.1.52
- 4 nouvelles évaluations ressources (AgentsView, AI Fluency, UX Pro Max)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-24 13:58:09 +01:00
Florian BRUNIAUX
6117145837 docs: integrate veille hebdo Anthropic 17-23 fev 2026 (+177 lignes guide) 
P1 - Prompt caching + env vars:
- Strategy 6 cost optimization: cache_control API, pricing (write 1.25x, read 0.1x), break-even 2 hits
- CLAUDE_CODE_DISABLE_1M_CONTEXT + CLAUDE_CODE_SIMPLE ajoutés à la table env vars principale

P2 - Model deprecations + agents:
- Warning claude-3-haiku-20240307 deprecated 19 fev / retirement 20 avril 2026
- Frontmatter fields: background: true (v2.1.49+) + isolation: worktree (v2.1.50+)
- Section Background Agents: comportement non-blocking, gestion (ctrl+f, double ESC)
- Section claude agents CLI: commande + output annoté

P3 - Worktree isolation native + security cross-ref:
- Native worktree features: --worktree flag, isolation declaratif, WorktreeCreate/WorktreeRemove hooks
- §7.4 Security Hooks: cross-ref Claude Code Security scanner (research preview)

Eval: docs/resource-evaluations/2026-02-22-veille-hebdo-anthropic-17-23-fev.md (score 3/5)
Stats: 19K → 20K lignes (20 440 total)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-23 12:59:28 +01:00
Florian BRUNIAUX
dbb62306d7 release: v3.28.1 - Visual Diagrams Series (40 Mermaid diagrams) 
guide/diagrams/: new directory with 40 interactive Mermaid diagrams
- 10 thematic files: foundations, context/sessions, configuration,
  architecture, MCP ecosystem, dev workflows, multi-agent patterns,
  security/production, cost/optimization, adoption/learning
- Each diagram: Mermaid (GitHub-native) + ASCII fallback + source link
- Bold Guy palette (6-color system) consistent across all diagrams
- README with index, visual palette legend, navigation by use case

Also includes (backlog from v3.28.0→v3.28.1):
- guide/ultimate-guide.md: Managing Large MCP Server Sets, AI Code
  Disclosure Policy, claude-mem Gemini alternative, observability
- guide/workflows/plan-driven.md: Boris Tane custom markdown plans (+172L)
- guide/security-hardening.md: Part 4 PR security review workflow
- examples/agents/security-patcher.md: new security agent
- examples/hooks/bash/security-gate.sh: PreToolUse security hook
- guide/observability.md: activity monitoring, external tools, proxying
- docs/resource-evaluations/: 4 new evaluations (Boris Cherny, Moigneu,
  Boris Tane, Aristote AI instructions)
- README.md: Visual Diagrams section in "What Makes This Guide Unique"

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-22 15:51:21 +01:00
Florian BRUNIAUX
ac50ee7ad8 docs: add monitoring & activity audit sections to observability guide 
- guide/observability.md: +3 sections (Activity Monitoring, External Tools, Proxying)
  - Activity Monitoring: JSONL tool_use audit, jq queries, sensitive pattern detection
  - External Tools: ccusage / claude-code-otel / Akto / MLflow / ccboard comparison
  - Proxying: NODE_EXTRA_CA_CERTS, ANTHROPIC_API_URL, mitmproxy, Python proxy
- docs: ccboard Activity module implementation plan (Tab 10, Rust models, SQLite cache)
- docs: Mergify cross-system support evaluation

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-21 20:29:05 +01:00
Florian BRUNIAUX
6d847d24de docs: add Profile-Based Module Assembly pattern (Section 3.5) 
- Section 3.5 "Team Configuration at Scale" in ultimate-guide.md:
  profiles YAML + shared modules + skeleton + assembler script;
  59% context token reduction measured on 5-dev production team;
  includes CI drift detection, 5-step replication guide, trade-offs
- New workflow: guide/workflows/team-ai-instructions.md (6 phases,
  scaling thresholds, troubleshooting table)
- New templates: examples/team-config/ (profile-template.yaml,
  claude-skeleton.md, sync-script.ts)
- reference.yaml: 9 new entries for team_ai_instructions_*
- README: templates count 161 → 164, date Feb 19 → Feb 20
- CHANGELOG [Unreleased]: resource evaluations (AGENTS.md ETH Zürich
  4/5, Sylvain Chabaud 3/5), spec-first Task Granularity section,
  methodologies ATDD expansion

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-20 15:04:29 +01:00
Florian BRUNIAUX
373b50cf77 docs: add 4 resource evaluations + tasks/lessons.md pattern (v3.27.7+) 
- Add tasks/lessons.md variant to Fresh Context Pattern section — lightweight
  self-improvement loop where Claude captures behavioral rules after corrections
- Resource evaluations (4 new, 67 → 78 total):
  - SKILLMIND/Boris Cherny workflow (2/5): self-improvement loop concept
  - Augment Context Engine MCP (3/5): cloud alternative to grepai
  - LinkedIn context engineering post (2/5): marginal relevance
  - LinkedIn activity-7428930570451083264 (inaccessible)
- README: update evaluations count 67 → 78, threat DB badge 18/341 → 19/655
- CLAUDE.md: add Whitepaper Generation section (PDF + EPUB commands)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-19 13:47:38 +01:00
Florian BRUNIAUX
895ace49f7 docs: add Borg et al. 2025 RCT on AI code maintainability (v3.27.7) 
- Resource eval: arXiv:2507.00788 "Echoes of AI" (151 devs, 95% pros,
  2-phase blind RCT) — 30.7% faster median, ~55.9% habitual users,
  no significant downstream maintainability impact
- guide/learning-with-ai.md: citation + "On maintainability fear" note
- guide/ultimate-guide.md: nuance blockquote in §1.7 Trust Calibration
- machine-readable/reference.yaml: 4 new RCT/maintainability entries
- docs/resource-evaluations/: evaluation file with technical-writer audit

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-19 09:59:50 +01:00
Florian BRUNIAUX
e4d9d9e825 fix: correct v2.1.39/v2.1.41 feature attributions + add claude auth CLI docs 
3 features were incorrectly attributed to v2.1.39 instead of v2.1.41
(guard nested sessions, OTel speed attribute, Agent Teams model fix).
Verified against official CHANGELOG. Also adds claude auth login/status/logout
to the ultimate guide maintenance commands table.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-16 20:37:08 +01:00
Florian BRUNIAUX
4cf1bf3cec docs: v3.27.3 — track Claude Code v2.1.42 + Google Antigravity section 
- Claude Code releases: v2.1.41 → v2.1.42 (startup perf, prompt cache, Opus 4.6 effort callout)
- New AI ecosystem section: Google Antigravity agent-first IDE comparison
- Version sync across all docs (3.27.2 → 3.27.3)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-16 09:38:31 +01:00
Florian BRUNIAUX
d1182af4cf docs: v3.27.1 — fact-check corrections, grepai docs, RTK overhaul 
Fact-check (README positioning):
- Template count: 120/123 → 108 (ground truth recount)
- Ratio: 14× → 24× (19,000 ÷ 784 = 24.2×)
- everything-cc stars: 31.9k → 45k+ (verified Feb 15)
- Commands count: 20 → 23, hooks: 30 → 31

Added:
- Grepai MCP documentation (semantic search, call graphs)
- 3 hook templates (rtk-baseline, session-summary, session-summary-config)
- 2 resource evaluations (system-prompts update, qmd token savings)

Changed:
- RTK documentation overhaul (v0.7.0 → v0.16.0, rtk-ai org)
- Exports deprecated (kimi.pdf, notebooklm.pdf → deprecated/)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-15 18:41:45 +01:00
Florian BRUNIAUX
d72905e9ba docs: integrate Entire CLI across guide (v3.27.0) 
Major integration of Entire CLI, an agent-native platform launched
Feb 2026 by Thomas Dohmke (ex-GitHub CEO) with $60M funding. Provides
rewindable checkpoints, approval gates, and audit trails for AI sessions.

## Added (7 guide files + 3 meta files)

- **ai-traceability.md**: Replace git-ai 404 with Entire CLI (section 5.1)
- **third-party-tools.md**: Fill "Session replay" gap + add tool section
- **observability.md**: Add session portability alternative
- **ai-ecosystem.md**: Add governance-first orchestration (section 8.1.5)
- **ultimate-guide.md**: Enrich multi-instance section 9.17
- **security-hardening.md**: Add compliance audit trails (section 3.4)
- **cheatsheet.md**: Add Community Tools quick reference
- **README.md**: Update structure tree with third-party-tools mention
- **CHANGELOG.md**: Document v3.27.0 release
- **docs/resource-evaluations/entire-cli.md**: Formal evaluation (5/5)

## Fixed

- git-ai references (404 repo) replaced with working alternative
- "Session replay" Known Gap now marked as ✅ FILLED

## Key Features Documented

- Rewindable checkpoints (prompts + reasoning + tool usage)
- Governance layer (approval gates, permissions, audit trails)
- Multi-agent handoffs (Claude → Gemini with context)
- Compliance-ready (SOC2, HIPAA, FedRAMP)
- Session portability (path-agnostic vs native --resume)

## Positioning

- vs git-ai: Replaces non-existent tool (404)
- vs claude-code-viewer: Active replay vs read-only history
- vs Gas Town: Governance sequential vs parallel coordination

Files modified: 10 (7 content + 3 meta)
Words added: ~2,500
Version: 3.26.0 → 3.27.0

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-12 23:33:16 +01:00
Florian BRUNIAUX
971a297db3 feat(security): add threat intelligence DB, security commands, and cheatsheet audit fixes (v3.26.0) 
- Add threat-db.yaml v2.0.0 with 63 malicious skills, 22 CVEs, 4 campaigns
- Add /security-check, /security-audit, /update-threat-db slash commands
- Add Snyk ToxicSkills evaluation (58th resource evaluation)
- Fix cheatsheet: add Alt+T to keyboard shortcuts table, add /fast and /debug commands
- Update Features Meconnues table with Agent Teams and Auto-Memories
- Clean up cheatsheet.md.bak
- Bump version to 3.26.0

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-11 16:12:36 +01:00
Florian BRUNIAUX
c958738c20 docs: integrate AI fatigue symptom recognition (score 3/5) 
Add session time-boxing guidance and nondeterminism stress recognition
to learning-with-ai.md across 3 strategic locations (~220 words total).

Changes:
- Red Flags Checklist: Add session fatigue warning with time-boxing mitigation
  (30 min limit, max 3 attempts before manual implementation)
- Productivity Reality: Add nondeterminism stress paragraph (identical prompts
  → varying outputs causes AI fatigue)
- UVAL Protocol: Add Step 2.5 checkpoint for fatigue signal recognition
  (session duration, retry count, frustration assessment)

Rationale:
- Score 3/5: Moderate relevance (90% overlap with existing content)
- Extracted only novel tactics: session time-boxing (distinct from weekly 70/30)
- Rejected contradictory recommendations (70% quality vs understand 100%)
- Full evaluation + technical-writer challenge: docs/resource-evaluations/

Source: Siddhant Khare, "AI Fatigue is Real and Nobody Talks About It"
        (Feb 2026, https://siddhantkhare.com/writing/ai-fatigue-is-real)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-10 13:13:32 +01:00
Florian BRUNIAUX
ef7cdd899e release: v3.24.0 - Agent Evaluation Framework 
Major addition: Complete agent evaluation framework with production-ready template.

## Added

- **Resource Evaluation**: nao framework (score 3/5)
  - Identified critical gap: agent evaluation not documented
  - Technical challenge adjusted score 2/5 → 3/5
  - All claims fact-checked (TypeScript 58.9%, Python 38.5%)

- **Guide Section**: Agent Evaluation (guide/agent-evaluation.md, ~3K tokens)
  - Metrics: response quality, tool usage, performance, satisfaction
  - Patterns: logging hooks, unit tests, A/B testing, feedback loops
  - Example: analytics agent with built-in metrics
  - Tools: nao framework reference, Claude Code hooks integration

- **AI Ecosystem**: Section 8.2 Domain-Specific Agent Frameworks
  - nao (Analytics Agents): Database-agnostic, built-in evaluation
  - Transposable patterns: context builder, evaluation hooks, DB integrations

- **Template**: Analytics Agent with Evaluation (5 files, ~1K lines)
  - README: setup, usage, troubleshooting
  - Agent: SQL generator with evaluation criteria, safety rules
  - Hook: automated metrics logging (safety, performance, errors)
  - Script: analysis with stats, safety reports, recommendations
  - Report template: monthly evaluation format

## Changed

- Agent Evaluation Guide: updated template references, verified links
- Landing Site: templates count 110 → 114
- Version: 3.23.5 → 3.24.0

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-10 11:52:13 +01:00
Florian BRUNIAUX
12568fbd61 docs: eval resource Rakesh Gohel / Aakash Gupta "Master Claude Code" infographic (score 2/5) 
Evaluation complète de l'infographie LinkedIn "Master Claude Code v1.0" (9 février 2026).
Score 2/5 (Marginal) - Ne pas intégrer.

Justifications:
- Aucune information technique nouvelle vs guide actuel
- Cheatsheet v3.23.4 strictement supérieur
- Erreur notable: recommandation Cursor comme "best experience" (red flag technique)
- Angle PM déjà couvert par Cowork Guide (repo dédié)
- 0/12 aspects apportent valeur nouvelle

Fichiers:
- docs/resource-evaluations/rakesh-gohel-aakash-gupta-master-claude-code.md (nouveau)
- docs/resource-evaluations/README.md (index mis à jour, 56→57 évaluations)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-10 10:42:11 +01:00
Florian BRUNIAUX
d5c3a82cac docs: add claude-mem plugin documentation (automatic session memory) 
Integrate claude-mem (thedotmack/claude-mem) into the guide as Section 8.2.5.
Score: 4/5 (High Value - automatic session capture fills documentation gap).

Added:
- Section 8.2.5: claude-mem plugin (automatic session memory)
  * Automatic capture via lifecycle hooks
  * AI compression + progressive disclosure (10x tokens)
  * Web dashboard at localhost:37777
  * Natural language search
  * Privacy controls (<private> tags)
  * Cost analysis ($0.15/100 obs)
  * AGPL-3.0 licensing considerations

- Memory Tools Decision Matrix (claude-mem vs Serena vs grepai)
  * 4-layer memory stack pattern
  * Integrated workflow examples
  * When to use automatic vs manual memory

- Plugin template: examples/plugins/claude-mem.md
  * Installation, configuration, troubleshooting
  * Advanced features (progressive disclosure, endless mode)
  * Export/import, cost optimization

- Resource evaluation: docs/resource-evaluations/claude-mem-evaluation.md
  * Technical analysis (fact-checked stats)
  * Comparison to existing tools
  * Integration recommendations

- reference.yaml: 14 new claude-mem entries

Changed:
- Updated search tools comparison (5 tools: rg, grepai, Serena, ast-grep, claude-mem)
- Extended feature matrix with "Auto capture" and "Web dashboard" rows

Stats (verified 2026-02-10):
- 26.5k GitHub stars, 1.8k forks
- 181 releases, 46 contributors
- Latest: v9.1.1 (Feb 7, 2026)
- License: AGPL-3.0 + PolyForm Noncommercial

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-10 08:47:17 +01:00
Florian BRUNIAUX
89084c89ec docs: integrate Anthropic 2026 Agentic Coding Trends Report 
Integration strategy: diffusion transversale (~450 lines across 5 files)
instead of monolithic Section 9.21 (rejected after technical-writer review).

Evaluation: 4/5 score (high value, but lacks concrete code examples)
Source: https://resources.anthropic.com/hubfs/2026%20Agentic%20Coding%20Trends%20Report.pdf

Changes:
1. Created evaluation report (docs/resource-evaluations/)
   - Summary, gap analysis, challenge results, fact-check
   - Justification: validation industrie, benchmarks, anti-patterns

2. Modified guide/ultimate-guide.md (3 insertions, ~270 lines)
   - Section 9 intro: Industry context encadré with adoption data
   - Section 9.17 Multi-Instance: ROI benchmarks ($500-1K/month validation)
   - Section 9.11: Enterprise Anti-Patterns section (5 detailed patterns)

3. Modified guide/workflows/agent-teams.md (~80 lines)
   - Industry adoption data with case studies
   - Timeline: 3-6 months, success rates by phase
   - Real-world performance metrics (Fountain 50%, Rakuten 7h, TELUS 500K hours)

4. Modified machine-readable/reference.yaml (~40 lines)
   - Added agentic_trends_2026_* metadata section
   - Research data, case studies, benchmarks, anti-patterns references

5. Modified README.md (~8 lines)
   - Added "Research & Industry Reports" section
   - Link to Anthropic report with evaluation details

Stats validated: 60% AI usage, 0-20% full delegation, 67% more PRs/day,
27% new work, 7 case studies (Fountain, Rakuten, CRED, TELUS, Legora, Zapier, Augment).

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-09 17:18:52 +01:00
Florian BRUNIAUX
17846b1179 docs: complete Wasp fullstack essentials integration 
Complete all 4 action items from wasp-fullstack-essentials-eval.md resource
evaluation (score 3/5). Framework-agnostic insights only, promotional content
excluded.

Changes (3 sections):

1. Background tasks workflow (Section 9.5)
   - New subsection: "Background Tasks for Fullstack Development"
   - When to background tasks (5 scenarios table)
   - Fullstack workflow pattern with examples
   - Context rot prevention strategies
   - Limitations and workarounds
   - Integration with teleportation
   - /tasks monitoring guide
   - ~100 lines added to Section 9.5 "Tight Feedback Loops"

2. Chrome DevTools MCP (mcp-servers-ecosystem.md)
   - New server entry in "Browser Automation" section
   - Official Anthropic server (not community)
   - Comparison table vs Playwright MCP (debugging vs testing)
   - Setup and configuration
   - Use cases and limitations
   - Updated stats: 3 browser servers (was 2), 6 official servers (was 5)
   - ~60 lines added to Browser Automation section

3. Convention-over-config for AI (Section 9.18.1)
   - New subsection: "Convention-Over-Configuration for AI Agents"
   - Why opinionated frameworks reduce agent cognitive load
   - Comparison table: custom vs opinionated architectures
   - Examples: Next.js, Rails, Phoenix, Django
   - Real-world impact on agent productivity
   - Trade-offs analysis
   - Connection to CLAUDE.md sizing (token reduction)
   - ~60 lines added to Section 9.18.1

Total additions: ~220 lines (workflow patterns + MCP server + AX framework)

Source evaluation: docs/resource-evaluations/wasp-fullstack-essentials-eval.md
Primary sources: llmstxt.org (llms.txt), official docs (background tasks, Chrome
DevTools MCP), existing Section 9.18 (Marmelab/AX framework)

Related commits:
- 783c43b: llms.txt conceptual documentation (completed earlier)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-09 10:00:53 +01:00
Florian BRUNIAUX
783c43baed docs: add llms.txt conceptual documentation to Section 9.18 
Add comprehensive llms.txt documentation based on Wasp fullstack essentials
resource evaluation (score 3/5). Sourced from llmstxt.org spec, not the
promotional article.

Changes:
- New section 9.18.4: Documentation Formats for Agents (llms.txt)
- Explains llms.txt standard, format, and use cases
- Clarifies complementarity with Context7 MCP (not opposition)
- Provides minimal and advanced examples with line numbers
- Integration patterns with CLAUDE.md
- References this repo's own llms.txt implementation
- Updated section numbering (9.18.4-9.18.11)
- Updated Section 9.18 TL;DR with new principle
- Added reference.yaml entries for llms.txt

Resource evaluation:
- File: docs/resource-evaluations/wasp-fullstack-essentials-eval.md
- Source: Wasp DevRel blog (framework-agnostic insights extracted)
- Score: 3/5 (partial integration, promotional content excluded)
- Gap identified: Embarrassing to have llms.txt file without explaining concept
- Primary source: llmstxt.org specification

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-09 09:46:50 +01:00
Florian BRUNIAUX
9805b615c5 docs: correct Agent Teams architecture + add session handoff template 
## Agent Teams Architecture Corrections

Based on official sources (Addy Osmani blog, Feb 2026):

**Major changes**:
- Add mailbox system documentation (peer-to-peer messaging)
- Correct communication model: not only team lead synthesis
- Update diagrams to show peer-to-peer arrows
- Clarify context isolation vs message sharing
- Add 7 sections with source attribution
- Add documentation update note (2026-02-09)

**Key correction**: Agents communicate via mailbox system (direct
peer-to-peer + team lead synthesis), not only hierarchical reporting.

**Files modified**:
- guide/workflows/agent-teams.md (+72 -19): 7 major corrections
- CHANGELOG.md: Document session handoff template addition
- guide/architecture.md: Architecture clarifications
- guide/ultimate-guide.md: Cross-references updates

**Sources**:
- https://addyosmani.com/blog/claude-code-agent-teams/
- Perplexity research (sonar-reasoning-pro, Feb 2026)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-09 09:23:41 +01:00
Florian BRUNIAUX
b8eb937642 fix: correct evaluation count in README (25 → 55) 
The previous automatic update showed 25 evaluations instead of 55.
Verified with: find docs/resource-evaluations -type f -name '*.md' ! -name 'README.md' | wc -l

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-07 16:14:37 +01:00
Florian BRUNIAUX
4c0e4b6ac6 docs: integrate Gur Sannikov ADR workflow + native capabilities audit (4/5) 
- Add ADR-Driven Development pattern to methodologies.md (~60 lines)
  - Pattern: ADR → skill → native execution
  - Example ADR template (database migration)
  - Complete bash workflow with benefits
- Add Native Capabilities Audit checklist to architecture.md (~50 lines)
  - 11 native capabilities with internal links
  - Onboarding tip for comprehension audit
- Add Dynamic Model Switching pattern to cheatsheet.md (~40 lines)
  - Pattern: Sonnet → Opus → Sonnet
  - Cost comparison table and best practices
- Add Community Validation to architecture.md (~15 lines)
  - External validation of 'less scaffolding, more model' approach
  - Cursor power user adopting Agent Skills standard
- Track evaluation in docs/resource-evaluations/ (full methodology)
- Update evaluations count: 24 → 55 (README + reference.yaml)
- Update CHANGELOG.md with integration details

Source: https://www.linkedin.com/posts/gursannikov_claudecode-embeddedengineering-aiagents-activity-7423851983331328001-DrFb
Score: 4/5 (HIGH VALUE) - fills ADR workflow gap + onboarding checklist

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-07 16:12:53 +01:00
Florian BRUNIAUX
b48d95c024 feat: add agent/skill quality audit tooling + Grenier evaluation 
AUDIT TOOLING (3 templates):
- Command: /audit-agents-skills (quick project audits)
  - 16-criteria framework (Identity 3x, Prompt 2x, Validation 1x, Design 2x)
  - Weighted scoring: 32 pts (agents/skills), 20 pts (commands)
  - Production grading (A-F, 80% threshold)
  - Fix mode with actionable suggestions
- Skill: audit-agents-skills (advanced audits)
  - 3 modes: Quick (top-5), Full (all 16), Comparative (vs templates)
  - JSON + Markdown output for CI/CD
- Scoring grids: criteria.yaml (externalized for reuse)

EVALUATION:
- Grenier agent/skill quality (3/5 - Moderate Value)
  - Gap: 29.5% deploy without evaluation (LangChang 2026)
  - Integration: Created audit command + skill + criteria
  - Industry context: 18% cite agent bugs as top challenge

DOCUMENTATION:
- Guide refs: 2 strategic call-outs (after Agent/Skill validation)
- CHANGELOG: New "Added" section + evaluation details
- README: Templates 106→107, Evaluations 49→24 (count corrections)
- reference.yaml: 10 new audit entries + updated counts

SYNC:
- Landing index.html: Templates 107, Evals 24, Quiz 257
- Landing examples/index.html: Templates 107

FILES: 14 changed, 4148 insertions (+1250 lines new audit content)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-07 15:40:18 +01:00
Florian BRUNIAUX
c5fad9f092 docs: add Context Engineering (Thoughtworks) + corporate marketplaces footnotes 
- Add Context Engineering framework reference (Thoughtworks Tech Radar Vol 33)
- Add emerging corporate AI marketplaces concept (Hugo 2026)
- Document evaluation in docs/resource-evaluations/hugo-ai-impact-2026.md
- Score: 2/5 (marginal) - minimal integration via footnotes only

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-06 16:09:02 +01:00
Florian BRUNIAUX
bd01add3f6 docs: integrate /insights architecture from Zolkos deep dive (4/5) 
1. Resource evaluation (docs/resource-evaluations/zolkos-insights-deep-dive.md):
   - Score: 4/5 (High Value) - comprehensive technical architecture
   - Content: 7-stage pipeline, facets classification (6 dimensions), technical specs
   - Decision: Integrate architecture + facets (complementary with usage doc)
   - Comparison: Zolkos (architecture interne) vs Guide (usage externe) = complet
   - Why not 5/5: Missing user guidance, screenshots, prompt examples
   - Updated index: 23 evaluations total

2. Architecture Overview added to guide (ultimate-guide.md L6460+):
   - 7-stage pipeline: filtering, summarization, facet extraction, aggregation,
     executive summary, report generation, facet caching
   - Facets Classification System (6 dimensions):
     * Goals (13 types): Debug, Implement, Fix Bug, Write Script, Refactor, etc.
     * Friction (12): Misunderstood, wrong approach, buggy code, user rejection, etc.
     * Satisfaction (6): Frustrated → Dissatisfied → Likely → Satisfied → Happy
     * Outcomes (4): Not → Partially → Mostly → Fully Achieved
     * Success (7): Fast search, correct edits, explanations, proactive, multi-file, etc.
     * Session Types (5): Single, multi, iterative, exploration, quick question
   - Performance: Caching system (facets/<session-id>.json) for incremental analysis
   - Interpretation guidance: How facets help understand report recommendations
   - Source attribution: Zolkos Technical Deep Dive (2026-02-04)

3. CHANGELOG [Unreleased]:
   - Comprehensive /insights documentation with architecture deep dive
   - Facets classification system (6 dimensions documented)
   - Performance optimization explanation (caching)
   - Resource evaluation: Zolkos deep dive (4/5, integrated)

Impact: Power users can now understand WHY /insights generates specific suggestions
(based on facets classification), optimize workflows for better analysis (avoid <2 msg
sessions), and interpret friction categories with context (12 types documented).

Complementarity proven: Usage documentation (existing) + Architecture (Zolkos) = complete.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-06 15:38:45 +01:00
Florian BRUNIAUX
669199e215 docs: add comprehensive /insights documentation + eval Kajan Siva post 
1. Slash Commands documentation (ultimate-guide.md L6339+):
   - What /insights analyzes: Project areas, interaction style, success/friction patterns
   - Report structure: 8 sections (At a Glance, Work Areas, Usage Style, Wins, Friction, Features, Patterns, Horizon)
   - Interactive elements: Copy buttons, checkboxes, charts, navigation TOC
   - Technical details: Haiku, 50 sessions max, 8192 tokens, ~/.claude/usage-data/
   - Typical insights: CLAUDE.md suggestions, feature recommendations, horizon workflows
   - Integration examples: Monthly optimization, git cross-reference, ccboard combo
   - Comparison table: /insights vs /status vs ccboard vs git history

2. Cheatsheet (cheatsheet.md L25):
   - Added /insights to command table: "Usage analytics + optimization report"

3. Resource evaluation (docs/resource-evaluations/kajan-siva-insights-command.md):
   - Score: 2/5 (Marginal) - no technical content, just surface mention
   - Post confirms /insights exists + provides suggestions, but zero details
   - Real value: HTML report with 18+ actionable suggestions (not documented in post)
   - Recommendation: Do NOT integrate post, document command from actual usage
   - Next: Evaluate Zolkos deep dive for technical architecture specs

4. CHANGELOG [Unreleased]:
   - Comprehensive /insights documentation added to Section 6.1
   - Interactive HTML report details, typical insights, integration examples

Impact: Users can now understand /insights output structure, actionable sections,
and integration workflows. Command properly documented with generic examples.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-06 15:21:19 +01:00
Florian BRUNIAUX
c81180aec7 feat: adaptive onboarding architecture v2.0.0 (v3.23.0) 
Major overhaul of onboarding system with adaptive topic selection based on
user context and keywords. Addresses 8 critical gaps identified by technical-
writer agent challenge.

Core Changes:
- Adaptive matrix: core topics (always) + adaptive topics (keyword-triggered)
- Security-first: moved sandbox_native_guide to beginner_5min (before commands)
- Time budget validation: all 18 profiles validated at 6-8 min/topic
- Quiz integration: positioned as exit activity in Phase 4 wrap-up
- New learn_security goal with 2 profiles (beginner_15min, advanced_60min)

Technical Improvements:
- Added onboarding_matrix_meta for version tracking and maintenance triggers
- Created validation script (validate-onboarding.sh) with 6 automated checks
- Created automation script (detect-new-onboarding-topics.sh) for monthly reviews
- Fixed 8 missing deep_dive keys (rules, workflow, fix, architecture, etc.)
- Removed duplicate deep_dive section causing validation failures

Documentation:
- README.md: version 3.23.0, harmonized counts (106 templates, 49 evaluations)
- CHANGELOG.md: comprehensive v3.23.0 entry with all changes
- Onboarding-prompt.md: updated Phase 1.5, 2, 4 with adaptive logic
- Reference.yaml: 180+ lines added for adaptive architecture

Validation:
- All 18 profiles pass time budget constraints (30-50% buffer maintained)
- All deep_dive keys verified (no missing references)
- Version synchronized across 6 files via sync-version.sh

Challenge: technical-writer agent identified 8 gaps in initial analysis
Result: Full adaptive approach implemented, all gaps addressed

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-05 22:19:58 +01:00
Florian BRUNIAUX
1c27aa293d docs: add ShipTypes resource evaluation (score 2/5 - marginal) 2026-02-04 12:14:12 +01:00
Florian BRUNIAUX
9c5d030b11 docs: add dual-instance planning pattern (Jon Williams) 
Add vertical separation pattern (planner/implementer) as complement to horizontal scaling (Boris pattern).

## Changes

**Main guide (ultimate-guide.md)**:
- New Section 9.17.1: "Alternative Pattern: Dual-Instance Planning" (~350 lines)
  - When to use (solo devs, spec-heavy, $100-200/month)
  - Setup instructions (2 Claude instances, Plans/ directory)
  - Complete workflow (5 phases: planning, review, implementation, verification, archive)
  - Comparison table (Boris horizontal vs Jon vertical scaling)
  - Cost analysis (2 instances vs correction loops)
  - Agent-ready plan best practices
  - Limitations and tips

**Workflow file (workflows/dual-instance-planning.md)**:
- Full workflow guide (~750 lines)
- Complete example (JWT auth implementation)
- Plan template (ready to copy-paste)
- Cost breakdown and decision matrix
- Troubleshooting and bash aliases

**References updated**:
- machine-readable/reference.yaml: 15 new entries
  - dual_instance_planning, dual_instance_workflow, etc.
  - Line numbers, source attribution, metadata
- guide/workflows/plan-driven.md: Link in See Also section
- README.md: Update evaluation count (46 → 47)

**Evaluation documented**:
- docs/resource-evaluations/jon-williams-dual-instance-pattern.md
  - Full methodology (fetch, analyze, challenge, fact-check)
  - Score progression (2-3/5 → 4/5 after technical-writer challenge)
  - Gap analysis, comparison, integration rationale

## Source
LinkedIn post by Jon Williams (Product Designer, UK)
Date: 2026-02-03
URL: https://www.linkedin.com/posts/thatjonwilliams_ive-been-using-cursor-for-six-months-now-activity-7424481861802033153-k8bu

Context: Transition from Cursor (6 months) to Claude Code with Opus 4.5
Pattern: Vertical separation (Claude Zero: planning/review, Claude One: implementation)
Distinction: Orthogonal to Boris pattern (vertical vs horizontal scaling)

## Stats
- Lines added: ~1,400
- Files modified: 4
- Files created: 2 (workflow + evaluation)
- References added: 15 (reference.yaml)
- Evaluation score: 4/5 (High Value)
- Integration time: ~2.5 hours

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-04 10:38:10 +01:00
Florian BRUNIAUX
0a2e05f290 fix(keybindings): correct Ctrl+R from "Retry" to "Search history" 
- Updated 5 locations in guide (cheatsheet + ultimate-guide)
- Verified against official keybindings: history:search action
- Added resource evaluation: Sankalp's Claude Code experience (2/5)
- Blog correctly identified guide error

Closes evaluation workflow for sankalp-claude-code-experience

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-03 17:27:54 +01:00
Florian BRUNIAUX
b15647d57f docs: add Git MCP Server (Official) comprehensive documentation 
Integration:
- New section "Version Control (Official Servers)" in mcp-servers-ecosystem.md (~1600 words)
- Decision matrix: Git MCP vs GitHub MCP vs Bash tool (11 operations)
- 12 tools documented with setup, config, use cases, limitations
- Resource evaluation file created (git-mcp-server-evaluation.md)
- Machine-readable index updated (11 new entries)
- Evaluation count corrected: 36 → 46 (actual file count)

Score: 5/5 (CRITICAL) after technical-writer challenge
Gap filled: Official Git server 0% documented → 100% comprehensive

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-03 17:20:12 +01:00
Florian BRUNIAUX
975b8019ac feat: add 4 ClaudeKit-inspired hooks (checkpoint, validation, file-guard) 
- Add auto-checkpoint.sh (Stop event, git stash automation)
- Add typecheck-on-save.sh (PostToolUse, TypeScript validation)
- Add test-on-change.sh (PostToolUse, smart test detection)
- Add file-guard.sh (PreToolUse, unified file protection)
- Add ClaudeKit evaluation (3/5, patterns extracted)
- Version bump 3.21.0 → 3.21.1 (sync across all docs)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 21:50:48 +01:00
Florian BRUNIAUX
6910c06981 docs: add Native Sandboxing comprehensive documentation (v3.21.1) 
Integration of official Anthropic sandboxing docs (5/5 CRITICAL):

Created (5 files):
- guide/sandbox-native.md (~3K words): Complete technical reference
  * OS primitives (Seatbelt/bubblewrap), filesystem/network isolation
  * Sandbox modes, escape hatch, security limitations
  * Decision trees, config examples, troubleshooting
- docs/resource-evaluations/native-sandbox-official-docs.md (5/5 score)
- examples/config/sandbox-native.json (production config)
- examples/commands/sandbox-status.md (sandbox inspection)
- examples/hooks/bash/sandbox-validation.sh (prod validation)

Updated (5 files):
- guide/sandbox-isolation.md: Section 4 "Native Claude Code Sandbox"
  * Comparison Native vs Docker (process-level vs microVM)
  * Updated TL;DR, comparison matrix, decision tree
- guide/architecture.md: Native Sandbox sub-section in Security Model
- machine-readable/reference.yaml: +24 sandbox entries
- VERSION: 3.21.0 → 3.21.1
- README.md: Templates 100→103, Evaluations 44→45
- CHANGELOG.md: v3.21.1 entry

Closes critical security documentation gap (~1800 words missing).
Fact-checked 100%, agent-challenged (technical-writer), production-ready.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 20:24:17 +01:00
Florian BRUNIAUX
0630fcd883 feat: add configuration management and MCP secrets workflows (closes #16204) 
Major additions to address critical gaps in Claude Code configuration:

## New Documentation Sections

1. Section 3.2.1 "Version Control & Backup" (guide/ultimate-guide.md:4085)
   - Configuration hierarchy: global → project → local
   - Git strategy for ~/.claude (symlinks approach)
   - Backup strategies: Git remote, cloud sync, cron
   - Multi-machine sync workflows
   - Disaster recovery procedures
   - Documented .claude/settings.local.json (previously undocumented)

2. Section 8.3.1 "MCP Secrets Management" (guide/ultimate-guide.md:8113)
   - Three practical approaches: OS Keychain, .env, Secret Vaults
   - Secrets rotation workflow
   - Pre-commit secret detection
   - Verification checklist
   - Best practices summary

## New Templates

1. sync-claude-config.sh (examples/scripts/)
   - Commands: setup, sync, backup, restore, validate
   - .env parsing + envsubst for variable substitution
   - Git repo creation with symlinks
   - Validation checks (secrets not in Git)

2. pre-commit-secrets.sh (examples/hooks/bash/)
   - Detects 10+ secret patterns (OpenAI, GitHub, AWS, etc.)
   - Whitelist system for false positives
   - Clear error messages with remediation steps

3. settings.local.json.example (examples/config/)
   - Machine-specific overrides template
   - Example use cases and patterns

## Resource Evaluation

- Added docs/resource-evaluations/ratinaud-config-management-evaluation.md
- Score: 5/5 (CRITICAL)
- Validated via 3 Perplexity searches + technical-writer agent challenge
- Community demand: GitHub #16204 + brianlovin/claude-config

## Updated References

- machine-readable/reference.yaml: 22 new entries
- Configuration management sections
- MCP secrets workflows
- Community resources (Ratinaud, brianlovin, GitHub issue)

## Impact

- Security: Pre-commit hook prevents secret leaks
- Productivity: Multi-machine sync reduces manual reconfig
- Team coordination: Onboarding workflow for ~/.claude setup
- Disaster recovery: Backup/restore strategies documented

Credits:
- Martin Ratinaud (504 sessions, LinkedIn post)
- brianlovin/claude-config (community example)
- GitHub Issue #16204 (community request)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 18:17:42 +01:00
Florian BRUNIAUX
5b69db64a9 docs: add Alan Tour Eiffel paradigm evaluation (5/5 CRITICAL) 
Integration of Alan Engineering team's paradigm shift framework:
- Tour Eiffel Principle (transformation vs acceleration)
- Ralph Wiggum Programming (agentic loops)
- Verification Paradox (automated guardrails over human review)

Files added:
- docs/resource-evaluations/alan-tour-eiffel-paradigm.md (291 lines)

Files modified:
- guide/production-safety.md: New Rule 7 "Verification Paradox"
- guide/ai-ecosystem.md: Added practitioner insight (line 2133)
- machine-readable/reference.yaml: Added Alan + verification paradox entries
- README.md: Fixed evaluation counters (37/35/38 → 41)

Source: https://www.linkedin.com/pulse/le-principe-de-la-tour-eiffel-et-ralph-wiggum-maxime-le-bras-psmxe/
Authors: Charles Gorintin (CTO Alan), Maxime Le Bras (Talent Lead)
Published: 2026-02-02

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-02 14:21:51 +01:00
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
fb339b8575 docs: update RTK evaluation (v0.2.0 → v0.7.0) 
BREAKING UPDATE: All gaps from initial evaluation resolved upstream.

## Version Evolution
- Initial eval: v0.2.0 (2026-01-28, score 4/5)
- Updated eval: v0.7.0 (2026-02-01, score 4.5/5)
- Development: 5 major releases in 9 days

## Critical Changes Resolved
✅ pnpm support (v0.6.0) - was MISSING
✅ npm/vitest support (v0.6.0) - was MISSING
✅ Git arg parsing (v0.7.0) - was BROKEN
✅ grep functionality (v0.7.0) - was BROKEN
✅ ls efficiency (v0.7.0+) - was BROKEN (-274% worse)
✅ Analytics (v0.4.0) - rtk gain temporal audit
✅ Opportunity scanner (v0.7.0) - rtk discover
✅ GitHub CLI (v0.6.0) - full gh support
✅ Cargo commands (v0.6.0) - build/test/clippy
✅ Auto-rewrite hook (v0.7.0) - PreToolUse integration

## Score Changes
| Criterion | v0.2.0 | v0.7.0 | Change |
|-----------|--------|--------|--------|
| Accuracy & Reliability | 3 | 4 | +1 |
| Depth & Comprehensiveness | 4 | 5 | +1 |
| Practical Value | 5 | 5 | 0 |
| Originality & Uniqueness | 5 | 5 | 0 |
| Production Readiness | 3 | 4 | +1 |
| Community Validation | 2 | 3 | +1 |
| **TOTAL** | 3.90 | 4.33 | +0.43 |

Rounded: 4/5 → **4.5/5**

## Community Growth
- Stars: 8 → 17 (+113%)
- Forks: 0 → 2 (+200%)
- PRs merged: 0 → 10+ (community contributions)
- Contributors: 1 → 2+

## Architecture Maturity
- 24 command modules (was 12)
- 9 filtering strategies (50-99% reduction)
- SQLite token tracking (~/.local/share/rtk/history.db)
- Configuration system (~/.config/rtk/config.toml)

## Recommendation Update
- OLD: "GOOD (4/5) - git-only, bugs, experimental"
- NEW: "EXCELLENT (4.5/5) - production-ready, full stack"

## Fork Status
- Fork (FlorianBruniaux) contributed 10+ PRs to upstream
- All features merged → fork no longer needed
- Recommendation: Use upstream v0.7.0 directly

## Impact
- Token reduction: 72.6% (git) → 89.4% (full stack)
- Command coverage: 40% → 85% (dev sessions)
- Maturity: experimental → production-ready (early adopters)

File changes: 633 lines (+69), 405 insertions, 335 deletions (major rewrite)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-01 23:07:12 +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
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
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
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
97d41b8598 release: v3.19.0 - Hook Execution Model documentation 
Adds comprehensive async hooks documentation filling critical gap.
Includes decision matrix, migration guide, and Aristote case study.

Changes:
- Added Hook Execution Model section to ultimate-guide.md (~97 lines)
- Documented sync vs async hooks (v2.1.0+) with configuration examples
- Added decision matrix for 15 use cases
- Updated reference.yaml with 7 new hook async entries
- Resource evaluation: Melvyn Malherbe LinkedIn post (score 1/5)
- Aristote case study: 7 hooks analyzed, 3 migrated async
- Version bump: 3.18.2 → 3.19.0

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-30 12:37:23 +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
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