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 · 2026-02-16 09:38:31 +01:00 · 4cf1bf3cec
commit 4cf1bf3cec
parent 66ebec567a
10 changed files with 208 additions and 19 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@ -8,6 +8,13 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).

 <!-- New entries go here -->

+## [3.27.3] - 2026-02-16
+
+### Updated
+
+- **Claude Code Releases**: Updated tracking v2.1.41 → v2.1.42
+  - v2.1.42: Startup optimization (deferred Zod schema), prompt cache hit rate improvement (date outside system prompt), Opus 4.6 effort callout, `/resume` and image error UX fixes
+
 ## [3.27.2] - 2026-02-15

 ### Added
--- a/README.md
+++ b/README.md
@ -6,7 +6,7 @@

 <p align="center">
  <a href="https://github.com/FlorianBruniaux/claude-code-ultimate-guide/stargazers"><img src="https://img.shields.io/github/stars/FlorianBruniaux/claude-code-ultimate-guide?style=for-the-badge" alt="Stars"/></a>
-  <a href="./CHANGELOG.md"><img src="https://img.shields.io/badge/Updated-Feb_15,_2026_·_v3.27.2-brightgreen?style=for-the-badge" alt="Last Update"/></a>
+  <a href="./CHANGELOG.md"><img src="https://img.shields.io/badge/Updated-Feb_16,_2026_·_v3.27.3-brightgreen?style=for-the-badge" alt="Last Update"/></a>
  <a href="./quiz/"><img src="https://img.shields.io/badge/Quiz-264_questions-orange?style=for-the-badge" alt="Quiz"/></a>
  <a href="./examples/"><img src="https://img.shields.io/badge/Templates-108-green?style=for-the-badge" alt="Templates"/></a>
  <a href="./guide/security-hardening.md"><img src="https://img.shields.io/badge/🛡️_Threat_DB-18_CVEs_·_341_malicious_skills-red?style=for-the-badge" alt="Threat Database"/></a>
@ -746,7 +746,7 @@ See [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines.

 ---

-*Version 3.27.2 | Updated daily · Feb 15, 2026 | Crafted with Claude*
+*Version 3.27.3 | Updated daily · Feb 16, 2026 | Crafted with Claude*

 <!-- SEO Keywords -->
 <!-- claude code, claude code tutorial, anthropic cli, ai coding assistant, claude code mcp,
--- a/2
+++ b/2
@ -1 +1 @@
-3.27.2
+3.27.3
--- a/docs/resource-evaluations/google-antigravity-evaluation.md
+++ b/docs/resource-evaluations/google-antigravity-evaluation.md
@ -0,0 +1,115 @@
+# Resource Evaluation: Google Antigravity (Agent-First IDE)
+
+**URL (trigger)**: https://www.linkedin.com/posts/prajwal-tomar-9472081a5_claude-code-antigravity-is-the-most-slept-on-activity-7428808594835558400-pui4
+**Primary Sources**: Google Codelabs, Google Cloud Blog, Bind AI, XDA Developers, npm (antigravity-claude-proxy)
+**Type**: IDE / Development Platform
+**Evaluated**: February 16, 2026
+**Score**: 3/5 (PERTINENT — complément utile)
+
+---
+
+## Executive Summary
+
+Google Antigravity is an **agent-first IDE** (VS Code fork) launched late 2025 that shifts development from traditional code editing to autonomous agent-driven workflows. It represents a fundamentally different philosophy from Claude Code: maximum agent autonomy vs explicit developer control.
+
+**Why 3/5**: Not a direct integration with Claude Code, but a significant ecosystem player that our guide should acknowledge. The philosophical contrast (terminal-first vs agent-first) is educational for readers choosing their workflow. The antigravity-claude-proxy bridge creates a concrete connection.
+
+---
+
+## Content Analysis
+
+### Key Facts (Verified)
+
+1. **Architecture**: Agent-first IDE (VS Code fork) with three surfaces — Editor, Agent Manager, Browser integration
+2. **Multi-model**: Uses Gemini 3 Pro, Claude 4.5, Liquid AI simultaneously for different tasks
+3. **Skills ecosystem**: Community repos with 58 to 856+ skills (GitHub repos verified: rmyndharis/antigravity-skills, sickn33/antigravity-awesome-skills)
+4. **Pricing**: $20/month (bundled) or $80-90/month
+5. **Claude bridge**: `antigravity-claude-proxy` npm package — proxy server exposing Anthropic-compatible API backed by Antigravity's Cloud Code
+
+### Philosophy Comparison
+
+| Dimension | Claude Code | Google Antigravity |
+|-----------|-------------|-------------------|
+| **Paradigm** | Terminal-first, CLI-native | Agent-first, IDE-native |
+| **Developer control** | Explicit approval per edit | Higher autonomy, agents act independently |
+| **Context model** | Codebase-level via CLAUDE.md | Multi-surface (editor + browser + terminal) |
+| **CI/CD** | Native (headless, pipelines) | Not mature |
+| **Risk profile** | Predictable, conservative | Higher autonomy = higher risk of overstep |
+| **Multi-agent** | Agent Teams (v2.1+) | Built-in multi-agent orchestration |
+| **Skills** | `.claude/skills/` (YAML frontmatter) | Directory-based, different format |
+| **Pricing** | Max plan subscription | $20-90/month |
+
+---
+
+## Fact-Check
+
+| Claim | Status | Source |
+|-------|--------|--------|
+| Antigravity = VS Code fork, agent-first | ✅ Verified | Google Codelabs, Google Cloud Blog |
+| Multi-model (Gemini + Claude + Liquid AI) | ✅ Verified | Multiple reviews, Vertu, Emergent.sh |
+| $20/month pricing | ✅ Verified | Vertu review, multiple sources |
+| Skills ecosystem (community repos) | ✅ Verified | GitHub repos (rmyndharis, sickn33, Sounder25) |
+| antigravity-claude-proxy exists | ✅ Verified | npm package, GitHub repo (badrisnarayanan) |
+| "50,000+ stars" (from LinkedIn post) | ⚠️ Unverifiable | Likely refers to Antigravity repo, not skills |
+| 32 min benchmark (vs 5-10 min Copilot) | ⚠️ Single source | addshore.com blog, not peer-reviewed |
+| Google official comparison page | ✅ Verified | cloud.google.com/blog (Antigravity vs Gemini CLI) |
+
+---
+
+## Gap Analysis
+
+| Aspect | Our Guide | Gap? |
+|--------|-----------|------|
+| IDE-based tools (Cursor, Windsurf, Cline) | ✅ Section 6 | No |
+| Agent-first IDEs (Antigravity) | ❌ Not mentioned | **Yes** |
+| Claude Code vs Antigravity comparison | ❌ Not covered | **Yes** |
+| antigravity-claude-proxy bridge | ❌ Not documented | **Minor gap** |
+| Skills format comparison (SKILL.md vs AG skills) | ❌ Not covered | **Minor gap** |
+| Multi-model orchestration concept | ✅ Partially (Section 8) | No |
+
+---
+
+## Integration Recommendation
+
+### Where
+
+**Section 6.1**: New subsection after Section 6 (IDE-Based Tools), before Section 7.
+
+Title: `## 6.1 Google Antigravity (Agent-First IDE)`
+
+### What to Include
+
+1. **What it is** (3 lines): Agent-first IDE, VS Code fork, multi-agent orchestration
+2. **Philosophy comparison**: Terminal-first vs agent-first (table)
+3. **Bridge tool**: antigravity-claude-proxy npm package
+4. **Trade-offs**: Autonomy vs predictability, CI/CD maturity, cognitive overhead
+5. **When to consider**: Vibe coding, rapid prototyping, non-CLI workflows
+
+### What NOT to Include
+
+- No tutorial (out of scope — we document Claude Code, not competitors)
+- No skills migration guide (different ecosystems)
+- No pricing deep-dive (changes too fast)
+
+### Priority
+
+**Medium** — Not urgent, but a real gap in ecosystem coverage.
+
+---
+
+## Challenge (Technical-Writer)
+
+- **Score justified**: 3/5 correct. Not 4/5 because Antigravity is a separate tool, not a Claude Code integration. Not 2/5 because the philosophical contrast is genuinely educational.
+- **Risk of non-integration**: Readers comparing tools won't find Antigravity in our guide. The AI Coding Agents Matrix (Section 11) partially covers this, but lacks the nuanced comparison we can provide.
+- **Score adjusted**: 3/5 (unchanged)
+
+---
+
+## Decision
+
+| Criterion | Value |
+|-----------|-------|
+| **Final score** | 3/5 |
+| **Action** | Integrate as Section 6.1 in ai-ecosystem.md |
+| **Confidence** | High (multiple primary sources verified) |
+| **Priority** | Medium |
--- a/guide/ai-ecosystem.md
+++ b/guide/ai-ecosystem.md
@ -21,6 +21,7 @@ tags: [ai-ecosystem, guide, workflows, integration]
 - [4. NotebookLM (Synthesis & Audio)](#4-notebooklm-synthesis--audio)
 - [5. Voice-to-Text Tools (Wispr Flow, Superwhisper)](#5-voice-to-text-tools-wispr-flow-superwhisper)
 - [6. IDE-Based Tools (Cursor, Windsurf, Cline)](#6-ide-based-tools-cursor-windsurf-cline)
+- [6.1 Google Antigravity (Agent-First IDE)](#61-google-antigravity-agent-first-ide)
 - [7. UI Prototypers (v0, Bolt, Lovable)](#7-ui-prototypers-v0-bolt-lovable)
 - [8. Workflow Orchestration](#8-workflow-orchestration)
 - [9. Cost & Subscription Strategy](#9-cost--subscription-strategy)
@ -1362,6 +1363,49 @@ When you need Claude's deeper analysis:

 ---

+## 6.1 Google Antigravity (Agent-First IDE)
+
+> **Source**: [Google Codelabs](https://codelabs.developers.google.com/getting-started-google-antigravity), [Google Cloud Blog](https://cloud.google.com/blog/topics/developers-practitioners/choosing-antigravity-or-gemini-cli), community reviews (Feb 2026)
+
+Google Antigravity is an **agent-first IDE** (VS Code fork) launched late 2025. Unlike traditional IDE tools that add AI to an editor, Antigravity makes autonomous agents the primary interface — developers supervise through a mission control-style UI rather than writing code directly.
+
+### Claude Code vs Antigravity: Two Philosophies
+
+| Dimension | Claude Code | Google Antigravity |
+|-----------|-------------|-------------------|
+| **Paradigm** | Terminal-first, CLI-native | Agent-first, IDE-native |
+| **Developer control** | Explicit approval per edit | Higher agent autonomy |
+| **Context model** | Codebase-level via CLAUDE.md | Multi-surface (editor + browser + terminal) |
+| **Multi-agent** | Agent Teams (v2.1+) | Built-in multi-agent orchestration |
+| **CI/CD** | Native (headless, pipelines) | Not mature yet |
+| **Risk profile** | Predictable, conservative | Higher autonomy = higher overstep risk |
+| **Skills format** | `.claude/skills/` (YAML frontmatter) | Directory-based, different ecosystem |
+| **Models** | Claude (Anthropic) | Multi-model (Gemini, Claude, Liquid AI) |
+
+### Bridge: antigravity-claude-proxy
+
+A community [npm package](https://www.npmjs.com/package/antigravity-claude-proxy) exposes an Anthropic-compatible API backed by Antigravity's Cloud Code service. This lets developers use Claude models through Antigravity's interface, or chain both tools in a single workflow.
+
+### When to Consider Antigravity
+
+| Scenario | Recommendation |
+|----------|---------------|
+| Rapid prototyping ("vibe coding") | Antigravity (higher autonomy, visual feedback) |
+| Production code with CI/CD | Claude Code (predictable, headless, pipeline-native) |
+| Multi-model experimentation | Antigravity (~150 models via OpenRouter) |
+| Team standardization | Claude Code (CLAUDE.md, skills, hooks ecosystem) |
+| Non-CLI developers | Antigravity (IDE-native, less terminal friction) |
+
+### Trade-offs to Know
+
+**Antigravity strengths**: Broader visual context (agents "see" browser + editor), parallel agent orchestration, lower barrier for non-CLI developers.
+
+**Antigravity weaknesses**: Higher cognitive overhead (monitoring multiple agents), less predictable behavior, CI/CD not mature, destructive operations risk when agents act autonomously.
+
+**Bottom line**: Claude Code optimizes for **predictability and integration with existing developer workflows**. Antigravity optimizes for **maximum agent autonomy with experimental trade-offs**. They serve different philosophies — choose based on your risk tolerance and workflow preferences.
+
+---
+
 ## 7. UI Prototypers (v0, Bolt, Lovable)

 ### When to Use Prototypers
--- a/guide/cheatsheet.md
+++ b/guide/cheatsheet.md
@ -12,7 +12,7 @@ tags: [cheatsheet, reference]

 **Written with**: Claude (Anthropic)

-**Version**: 3.27.2 | **Last Updated**: February 2026
+**Version**: 3.27.3 | **Last Updated**: February 2026

 ---

@ -544,4 +544,4 @@ where.exe claude; claude doctor; claude mcp list

 **Author**: Florian BRUNIAUX | [@Méthode Aristote](https://methode-aristote.fr) | Written with Claude

-*Last updated: February 2026 | Version 3.27.2*
+*Last updated: February 2026 | Version 3.27.3*
--- a/guide/claude-code-releases.md
+++ b/guide/claude-code-releases.md
@ -10,7 +10,7 @@ tags: [reference, release]
 > **Full details**: [github.com/anthropics/claude-code/CHANGELOG.md](https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md)
 > **Machine-readable**: [claude-code-releases.yaml](../machine-readable/claude-code-releases.yaml)

-**Latest**: v2.1.41 | **Updated**: 2026-02-13
+**Latest**: v2.1.42 | **Updated**: 2026-02-16

 ---

@ -25,6 +25,14 @@ tags: [reference, release]

 ## 2.1.x Series (January-February 2026)

+### v2.1.42 (2026-02-14)
+
+- **Improved**: Startup performance via deferred Zod schema construction (faster on large projects)
+- **Improved**: Prompt cache hit rate by moving date outside the system prompt (avoids daily cache invalidation)
+- **New**: Opus 4.6 effort callout for eligible users (one-time onboarding)
+- Fixed: `/resume` showing interrupt messages as session titles
+- Fixed: Image dimension limit errors now suggest using `/compact` instead of opaque failure
+
 ### v2.1.41 (2026-02-13)

 - **New**: `claude auth login`, `claude auth status`, `claude auth logout` CLI subcommands
--- a/guide/ultimate-guide.md
+++ b/guide/ultimate-guide.md
@ -16,7 +16,7 @@ tags: [guide, reference, workflows, agents, hooks, mcp, security]

 **Last updated**: January 2026

-**Version**: 3.27.2
+**Version**: 3.27.3

 ---

@ -4289,7 +4289,7 @@ The `.claude/` folder is your project's Claude Code directory for memory, settin
 | Personal preferences | `CLAUDE.md` | ❌ Gitignore |
 | Personal permissions | `settings.local.json` | ❌ Gitignore |

-### 3.27.2 Version Control & Backup
+### 3.27.3 Version Control & Backup

 **Problem**: Without version control, losing your Claude Code configuration means hours of manual reconfiguration across agents, skills, hooks, and MCP servers.

@ -19558,4 +19558,4 @@ We'll evaluate and add it to this section if it meets quality criteria.

 **Contributions**: Issues and PRs welcome.

-**Last updated**: January 2026 | **Version**: 3.27.2
+**Last updated**: January 2026 | **Version**: 3.27.3
--- a/machine-readable/claude-code-releases.yaml
+++ b/machine-readable/claude-code-releases.yaml
@ -3,8 +3,8 @@
 # Purpose: Track Claude Code product releases for documentation sync
 # Maintained: Manual updates when new releases are announced

-latest: "2.1.41"
-updated: "2026-02-13"
+latest: "2.1.42"
+updated: "2026-02-16"

 # ════════════════════════════════════════════════════════════════
 # RELEASES (newest first, condensed highlights only)
@ -15,6 +15,15 @@ releases:
  # 2.1.x Series (January-February 2026)
  # ─────────────────────────────────────────────────────────────

+  - version: "2.1.42"
+    date: "2026-02-14"
+    highlights:
+      - "Optimized startup via deferred Zod schema construction"
+      - "Improved prompt cache hit rate by moving date outside system prompt"
+      - "Opus 4.6 effort callout for eligible users"
+      - "Better error messaging for image dimension limits (suggests `/compact`)"
+    breaking: []
+
  - version: "2.1.41"
    date: "2026-02-13"
    highlights:
--- a/machine-readable/reference.yaml
+++ b/machine-readable/reference.yaml
@ -3,7 +3,7 @@
 # Source: guide/ultimate-guide.md
 # Purpose: Condensed index for LLMs to quickly answer user questions about Claude Code

-version: "3.27.2"
+version: "3.27.3"
 updated: "2026-02-09"

 # ════════════════════════════════════════════════════════════════
@ -60,6 +60,12 @@ deep_dive:
  rtk_version_tested: "v0.16.0"
  rtk_score: "5/5"
  rtk_installation: "cargo install rtk or brew install rtk-ai/tap/rtk"
+  # Google Antigravity (Agent-First IDE)
+  antigravity_guide: "guide/ai-ecosystem.md:1367"
+  antigravity_evaluation: "docs/resource-evaluations/google-antigravity-evaluation.md"
+  antigravity_proxy: "https://www.npmjs.com/package/antigravity-claude-proxy"
+  antigravity_codelabs: "https://codelabs.developers.google.com/getting-started-google-antigravity"
+  antigravity_vs_claude: "Claude Code = terminal-first predictability; Antigravity = agent-first autonomy"
  # PDF Generation
  pdf_generation: "guide/workflows/pdf-generation.md"
  pdf_generator_skill: "examples/skills/pdf-generator.md"
@ -172,7 +178,7 @@ deep_dive:
  third_party_toad: "https://github.com/batrachianai/toad"
  third_party_conductor: "https://docs.conductor.build"
  # Configuration Management & Backup (Added 2026-02-02)
-  config_management_guide: "guide/ultimate-guide.md:4085"  # Section 3.27.2
+  config_management_guide: "guide/ultimate-guide.md:4085"  # Section 3.27.3
  config_hierarchy: "guide/ultimate-guide.md:4095"  # Global → Project → Local precedence
  config_git_strategy_project: "guide/ultimate-guide.md:4110"  # What to commit in .claude/
  config_git_strategy_global: "guide/ultimate-guide.md:4133"  # Version control ~/.claude/
@ -1185,7 +1191,7 @@ ecosystem:
      - "Cross-links modified → Update all 4 repos"
    history:
      - date: "2026-01-20"
-        event: "Code Landing sync v3.27.2, 66 templates, cross-links"
+        event: "Code Landing sync v3.27.3, 66 templates, cross-links"
        commit: "5b5ce62"
      - date: "2026-01-20"
        event: "Cowork Landing fix (paths, README, UI badges)"
@ -1197,7 +1203,7 @@ ecosystem:
 onboarding_matrix_meta:
  version: "2.0.0"
  last_updated: "2026-02-05"
-  aligned_with_guide: "3.27.2"
+  aligned_with_guide: "3.27.3"
  changelog:
    - version: "2.0.0"
      date: "2026-02-05"
@ -1225,7 +1231,7 @@ onboarding_matrix:
      core: [rules, sandbox_native_guide, commands]
      time_budget: "5 min"
      topics_max: 3
-      note: "SECURITY FIRST - sandbox before commands (v3.27.2 critical fix)"
+      note: "SECURITY FIRST - sandbox before commands (v3.27.3 critical fix)"

    beginner_15min:
      core: [rules, sandbox_native_guide, workflow, essential_commands]
@ -1310,7 +1316,7 @@ onboarding_matrix:
        - default: agent_validation_checklist
      time_budget: "60 min"
      topics_max: 6
-      note: "Dual-instance pattern for quality workflows (v3.27.2)"
+      note: "Dual-instance pattern for quality workflows (v3.27.3)"

  learn_security:
    intermediate_30min:
@ -1321,7 +1327,7 @@ onboarding_matrix:
        - default: permission_modes
      time_budget: "30 min"
      topics_max: 4
-      note: "NEW goal (v3.27.2) - Security-focused learning path"
+      note: "NEW goal (v3.27.3) - Security-focused learning path"

    power_60min:
      core: [sandbox_native_guide, mcp_secrets_management, security_hardening]
@ -1346,7 +1352,7 @@ onboarding_matrix:
      core: [rules, sandbox_native_guide, workflow, essential_commands, context_management, plan_mode]
      time_budget: "60 min"
      topics_max: 6
-      note: "Security foundation + core workflow (v3.27.2 sandbox added)"
+      note: "Security foundation + core workflow (v3.27.3 sandbox added)"

    intermediate_120min:
      core: [plan_mode, agents, skills, config_hierarchy, git_mcp_guide, hooks, mcp_servers]
 @ -1 +1 @@
 .27.2
 .27.3