mirror of
https://github.com/luongnv89/claude-howto.git
synced 2026-07-25 11:40:52 +02:00
Luong NGUYEN
8f045173d1
* docs: sync to Claude Code v2.1.212 Bumps tutorial coverage from the v2.1.206 baseline (2026-07-11 sync) to v2.1.212, plus a repo-internal accuracy audit that surfaced defects independent of the version delta. Fixed: - Dead `#` memory-shortcut removed from 02-memory/README.md (two places documented a discontinued quick-memory-add pattern as working, directly contradicting the file's own commands table) - Auto mode opt-in -> opt-out on Bedrock/Vertex/Foundry (v2.1.207) - `auto` permission mode mislabeled "Research Preview" across 09-advanced-features/README.md, CATALOG.md, README.md, and the vi/ja/zh/uk translations (auto mode is GA, gated only by plan/model/provider) - `/fork` / `/branch` history corrected: they were a single aliased command only from v2.1.77 to v2.1.161, not "renamed" as previously stated - `effort` frontmatter enum in 04-subagents/README.md completed with `xhigh` - Bundled-skills count reconciled in CATALOG.md (9 -> 10) - INDEX.md Skills section count and Feature Coverage Matrix Total column fully recomputed and reconciled (Skills: 22, Plugins: 39) - Stale 2.1.160 footer cluster (5 files) bumped to 2.1.212 - QUICK_REFERENCE.md fully resynced (was 52 versions behind) - 02-memory/README.md's Memory Hierarchy section rewritten: replaced a fabricated 8-tier strict-precedence model with the verified structure (CLAUDE.md files are concatenated into context, not overridden; 4 real location tiers; rules and auto memory are separate mechanisms) - 02-memory/README.md's Memory Architecture diagram no longer conflates claude.ai's 24h synthesis cycle with Claude Code's continuous auto memory - Import recursion depth corrected (was documented as 5, actually 4 hops) Added: - Subagent output scanning (v2.1.210) documented in 04-subagents/README.md - Session-wide spawn caps (v2.1.212): WebSearch and subagent limits - MCP long-running-tool auto-backgrounding (v2.1.212) in 05-mcp/README.md - `claude auto-mode reset` and `/resume` picker (v2.1.212) - Screen reader mode (v2.1.208): --ax-screen-reader / CLAUDE_AX_SCREEN_READER - Task tool `mode` parameter deprecation note (v2.1.212) Known gaps (deferred, not fixed this pass): - 03-skills/blog-draft/ vs 03-skills/.claude/skills/blog-draft/: confirmed the latter is gitignored local testing scratch, not a repo duplicate * fix(INDEX): correct Skills row arithmetic and stale changelog notes INDEX.md's Skills header/matrix shipped as 22 (5+9+8) despite the PR's own CHANGELOG claiming it was fixed to 21 — three independent counts (file-type breakdown, filesystem listing, changelog intent) agree on 21; the Docs column was off by one. Also removes two stale CHANGELOG "Known gaps" entries this same PR already resolved (memory hierarchy rewrite, blog-draft gitignore confirmation) and adds the missing Fixed-section bullet documenting the memory hierarchy rewrite.
9.2 KiB
9.2 KiB
Checkpoint Examples
Real-world examples of using checkpoints effectively in Claude Code.
Note: Checkpoints are created automatically with every user prompt. You do not need to manually save them. To rewind, press Esc twice (Esc+Esc) or use /rewind to open the checkpoint browser.
Example 1: Database Migration
Scenario
You need to migrate from MySQL to PostgreSQL but want to explore both a direct migration and a gradual dual-write approach.
Workflow
User: Let's implement a direct migration from MySQL to PostgreSQL
[Checkpoint A created automatically]
Claude: I'll implement the direct migration...
[Changes database driver, updates queries, modifies schema]
User: Run the tests
[Checkpoint B created automatically]
Claude: Running tests...
❌ 15 tests failing - connection pool issues
User: This approach has issues. Let's try the dual-write pattern instead.
[User presses Esc+Esc, selects Checkpoint A, chooses "Restore code and conversation"]
User: Now implement a dual-write pattern where we write to both databases
Claude: I'll implement dual-write migration...
[Implements dual-write layer, gradual migration strategy]
User: Run the tests
Claude: Running tests...
✅ All tests passing
User: The dual-write approach is clearly safer. Let's commit this.
Example 2: Performance Optimization
Scenario
Multiple performance optimization strategies to try.
Workflow
User: Let's optimize the API response time. Current: 450ms
[Checkpoint "Baseline" created automatically]
Claude: I'll add database query caching...
[Implements Redis caching]
User: Run performance tests
Claude: Results: 280ms average response time (38% improvement)
User: Let me try a different approach.
[User presses Esc+Esc, selects "Baseline" checkpoint, chooses "Restore code and conversation"]
User: Try database query optimization instead
Claude: I'll optimize database queries...
[Adds indexes, optimizes N+1 queries]
User: Run performance tests
Claude: Results: 180ms average response time (60% improvement)
User: Let me also try a third approach.
[User presses Esc+Esc, selects "Baseline" checkpoint, chooses "Restore code and conversation"]
User: Try response compression and CDN
Claude: I'll add compression and CDN...
[Implements gzip, sets up CDN]
User: Run performance tests
Claude: Results: 320ms average response time (29% improvement)
User: Query optimization was the best. Let me go back and combine it with caching.
[User presses Esc+Esc, selects the checkpoint after query optimization, chooses "Restore code and conversation"]
User: Now add Redis caching on top of these optimized queries
Claude: [Adds Redis caching on top of optimized queries]
User: Run performance tests
Claude: Results: 95ms average response time (79% improvement) 🎉
User: Perfect! This is the winner. Let's commit this.
Example 3: UI/UX Iteration
Scenario
Trying different layouts for a dashboard.
Workflow
User: Let's redesign the dashboard with a sidebar layout
[Checkpoint "Start" created automatically]
Claude: [Implements sidebar layout]
User: Show me a screenshot
Claude: [Shows screenshot]
User: The sidebar feels cramped. Let's try a top navigation instead.
[User presses Esc+Esc, selects "Start" checkpoint, chooses "Restore code and conversation"]
User: Try a top navigation layout
Claude: [Implements top navigation]
User: Show me a screenshot
Claude: [Shows screenshot]
User: Better, but let's try a card-based grid layout
[User presses Esc+Esc, selects "Start" checkpoint, chooses "Restore code and conversation"]
User: Try a card-based grid layout
Claude: [Implements card grid]
User: Show me a screenshot
Claude: [Shows screenshot]
User: This is great! But can we combine the top nav with the card grid?
[User presses Esc+Esc, selects the checkpoint after the card grid, chooses "Restore code and conversation"]
User: Add top navigation to the card grid layout
Claude: [Adds top navigation to card grid]
User: Perfect! This is the final design.
Example 4: Debugging Session
Scenario
Hunting down a tricky bug with multiple hypotheses.
Workflow
User: There's a memory leak in the application
[Checkpoint "Before debugging" created automatically]
Claude: Let me investigate...
[Analyzes code]
User: I think it's in the event listeners. Let's fix those.
Claude: [Fixes event listener cleanup]
User: Run memory profiler
Claude: Still leaking memory - event listeners weren't the issue
User: Let me go back and try a different hypothesis.
[User presses Esc+Esc, selects "Before debugging" checkpoint, chooses "Restore code and conversation"]
User: Maybe it's the database connections?
Claude: [Implements connection pooling fixes]
User: Run memory profiler
Claude: Still leaking - not the connections either
User: Let me go back and try another angle.
[User presses Esc+Esc, selects "Before debugging" checkpoint, chooses "Restore code and conversation"]
User: Let's check for circular references
Claude: [Finds and fixes circular references in cache]
User: Run memory profiler
Claude: ✅ Memory leak fixed! The circular references in the caching layer were the culprit.
User: Excellent! Let's commit this fix.
Example 5: API Design Evolution
Scenario
Designing a REST API with multiple iterations.
Workflow
User: Create a REST API for our blog platform
[Checkpoint "Before API design" created automatically]
Claude: [Creates basic CRUD API]
User: This is too simple. Let's add pagination and filtering
Claude: [Adds pagination and filtering]
User: We need better resource relationships
Claude: [Implements HATEOAS links]
User: Actually, let's try GraphQL instead of REST
[User presses Esc+Esc, selects "Before API design" checkpoint, chooses "Restore code and conversation"]
User: Implement a GraphQL API for our blog platform instead
Claude: [Implements GraphQL API]
User: I think REST is better for our use case.
[User presses Esc+Esc, selects the checkpoint after HATEOAS, chooses "Restore code and conversation"]
User: Let's finalize the REST approach.
Example 6: Configuration Management
Scenario
Testing different configuration approaches.
Workflow
User: Move configuration to environment variables
[Checkpoint "Original config" created automatically]
Claude: [Implements env var configuration]
User: Test in development
Claude: Works locally but deployment issues in production
User: Let me try a different approach.
[User presses Esc+Esc, selects "Original config" checkpoint, chooses "Restore code and conversation"]
User: Try a config file approach with validation
Claude: [Implements YAML config with JSON schema validation]
User: Test in development
Claude: ✅ Works well, good validation errors
User: Can we also support env vars for sensitive values?
Claude: [Adds env var override for secrets]
User: Test deployment
Claude: ✅ All environments working correctly
User: Perfect! This is production-ready.
Example 7: Test Strategy
Scenario
Implementing comprehensive testing.
Workflow
User: Add unit tests for the auth module
[Checkpoint created automatically]
Claude: [Adds Jest unit tests]
User: Run tests
Claude: 45 tests passing, 78% coverage
User: Add integration tests too
Claude: [Adds integration tests]
User: Run tests
Claude: 89 tests passing, 92% coverage, but tests are slow (3 minutes)
User: The tests are too slow. Let's optimize.
Claude: [Optimizes test setup, adds parallel execution]
User: Run tests
Claude: 89 tests passing, 92% coverage, 35 seconds ✅
User: Great! Now add E2E tests for critical paths
Claude: [Adds Playwright E2E tests]
User: Run all tests
Claude: 112 tests passing, 94% coverage, 2 minutes
User: Perfect balance of coverage and speed!
Example 8: Using Summarize from Checkpoint
Scenario
After a long debugging session, you want to condense the conversation while preserving context.
Workflow
User: [After 20+ messages of debugging and exploration]
[User presses Esc+Esc, selects an early checkpoint, chooses "Summarize from here"]
[Optionally provides instructions: "Focus on what we tried and what worked"]
Claude: [Generates a summary of the conversation from that point forward]
[Original messages are preserved in the transcript]
[The summary replaces the visible conversation, reducing context window usage]
User: Now let's continue with the approach that worked.
Key Takeaways
- Checkpoints are automatic: Every user prompt creates a checkpoint -- no manual saving needed
- Use Esc+Esc or /rewind: These are the two ways to access the checkpoint browser
- Choose the right restore option: Restore code, conversation, both, or summarize depending on your needs
- Don't fear experimentation: Checkpoints make it safe to try radical changes
- Combine with git: Use checkpoints for exploration, git for finalized work
- Summarize long sessions: Use "Summarize from here" to keep conversations manageable
Last Updated: July 18, 2026 Claude Code Version: 2.1.212 Sources:
- https://code.claude.com/docs/en/checkpointing
- https://code.claude.com/docs/en/changelog Compatible Models: Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5