- Add Step 0 asking user if they want to watch browser tests
- Headed mode opens visible browser window
- Headless mode runs faster in background
- Bump version to 2.25.0
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Remove Playwright MCP server from plugin
- Add new agent-browser skill for CLI-based browser automation
- Rename /playwright-test to /test-browser command
- Update all commands and agents to use agent-browser CLI
- Update README and plugin.json
agent-browser is Vercel's headless browser CLI designed for AI agents.
It uses ref-based selection (@e1, @e2) from accessibility snapshots
and provides a simpler CLI interface compared to MCP tools.
Key benefits:
- No MCP server required
- Simpler Bash-based workflow
- Same ref-based element selection
- Better for quick automation tasks
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
All 26 agents now use `model: inherit` so they match whatever model
the user has configured in their main conversation.
Only `lint` keeps `model: haiku` since it's a simple task.
Fixes#69
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- New command for comprehensive agent-native architecture review
- Launches 8 parallel sub-agents, one per core principle
- Principles: Action Parity, Tools as Primitives, Context Injection,
Shared Workspace, CRUD Completeness, UI Integration, Capability
Discovery, Prompt-Native Features
- Each agent produces specific score (X/Y format with percentage)
- Generates summary report with overall score and top 10 recommendations
- Supports single principle audit via argument
Co-Authored-By: Claude <noreply@anthropic.com>
The previous version incorrectly recommended XML tags for skill body content.
Anthropic's official specification uses standard markdown headings.
Changes:
- SKILL.md: Complete rewrite using markdown format, not XML tags
- Added references/official-spec.md from code.claude.com/docs/en/skills
- Added references/best-practices.md from platform.claude.com
- Removed obsolete use-xml-tags.md
- Updated naming to gerund form (creating-agent-skills)
- Descriptions now third person with "what" and "when"
BREAKING: If you followed the old XML tag guidance, convert to markdown headings.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add /deepen-plan command that enhances plans with parallel research agents
- Each plan section gets its own sub-agent for best practices, performance, UI research
- Update /workflows:plan to offer /deepen-plan as option 2 after plan creation
- Auto-run /deepen-plan when using ultrathink mode for maximum depth
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* [2.17.0] Expand agent-native skill with mobile app learnings
Major expansion of agent-native-architecture skill based on real-world
learnings from building the Every Reader iOS app.
New reference documents:
- dynamic-context-injection.md: Runtime app state in system prompts
- action-parity-discipline.md: Ensuring agents can do what users can
- shared-workspace-architecture.md: Agents and users in same data space
- agent-native-testing.md: Testing patterns for agent-native apps
- mobile-patterns.md: Background execution, permissions, cost awareness
Updated references:
- architecture-patterns.md: Added Unified Agent Architecture, Agent-to-UI
Communication, and Model Tier Selection patterns
Enhanced agent-native-reviewer with comprehensive review process covering
all new patterns, including mobile-specific verification.
Key insight: "The agent should be able to do anything the user can do,
through tools that mirror UI capabilities, with full context about the
app state."
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* [2.18.0] Add Dynamic Capability Discovery and iCloud sync patterns
New patterns in agent-native-architecture skill:
- **Dynamic Capability Discovery** - For agent-native apps integrating with
external APIs (HealthKit, HomeKit, GraphQL), use a discovery tool (list_*)
plus a generic access tool instead of individual tools per endpoint.
(Note: Static mapping is fine for constrained agents with limited scope.)
- **CRUD Completeness** - Every entity needs create, read, update, AND delete.
- **iCloud File Storage** - Use iCloud Documents for shared workspace to get
free, automatic multi-device sync without building a sync layer.
- **Architecture Review Checklist** - Pushes reviewer findings earlier into
design phase. Covers tool design, action parity, UI integration, context.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Fixed issues flagged by skill-creator spec:
- Reference files now use proper markdown links instead of backtick text
- Descriptions use third person ("This skill should be used when...")
- Added Skill Compliance Checklist to CLAUDE.md with validation commands
Affected skills: agent-native-architecture, andrew-kane-gem-writer,
compound-docs, create-agent-skills, dhh-rails-style, dhh-ruby-style,
dspy-ruby, every-style-editor, file-todos, frontend-design, gemini-imagegen
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- New `/xcode-test` command for building and testing iOS apps
- Uses XcodeBuildMCP to discover projects, build, install, launch
- Takes screenshots and captures console logs
- Supports human verification for Sign in with Apple, push, IAP
- Checks for XcodeBuildMCP installation before proceeding
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- New `/playwright-test` command for end-to-end browser tests on PR-affected pages
- Uses Playwright MCP to navigate, snapshot, check console errors
- Supports human-in-the-loop for OAuth/email/payment flows
- Creates P1 todos for failures and retries until passing
- Added Section 7 to `/workflows:review` - optional Playwright testing as subagent
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Router-pattern skill with sectioned references:
- controllers.md: REST mapping, concerns, Turbo, API patterns
- models.md: Concerns, state records, callbacks, scopes
- frontend.md: Turbo, Stimulus, CSS architecture
- architecture.md: Routing, auth, jobs, caching, config
- gems.md: What they use vs avoid, decision framework
Based on analysis of Fizzy (Campfire) codebase.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
New review agents for validating database migrations and risky data deployments:
- data-migration-expert: Validates ID mappings match production reality, checks
for swapped values, verifies rollback safety, provides SQL verification snippets
- deployment-verification-agent: Produces Go/No-Go deployment checklists with
pre/post-deploy SQL queries, data invariants, rollback procedures, monitoring
Updated /workflows:review to conditionally run these agents when PRs contain
database migrations (db/migrate/*.rb), data backfills, or ID/enum mappings.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Fixes#41
The /prime command was a personal setup command that shouldn't have been
included in the distributed plugin. It caused confusion when users had
hooks that auto-invoked it on session start.
Users who want a prime command can add it to their personal ~/.claude/commands/
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Fixes#42
Workflow commands now use `workflows:` prefix to avoid collisions with
Claude Code's built-in commands:
- `/workflows:plan` (was `/plan`)
- `/workflows:review` (was `/review`)
- `/workflows:work` (was `/work`)
- `/workflows:compound` (was `/compound`)
To upgrade: Update to latest plugin version. If you see duplicate `/plan`
commands, the new namespaced commands avoid this collision.
Also fixed in this release:
- Added missing `name:` field to heal-skill.md and create-agent-skill.md
- Rewrote corrupted prime.md
- Shortened Playwright MCP alias from `playwright` to `pw`
- Removed deprecated codify.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add agent-native-reviewer agent to verify features are agent-accessible
- Add agent-native-architecture skill for prompt-native design patterns
- Add agent-native-reviewer to /review command parallel agents
- Move agent-native skill to correct plugin folder
- Update component counts (25 agents, 12 skills)
- Include mermaid dark mode fix from PR #45🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Made capturing screenshots REQUIRED for any UI changes
- Updated to use imgup skill with pixhost as default host
- Clarified what to capture: new screens, before/after, Figma matches
- Removed outdated curl/0x0.st reference
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added "Open plan in editor" as the first option in post-generation menu
- Opens plan file in user's default editor for review before next steps
- Reordered options: open → review → work → work remote → create issue → simplify
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added step to capture before/after screenshots for UI changes
- Use Playwright MCP tools for screenshots
- Upload via 0x0.st (imgup skill)
- Updated PR template with before/after table format
- Updated quality checklist
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Reorder options: Review first, Work locally second, Work on remote third
- Add "Work on remote" option with `&` for background execution on Claude Code web
- Remove separate "Rework" option since "Other" handles custom changes
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
BREAKING: Plugin renamed from compounding-engineering to compound-engineering.
Users will need to reinstall with the new name:
claude /plugin install compound-engineering
Changes:
- Renamed plugin directory and all references
- Updated documentation counts (24 agents, 19 commands)
- Added julik-frontend-races-reviewer to docs
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
