The plugin had hardcoded references to 'CORA' (Every's internal project)
throughout the documentation workflow, making it project-specific rather
than generic. This affected users trying to use the plugin on non-CORA
projects.
Changes:
- Replace 'cora-critical-patterns.md' with 'critical-patterns.md'
- Replace 'Which CORA module' with 'Which module or component'
- Replace 'CORA-Specific Resources' with 'Project-Specific Resources'
- Replace 'CORA-MODULES.md' with 'modules documentation'
- Replace 'CORA system' with 'System-wide' in templates
- Update cora-test-reviewer description to be generic
Files modified:
- learnings-researcher.md: Fixed critical patterns file reference
- compound-docs/SKILL.md: Removed module and filename hardcoding
- compound-docs/assets/*.md: Generalized template references
- workflows/compound.md: Changed 'CORA schema' to 'solution schema'
- workflows/work.md: Made test reviewer description generic
This makes the plugin truly project-agnostic as advertised.
- Bump version to 2.28.0 in plugin.json and marketplace.json
(CHANGELOG was updated but version numbers were missed)
- Fix all repo URLs from kieranklaassen/* to EveryInc/compound-engineering-plugin
- Update component counts in docs: 28 agents, 24 commands, 15 skills, 1 MCP
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(compound-docs): correct severity enum in validation example
The example error message referenced [critical, moderate, minor] but
the yaml-schema.md defines severity as [critical, high, medium, low].
* refactor(agents): standardize search tool recommendations
- Update repo-research-analyst to recommend built-in Grep tool instead
of CLI rg (Grep uses ripgrep under the hood)
- Add TypeScript example for ast-grep alongside Ruby
- Update pattern-recognition-specialist to use built-in Grep tool
- Keep ast-grep for AST-based structural matching (language-specific)
* feat(agents): add learnings-researcher for institutional knowledge
Add new research agent that efficiently searches docs/solutions/ for
relevant past solutions before implementing features or fixing bugs.
Key features:
- Grep-first filtering strategy for efficiency with 100+ files
- Category-based narrowing to reduce search scope
- Parallel Grep calls with synonym support (OR patterns)
- Frontmatter-only reads before full document reads
- Always checks critical patterns file
- Uses haiku model for speed (structured task, recipe-based)
Integrates with /workflows:plan to run in parallel with
repo-research-analyst during local research phase.
Closes the loop on compound engineering: solutions documented via
/workflows:compound are now discoverable during planning.
- Move plans from `plans/` to `docs/plans/` for consistency with other artifacts
- Add date prefix (YYYY-MM-DD) to both plans and brainstorms for chronological sorting
- Add self-documenting suffixes: `-plan` and `-brainstorm` to identify artifact type
- Update filename derivation to extract title from content, not filename
- Clarify deepened plan naming: append `-deepened` after `-plan` suffix
New conventions:
- Brainstorms: `docs/brainstorms/YYYY-MM-DD-<topic>-brainstorm.md`
- Plans: `docs/plans/YYYY-MM-DD-<type>-<name>-plan.md`
- Deepened: `docs/plans/YYYY-MM-DD-<type>-<name>-plan-deepened.md`
* feat(workflows:plan): Add smart research decision logic
Previously, /workflows:plan always ran all 3 research agents (repo-research,
best-practices, framework-docs) regardless of task complexity. This wasted
tokens and time for simple tasks like UI tweaks or bug fixes with clear causes.
Now the workflow:
- Always runs repo research first (fast, local)
- Makes an informed decision about external research based on:
- Signals gathered during idea refinement (familiarity, intent, risk)
- Repo research findings (existing patterns, CLAUDE.md guidance)
- High-risk topics (security, payments, external APIs) always trigger research
- Strong local context allows skipping external research
- Announces the decision and proceeds, user can redirect if needed
This makes the planning workflow smarter about when web research adds value.
* feat: Add /workflows:brainstorm command and skill
Add brainstorming workflow to explore requirements and approaches
before planning implementation:
- New `/workflows:brainstorm` command for collaborative dialogue
- New `brainstorming` skill with process knowledge and techniques
- Update `/workflows:plan` to detect brainstorm output and skip
idea refinement when relevant brainstorm exists
- Add brainstorm to README workflow commands table
The brainstorm → plan flow enables:
- Phase 0: Assess requirement clarity
- Phase 1: Understand the idea via repo research + dialogue
- Phase 2: Explore 2-3 approaches with trade-offs
- Phase 3: Capture design to docs/brainstorms/
- Phase 4: Handoff to /workflows:plan
Add deprecation/sunset checks to research agents before they recommend
external APIs, OAuth flows, or third-party services.
Changes:
- framework-docs-researcher: Added step 2 "Deprecation/Sunset Check"
and updated Quality Standards
- best-practices-researcher: Added Phase 1.5 "MANDATORY Deprecation Check"
This prevents wasted development time on deprecated APIs. For example,
Google Photos Library API scopes were deprecated in March 2025, and
without validation, developers can spend hours debugging OAuth errors
on dead APIs.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Add two new phases to improve plan quality through user collaboration:
- Phase 0: Idea Refinement - Refines feature ideas through dialogue
before running research agents. Asks questions one at a time,
prefers multiple choice, focuses on purpose/constraints/success
criteria. Skip option for detailed descriptions.
- Research Validation - After research completes, summarizes findings
and validates alignment before drafting the full plan.
Both phases are optional and can be skipped, ensuring the workflow
remains lightweight while catching misunderstandings early.
- Update "current year is 2025" to 2026 in 4 research agents
- Update year ranges to 2024-2026 for content searches in deepen-plan
and create-agent-skills workflows
- Change "currency" to "recency" for clarity in domain expertise skill
- Add branch detection at start of Setup Environment step
- Support continuing on existing feature branch or creating new
- Require explicit confirmation to commit to default branch
- Add incremental commit guidance with decision criteria table
- Include heuristic: "Can I write a meaningful commit message?"
- Generalize test commands to be framework-agnostic
- Remove quotes from the routing table's Response column
- Add blank line after <routing> tag to allow markdown parsing
GitHub treats custom XML tags as HTML, requiring a blank line
before markdown content to render correctly.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
- Renamed every-marketplace to compound-marketplace
- Updated all EveryInc references to kieranklaassen
- Updated owner info in marketplace.json
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Added step to update original plan document with completed checkboxes
([ ] → [x]) after each task is finished. Keeps the plan as a living
document showing progress.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Updated PR template to include badge at bottom linking to plugin repo
- Added badge requirement to quality checklist
- Badge provides attribution and link to the plugin
Co-Authored-By: Claude <noreply@anthropic.com>
Skills are auto-loaded in context, no need to manually cat files.
Simplified Step 0 to just reference loaded skill context.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added "Step 0: Discover and Load Design Skills (MANDATORY)"
- Discovers skills from all locations (plugin, global, project)
- Maps user context to relevant skills (Swiss → swiss-design, etc.)
- Changed iteration approach: ONE change per iteration, not 3-5
- Updated output format: focus on single most impactful change
- Added rule: "If you can't identify ONE clear improvement, stop"
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Phase 1: Discover and read relevant SKILL.md files before going online
- Add skill mappings for common technologies (Rails, Frontend, AI, etc.)
- Only proceed to online research if skills don't provide enough coverage
- Prioritize skill-based guidance with clear source attribution
- Synthesize findings from skills + online sources
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Orchestrates: plan → deepen-plan → work → review → resolve todos → test-browser → feature-video
- Uses ralph-loop for autonomous completion
- Migrated from local command
- Updated to use /test-browser instead of /playwright-test
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- 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>
The /workflows:plan skill was producing inconsistent plan filenames
(sometimes gibberish, sometimes descriptive) because it lacked explicit
rules for converting issue titles to filenames.
Changes:
- Step 2: Added instruction to convert title to kebab-case filename
with example transformation (feat: Add User Auth → feat-add-user-auth.md)
- Output Format: Replaced vague <issue_title> placeholder with clear
pattern and good/bad examples
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Enhanced /reproduce-bug command with browser automation:
- Added Phase 2 for visual bug reproduction using Playwright MCP
- Step-by-step guide for navigating to affected areas
- Screenshot capture at each reproduction step
- Console error checking
- User flow reproduction with clicks, typing, snapshots
- Better documentation structure with 4 clear phases
🤖 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>
- Add low-quality preview GIF creation (640px, 128 colors)
- Use --s3-no-check-bucket flag for rclone uploads
- Document GitHub limitation: external MP4s don't embed
- Use clickable GIF linking to video for PR descriptions
🤖 Generated with [Claude Code](https://claude.com/claude-code)
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>
- Read frontmatter (title, category, tags, module, symptom) of each learning
- Compare against plan to determine relevance
- SKIP learnings that are clearly not applicable
- SPAWN sub-agents only for learnings that MIGHT apply
- Example: 15 files found → filter to 3 relevant → spawn 3 sub-agents
Smarter than spawning 50 sub-agents when only 5 are relevant.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Discover documented learnings from /workflows:compound
- Project docs/solutions/
- User ~/.claude/docs/
- Plugin docs/
- Spawn sub-agent for EACH learning to check if relevant to plan
- All learning sub-agents run in parallel
- Categories: performance-issues, debugging-patterns, config-fixes, etc.
- Added learnings to synthesis sources
- Fixed section numbering (now 1-9)
Institutional knowledge - prevents repeating past mistakes.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Spawn a separate sub-agent for EVERY matched skill
- Each sub-agent reads and USES its assigned skill's SKILL.md
- All skill sub-agents run in parallel (10, 20, 30 is fine)
- Enhanced synthesis step to collect from ALL sources:
- Skill sub-agent outputs
- Research agents
- Review agents
- Context7 queries
- Web searches
- Deduplicate and prioritize findings before enhancing plan
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Dynamically discover ALL skills from all sources:
- Project .claude/skills/
- User ~/.claude/skills/
- compound-engineering plugin
- ALL other installed plugins
- Dynamically discover ALL agents from all sources:
- Project .claude/agents/
- User ~/.claude/agents/
- All installed plugins (not just compound-engineering)
- Local plugins
- Run ALL discovered agents in parallel (40+ is fine)
- No filtering by "relevance" - use everything available
- Match skills to plan sections and spawn sub-agents
🤖 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>
