wogiflow 2.3.3 → 2.4.1

package/.claude/commands/wogi-audit.md

@@ -1,5 +1,6 @@
 ---
 description: "Comprehensive project-wide deep analysis beyond code review"
+effort: high
 ---
 Comprehensive project-wide deep analysis that goes far beyond code review. While `/wogi-review` asks "did I introduce problems?", `/wogi-audit` asks "how can we make this project better?"
 

package/.claude/commands/wogi-bug.md

@@ -1,5 +1,6 @@
 ---
 description: "Create a bug report with investigation and structured fix execution"
+effort: medium
 ---
 <!-- PINS: bug-protocol, bug-cli, bug-investigation, bug-phases, bug-population, bug-severity, bug-creation, bug-execution, bug-specific-execution, bug-learning, bug-discovery, bug-output, bug-configuration, bug-comparison -->
 

package/.claude/commands/wogi-bulk-loop.md

@@ -1,5 +1,6 @@
 ---
 description: "Continuous work loop processing captured ideas and tasks automatically"
+effort: medium
 ---
 Continuous work loop - processes captured ideas and tasks automatically.
 

package/.claude/commands/wogi-bulk.md

@@ -1,5 +1,6 @@
 ---
 description: "Execute multiple tasks in sequence following all workflow rules"
+effort: medium
 ---
 Execute multiple tasks in sequence, following all workflow rules.
 

package/.claude/commands/wogi-capture.md

@@ -1,5 +1,6 @@
 ---
 description: "Quick-capture an idea or bug without interrupting current work"
+effort: low
 ---
 Quick capture an idea or bug without interrupting your current work. Provide a brief title: `/wogi-capture Add dark mode toggle`
 

package/.claude/commands/wogi-changelog.md

@@ -1,5 +1,6 @@
 ---
 description: "Generate a CHANGELOG from request-log entries"
+effort: low
 ---
 Generate a CHANGELOG from request-log entries.
 

package/.claude/commands/wogi-config.md

@@ -1,5 +1,6 @@
 ---
 description: "View or modify workflow configuration with natural language"
+effort: medium
 ---
 Smart configuration management for WogiFlow.
 

package/.claude/commands/wogi-context.md

@@ -1,5 +1,6 @@
 ---
 description: "Load all context needed to implement a task"
+effort: low
 ---
 Load all context needed to implement a task. Provide task ID: `/wogi-context wf-012`
 

package/.claude/commands/wogi-correction.md

@@ -1,5 +1,6 @@
 ---
 description: "Create a detailed correction report for a significant bug fix"
+effort: low
 ---
 Create a detailed correction report for a significant bug fix.
 

package/.claude/commands/wogi-debt.md

@@ -1,5 +1,6 @@
 ---
 description: "View and manage technical debt across sessions"
+effort: low
 ---
 View and manage technical debt across sessions.
 

package/.claude/commands/wogi-debug-browser.md

@@ -1,5 +1,6 @@
 ---
 description: "WebMCP-powered browser debugging with structured tool calls"
+effort: high
 ---
 WebMCP-powered browser debugging - uses structured tool calls instead of screenshots for precise, token-efficient UI investigation.
 

package/.claude/commands/wogi-debug-hypothesis.md

@@ -1,5 +1,6 @@
 ---
 description: "Parallel hypothesis debugging - spawns agents for competing theories"
+effort: high
 ---
 Parallel hypothesis debugging - spawns multiple agents to investigate competing theories simultaneously.
 

package/.claude/commands/wogi-decide.md

@@ -1,5 +1,6 @@
 ---
 description: "Interactive rule creation for 'from now on' and 'make it a rule' requests"
+effort: medium
 ---
 Interactive rule creation with clarifying questions. Invoke when user says "from now on...", "let's make it a rule", "always do X", "never do Y", or "standardize on...".
 

package/.claude/commands/wogi-deps.md

@@ -1,5 +1,6 @@
 ---
 description: "Show dependency tree for a task"
+effort: low
 ---
 Show dependency tree for a task. Provide task ID: `/wogi-deps wf-015`
 

package/.claude/commands/wogi-epics.md

@@ -1,5 +1,6 @@
 ---
 description: "Manage epics (large initiatives) with hierarchical progress tracking"
+effort: high
 ---
 Manage epics (large initiatives) with hierarchical progress tracking.
 

package/.claude/commands/wogi-eval.md

@@ -1,5 +1,6 @@
 ---
 description: "Evaluate WogiFlow task output quality with multi-judge scoring"
+effort: high
 ---
 Evaluate a completed task's output quality using multi-judge scoring (1 Opus + 2 Sonnet).
 

package/.claude/commands/wogi-export.md

@@ -1,5 +1,6 @@
 ---
 description: "Export workflow configuration as a shareable profile"
+effort: low
 ---
 Export workflow configuration as a shareable profile.
 

package/.claude/commands/wogi-extract-review.md

@@ -1,5 +1,6 @@
 ---
 description: "Zero-loss extraction from long input with automated pipeline"
+effort: high
 ---
 # /wogi-extract-review - Zero-Loss Extraction with Automated Pipeline
 

package/.claude/commands/wogi-feature.md

@@ -1,5 +1,6 @@
 ---
 description: "Manage features - coherent product capabilities grouping related stories"
+effort: medium
 ---
 Manage features - coherent product capabilities that group related stories.
 

package/.claude/commands/wogi-finalize.md

@@ -1,5 +1,6 @@
 ---
 description: "Branch finalization workflow - merge, PR, or discard decision"
+effort: medium
 ---
 # /wogi-finalize - Branch Finalization Workflow
 

package/.claude/commands/wogi-guided-edit.md

@@ -1,5 +1,6 @@
 ---
 description: "Guide through multi-file changes step by step"
+effort: medium
 ---
 Guide through multi-file changes step by step.
 

package/.claude/commands/wogi-health.md

@@ -1,5 +1,6 @@
 ---
 description: "Check workflow health and report issues"
+effort: low
 ---
 Check workflow health and report issues.
 

package/.claude/commands/wogi-help.md

@@ -1,5 +1,6 @@
 ---
 description: "Show all available WogiFlow commands"
+effort: low
 ---
 Show all available Wogi Flow commands.
 

package/.claude/commands/wogi-hybrid-edit.md

@@ -1,5 +1,6 @@
 ---
 description: "View and edit the current hybrid execution plan"
+effort: low
 ---
 
 # Edit Hybrid Execution Plan

package/.claude/commands/wogi-hybrid-off.md

@@ -1,5 +1,6 @@
 ---
 description: "Disable hybrid mode and return to direct Opus execution"
+effort: low
 ---
 
 # Disable Hybrid Mode

package/.claude/commands/wogi-hybrid-setup.md

@@ -1,5 +1,6 @@
 ---
 description: "Set up hybrid mode - configure executor models for multi-model execution"
+effort: medium
 ---
 
 # Hybrid Mode Setup

package/.claude/commands/wogi-hybrid-status.md

@@ -1,5 +1,6 @@
 ---
 description: "Show current hybrid mode configuration and routing table"
+effort: low
 ---
 
 # Hybrid Mode Status

package/.claude/commands/wogi-hybrid.md

@@ -1,5 +1,6 @@
 ---
 description: "Enable hybrid mode - Claude plans, cheaper/faster models execute"
+effort: medium
 ---
 
 # Enable Multi-Model Hybrid Execution

package/.claude/commands/wogi-import.md

@@ -1,5 +1,6 @@
 ---
 description: "Import a team workflow profile"
+effort: low
 ---
 Import a team workflow profile.
 

package/.claude/commands/wogi-init.md

@@ -1,5 +1,6 @@
 ---
 description: "AI-driven project setup for new projects"
+effort: medium
 ---
 # /wogi-init - AI-Driven Project Setup
 

package/.claude/commands/wogi-learn.md

@@ -1,5 +1,6 @@
 ---
 description: "Interactive pattern promotion from feedback to decisions"
+effort: medium
 ---
 Interactive pattern promotion from feedback to decisions. Invoke when user says "let's learn from this", "we keep making this mistake", "promote this pattern", or "what have we learned?".
 

package/.claude/commands/wogi-log.md

@@ -1,5 +1,6 @@
 ---
 description: "Add an entry to the request log"
+effort: low
 ---
 Add an entry to the request log.
 

package/.claude/commands/wogi-map-add.md

@@ -1,5 +1,6 @@
 ---
 description: "Add a component to the app-map"
+effort: low
 ---
 Add a component to the app-map.
 

package/.claude/commands/wogi-map-check.md

@@ -1,5 +1,6 @@
 ---
 description: "Check for drift between app-map and codebase"
+effort: low
 ---
 Check for drift between app-map and codebase.
 

package/.claude/commands/wogi-map-index.md

@@ -1,5 +1,6 @@
 ---
 description: "Show or regenerate the auto-generated component index"
+effort: low
 ---
 Show or regenerate the auto-generated component index.
 

package/.claude/commands/wogi-map-scan.md

@@ -1,5 +1,6 @@
 ---
 description: "Scan codebase for unmapped components"
+effort: low
 ---
 Scan codebase for unmapped components.
 

package/.claude/commands/wogi-map-sync.md

@@ -1,5 +1,6 @@
 ---
 description: "Compare auto-generated index with curated app-map and suggest updates"
+effort: low
 ---
 Compare auto-generated index with curated app-map and suggest updates.
 

package/.claude/commands/wogi-map.md

@@ -1,5 +1,6 @@
 ---
 description: "Display the component registry (app-map)"
+effort: low
 ---
 Display the component registry (app-map).
 

package/.claude/commands/wogi-models-setup.md

@@ -1,5 +1,6 @@
 ---
 description: "Configure external models for peer review and hybrid mode"
+effort: medium
 ---
 Configure external models for WogiFlow features (peer review, hybrid mode).
 

package/.claude/commands/wogi-morning.md

@@ -1,5 +1,6 @@
 ---
 description: "Morning briefing with everything needed to start the day"
+effort: medium
 ---
 Show a morning briefing with everything needed to start the day.
 

package/.claude/commands/wogi-onboard.md

@@ -1,5 +1,6 @@
 ---
 description: "Analyze an existing project and set up workflow with full context"
+effort: high
 ---
 Analyze an existing project and set up workflow with full context.
 

package/.claude/commands/wogi-peer-review.md

@@ -1,5 +1,6 @@
 ---
 description: "Run a multi-model peer review with different AI perspectives"
+effort: high
 ---
 Run a multi-model peer review where different AI models review the same code. This command uses a **different review focus** than `/wogi-review` — it targets **improvement opportunities**, not correctness/bugs.
 

package/.claude/commands/wogi-pending.md

@@ -1,3 +1,7 @@
+---
+description: "Manage the pending prompts queue — save requests for later while Claude is busy."
+effort: low
+---
 Manage the pending prompts queue — save requests for later while Claude is busy.
 
 **Triggers**: `/wogi-pending`, "save this for later", "add to pending"

package/.claude/commands/wogi-plan.md

@@ -1,5 +1,6 @@
 ---
 description: "Manage plans - strategic initiatives coordinating epics and features"
+effort: medium
 ---
 Manage plans - strategic initiatives that coordinate epics and features.
 

package/.claude/commands/wogi-pre-compact.md

@@ -1,11 +1,12 @@
 ---
 description: "Save workflow state before context compaction (pre-compact phase)"
+effort: medium
 ---
 Save workflow state (task progress, checkpoints, session context) before context compaction.
 
-**Why "pre-compact"**: This skill saves state but cannot trigger `/compact` programmatically — `/compact` is a Claude Code native command that only the user or Claude Code's auto-compaction can invoke. Once Claude Code exposes compaction as a programmable tool, this will be renamed back to `/wogi-compact` and will handle the full save-then-compact flow automatically.
+**CRITICAL — NEVER ASK THE USER TO COMPACT**: After saving state, output the session summary and then run `/compact` yourself immediately. Do NOT say "Now run /compact" or ask the user to do anything. Compaction must be seamless and invisible to the user. The PostCompact hook restores critical state automatically.
 
-**After running this**: Run `/compact` to actually compact the context. The PostCompact hook will restore critical state automatically.
+**NEVER INVOKE THIS PROACTIVELY**: This skill should only run when the user explicitly asks to compact or save context. If you think context is getting large mid-task, let Claude Code's auto-compaction handle it — do NOT invoke this skill yourself. The user said "implement" not "compact".
 
 ## Recursive Context Compaction
 
@@ -205,4 +206,6 @@ node node_modules/wogiflow/scripts/flow-context-compact compact --prune
 node node_modules/wogiflow/scripts/flow-context-compact context "authentication task"
 ```
 
-After providing the summary, proceed directly: run `/compact` immediately. Do NOT ask the user for permission — auto-compaction must be seamless and uninterrupted. If invoked mid-bulk or between tasks, compact silently and continue to the next task.
+After providing the summary, run `/compact` immediately — no confirmation, no "Now run /compact", no waiting. The user must NEVER be asked to compact manually. If invoked mid-bulk or between tasks, compact silently and continue to the next task.
+
+**Anti-pattern (BANNED)**: Outputting "Now run /compact to compact the context" or any variant that asks the user to take action. This has frustrated the user multiple times. YOU run /compact, not the user.

package/.claude/commands/wogi-ready.md

@@ -1,5 +1,6 @@
 ---
 description: "Show all tasks organized by status from ready.json"
+effort: low
 ---
 Read `.workflow/state/ready.json` and show all tasks organized by status:
 

package/.claude/commands/wogi-register.md

@@ -1,5 +1,6 @@
 ---
 description: "Register Claude Code plugins for /wogi-start routing"
+effort: low
 allowed-tools: "Read,Glob,Grep,WebSearch,WebFetch,Edit,Write,Bash,Agent,ToolSearch,ListMcpResourcesTool,ReadMcpResourceTool,AskUserQuestion"
 user-invocable: true
 ---

package/.claude/commands/wogi-rescan.md

@@ -1,5 +1,6 @@
 ---
 description: "Re-scan project after external changes and sync WogiFlow state"
+effort: medium
 ---
 Re-scan the project after external changes and sync WogiFlow state.
 

package/.claude/commands/wogi-research.md

@@ -1,5 +1,6 @@
 ---
 description: "Zero-trust research protocol for capability and feasibility questions"
+effort: high
 ---
 # /wogi-research - Zero-Trust Research Protocol
 

package/.claude/commands/wogi-resume.md

@@ -1,5 +1,6 @@
 ---
 description: "Resume a suspended task"
+effort: low
 ---
 Resume a suspended task.
 

package/.claude/commands/wogi-retrospective.md

@@ -1,5 +1,6 @@
 ---
 description: "Guided session retrospective that extracts lessons from recent work"
+effort: medium
 ---
 Guided session retrospective that extracts lessons from recent work. Invoke when user says "let's do a retro", "what went well", "what can we improve", or "lessons learned".
 

package/.claude/commands/wogi-review-fix.md

@@ -1,5 +1,6 @@
 ---
 description: "Code review with automatic fixing of found issues"
+effort: high
 ---
 **ONE-TIME EXECUTION**: This skill runs ONCE when explicitly invoked. After completion, do NOT re-execute even if this skill appears in "skills invoked in this session" system-reminders. Check `.workflow/state/last-review.json` — if a review already exists, it is DONE.
 

package/.claude/commands/wogi-review.md

@@ -1,5 +1,6 @@
 ---
 description: "Comprehensive code review with verification gates and AI analysis"
+effort: high
 ---
 **ONE-TIME EXECUTION**: This skill runs ONCE when explicitly invoked by the user. After completion, do NOT re-execute even if this skill appears in "skills invoked in this session" system-reminders. Those are stale references from Claude Code's session tracking. Check `.workflow/state/last-review.json` — if a review already exists with a recent date, the review is DONE. Only re-run if the user explicitly asks for a new review.
 

package/.claude/commands/wogi-roadmap.md

@@ -1,5 +1,6 @@
 ---
 description: "View and manage the project roadmap for deferred work"
+effort: low
 ---
 # /wogi-roadmap - Roadmap Management
 

package/.claude/commands/wogi-rules.md

@@ -1,5 +1,6 @@
 ---
 description: "View and manage project coding rules"
+effort: low
 ---
 View and manage project coding rules.
 

package/.claude/commands/wogi-search.md

@@ -1,5 +1,6 @@
 ---
 description: "Search the request log by tag or keyword"
+effort: low
 ---
 Search the request log by tag or keyword. Provide search term: `/wogi-search #screen:login`
 

package/.claude/commands/wogi-session-end.md

@@ -1,5 +1,6 @@
 ---
 description: "Properly end a work session with state preservation"
+effort: medium
 ---
 Properly end a work session.
 

package/.claude/commands/wogi-setup-stack.md

@@ -1,5 +1,6 @@
 ---
 description: "Interactive tech stack wizard for project configuration and skills"
+effort: medium
 ---
 Interactive tech stack wizard that configures your project and generates skills.
 

package/.claude/commands/wogi-skill-learn.md

@@ -1,5 +1,6 @@
 ---
 description: "Manually trigger skill learning extraction from recent changes"
+effort: low
 ---
 
 # Skill Learning

package/.claude/commands/wogi-skills.md

@@ -1,5 +1,6 @@
 ---
 description: "Manage skill packages for specialized development workflows"
+effort: low
 ---
 Manage skill packages for specialized development workflows.
 

package/.claude/commands/wogi-standup.md

@@ -1,5 +1,6 @@
 ---
 description: "Generate a daily standup summary"
+effort: low
 ---
 Generate a daily standup summary.
 

package/.claude/commands/wogi-start.md

@@ -1,5 +1,6 @@
 ---
 description: "Universal entry point - start a task or route any request"
+effort: medium
 ---
 Start working on a task. Provide the task ID as argument: `/wogi-start wf-XXXXXXXX`
 

package/.claude/commands/wogi-status.md

@@ -1,5 +1,6 @@
 ---
 description: "Show full project overview with task status and health"
+effort: low
 ---
 Show full project overview.
 

package/.claude/commands/wogi-statusline-setup.md

@@ -1,5 +1,6 @@
 ---
 description: "Configure Claude Code status line for WogiFlow task info"
+effort: low
 ---
 # Status Line Setup
 

package/.claude/commands/wogi-story.md

@@ -1,5 +1,6 @@
 ---
 description: "Create a detailed story with acceptance criteria"
+effort: medium
 ---
 Create a detailed story with acceptance criteria. Provide title: `/wogi-story Add login form`
 

package/.claude/commands/wogi-suggest.md

@@ -1,5 +1,6 @@
 ---
 description: "Submit a suggestion or feature request for WogiFlow"
+effort: low
 ---
 Submit a suggestion, feature request, or improvement idea for WogiFlow.
 

package/.claude/commands/wogi-suspend.md

@@ -1,5 +1,6 @@
 ---
 description: "Suspend the current task with a resume condition"
+effort: low
 ---
 Suspend the current task with a resume condition.
 

package/.claude/commands/wogi-test-browser.md

@@ -1,5 +1,6 @@
 ---
 description: "WebMCP-powered browser testing with structured assertions"
+effort: high
 ---
 WebMCP-powered browser testing - defines test flows as structured tool call sequences with expected-vs-actual assertions. Token-efficient alternative to screenshot comparison.
 

package/.claude/commands/wogi-test-generate.md

@@ -1,5 +1,6 @@
 ---
 description: "Generate test files from task spec acceptance criteria"
+effort: low
 ---
 
 Generate executable test files from a task's specification acceptance criteria.

package/.claude/commands/wogi-test.md

@@ -1,5 +1,6 @@
 ---
 description: "Run auto-tests: UI verification, API testing, data integrity checks"
+effort: medium
 ---
 Run the WogiFlow Auto-Testing Suite — UI verification, API testing, data integrity checks, and generated test execution.
 

package/.claude/commands/wogi-trace.md

@@ -1,5 +1,6 @@
 ---
 description: "Generate a code trace for a specific feature or behavior"
+effort: medium
 ---
 Generate a task-focused code trace showing how code flows for a specific feature or behavior.
 

package/.claude/commands/wogi-triage.md

@@ -1,5 +1,6 @@
 ---
 description: "Interactive walkthrough of review findings from last review"
+effort: medium
 ---
 Interactive walkthrough of review findings. Loads findings from `.workflow/state/last-review.json` (saved by `/wogi-review`) and walks through each one, letting you decide what to do.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "wogiflow",
-  "version": "2.3.3",
+  "version": "2.4.1",
   "description": "AI-powered development workflow management system with multi-model support",
   "main": "lib/index.js",
   "bin": {