oh-my-claude-sisyphus 3.8.15 → 3.9.0

package/skills/cancel/SKILL.md

@@ -7,6 +7,12 @@ description: Cancel any active OMC mode (autopilot, ralph, ultrawork, ecomode, u
 
 Intelligent cancellation that detects and cancels the active OMC mode.
 
+**The cancel skill is the standard way to complete and exit any OMC mode.**
+When the stop hook detects work is complete, it instructs the LLM to invoke
+this skill for proper state cleanup. If cancel fails or is interrupted,
+retry with `--force` flag, or wait for the 2-hour staleness timeout as
+a last resort.
+
 ## What It Does
 
 Automatically detects which mode is active and cancels it:
@@ -80,9 +86,6 @@ This removes all state files:
 - `.omc/state/pipeline-state.json`
 - `.omc/state/plan-consensus.json`
 - `.omc/state/ralplan-state.json`
-- `~/.claude/ralph-state.json`
-- `~/.claude/ultrawork-state.json`
-- `~/.claude/ecomode-state.json`
 
 ## Implementation Steps
 
@@ -161,11 +164,6 @@ if [[ "$FORCE_MODE" == "true" ]]; then
   rm -f .omc/state/plan-consensus.json
   rm -f .omc/state/ralplan-state.json
 
-  # Remove global state files
-  rm -f ~/.claude/ralph-state.json
-  rm -f ~/.claude/ultrawork-state.json
-  rm -f ~/.claude/ecomode-state.json
-
   echo "All OMC modes cleared. You are free to start fresh."
   exit 0
 fi
@@ -189,13 +187,11 @@ if [[ -f .omc/state/autopilot-state.json ]]; then
     # Clean linked ultrawork first
     if [[ "$LINKED_UW" == "true" ]] && [[ -f .omc/state/ultrawork-state.json ]]; then
       rm -f .omc/state/ultrawork-state.json
-      rm -f ~/.claude/ultrawork-state.json
       echo "Cleaned up: ultrawork (linked to ralph)"
     fi
 
     # Clean ralph
     rm -f .omc/state/ralph-state.json
-    rm -f ~/.claude/ralph-state.json
     rm -f .omc/state/ralph-verification.json
     echo "Cleaned up: ralph"
   fi
@@ -234,14 +230,12 @@ if [[ -f .omc/state/ralph-state.json ]]; then
     # Only clear if it was linked to ralph
     if [[ "$UW_LINKED" == "true" ]]; then
       rm -f .omc/state/ultrawork-state.json
-      rm -f ~/.claude/ultrawork-state.json
       echo "Cleaned up: ultrawork (linked to ralph)"
     fi
   fi
 
-  # Clean ralph state (both local and global)
+  # Clean ralph state
   rm -f .omc/state/ralph-state.json
-  rm -f ~/.claude/ralph-state.json
   rm -f .omc/state/ralph-plan-state.json
   rm -f .omc/state/ralph-verification.json
 
@@ -264,9 +258,8 @@ if [[ -f .omc/state/ultrawork-state.json ]]; then
     exit 1
   fi
 
-  # Remove both local and global state
+  # Remove local state
   rm -f .omc/state/ultrawork-state.json
-  rm -f ~/.claude/ultrawork-state.json
 
   echo "Ultrawork cancelled. Parallel execution mode deactivated."
 fi
@@ -314,7 +307,7 @@ fi
 if [[ "$FORCE_MODE" == "true" ]]; then
   echo "FORCE CLEAR: Removing all OMC state files..."
 
-  mkdir -p .omc ~/.claude
+  mkdir -p .omc/state
 
   # Remove local state files
   rm -f .omc/state/autopilot-state.json
@@ -333,11 +326,6 @@ if [[ "$FORCE_MODE" == "true" ]]; then
   rm -f .omc/state/plan-consensus.json
   rm -f .omc/state/ralplan-state.json
 
-  # Remove global state files
-  rm -f ~/.claude/ralph-state.json
-  rm -f ~/.claude/ultrawork-state.json
-  rm -f ~/.claude/ecomode-state.json
-
   echo ""
   echo "All OMC modes cleared. You are free to start fresh."
   exit 0
@@ -366,13 +354,11 @@ if [[ -f .omc/state/autopilot-state.json ]]; then
         # Clean linked ultrawork first
         if [[ "$LINKED_UW" == "true" ]] && [[ -f .omc/state/ultrawork-state.json ]]; then
           rm -f .omc/state/ultrawork-state.json
-          rm -f ~/.claude/ultrawork-state.json
           CLEANED_UP+=("ultrawork")
         fi
 
         # Clean ralph
         rm -f .omc/state/ralph-state.json
-        rm -f ~/.claude/ralph-state.json
         rm -f .omc/state/ralph-verification.json
         CLEANED_UP+=("ralph")
       fi
@@ -420,7 +406,6 @@ if [[ -f .omc/state/ralph-state.json ]]; then
       # Only clear if it was linked to ralph
       if [[ "$UW_LINKED" == "true" ]]; then
         rm -f .omc/state/ultrawork-state.json
-        rm -f ~/.claude/ultrawork-state.json
         echo "Cleaned up: ultrawork (linked to ralph)"
       fi
     fi
@@ -434,14 +419,12 @@ if [[ -f .omc/state/ralph-state.json ]]; then
 
       if [[ "$ECO_LINKED" == "true" ]]; then
         rm -f .omc/state/ecomode-state.json
-        rm -f ~/.claude/ecomode-state.json
         echo "Cleaned up: ecomode (linked to ralph)"
       fi
     fi
 
-    # Clean ralph state (both local and global)
+    # Clean ralph state
     rm -f .omc/state/ralph-state.json
-    rm -f ~/.claude/ralph-state.json
     rm -f .omc/state/ralph-plan-state.json
     rm -f .omc/state/ralph-verification.json
 
@@ -464,9 +447,8 @@ if [[ -f .omc/state/ultrawork-state.json ]]; then
       echo "Clearing ultrawork state anyway..."
     fi
 
-    # Remove both local and global state
+    # Remove local state
     rm -f .omc/state/ultrawork-state.json
-    rm -f ~/.claude/ultrawork-state.json
 
     echo "Ultrawork cancelled. Parallel execution mode deactivated."
     CANCELLED_ANYTHING=true
@@ -487,9 +469,8 @@ if [[ -f .omc/state/ecomode-state.json ]]; then
       echo "Clearing ecomode state anyway..."
     fi
 
-    # Remove both local and global state
+    # Remove local state
     rm -f .omc/state/ecomode-state.json
-    rm -f ~/.claude/ecomode-state.json
 
     echo "Ecomode cancelled. Token-efficient execution mode deactivated."
     CANCELLED_ANYTHING=true
@@ -636,5 +617,5 @@ fi
 - **Dependency-aware**: Autopilot cancellation cleans up Ralph and UltraQA
 - **Link-aware**: Ralph cancellation cleans up linked Ultrawork or Ecomode
 - **Safe**: Only clears linked Ultrawork, preserves standalone Ultrawork
-- **Dual-location**: Clears both `.omc/` and `~/.claude/` state files
+- **Local-only**: Clears state files in `.omc/state/` directory
 - **Resume-friendly**: Autopilot state is preserved for seamless resume

package/skills/deep-executor/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: deep-executor
+description: Deep executor mode for complex goal-oriented tasks
+---
+
+# Deep Executor Skill
+
+Activate autonomous deep work mode for complex tasks.
+
+## Overview
+
+Deep Executor is the autonomous deep worker agent. When activated, it:
+
+1. **Explores First**: Uses its own tools (Glob, Grep, Read, ast_grep_search) to thoroughly understand the problem
+2. **Plans Strategically**: Creates execution plan based on exploration
+3. **Executes Directly**: Does all work itself using Edit, Write, Bash, ast_grep_replace
+4. **Verifies Everything**: Runs builds, tests, and diagnostics before claiming completion
+5. **Completes 100%**: Guarantees full completion with evidence
+
+## Usage
+
+```
+/oh-my-claudecode:deep-executor <your complex task>
+```
+
+Or use magic keywords:
+- "deep-executor: ..."
+- "deep work: ..."
+- "forge: ..."
+
+## When to Use
+
+| Situation | Use Deep Executor? |
+|-----------|-----------------|
+| Complex multi-file refactoring | YES |
+| Unclear implementation path | YES |
+| Need guaranteed completion | YES |
+| Simple single-file fix | NO (use executor) |
+| Quick code search | NO (use explore) |
+| Cost-sensitive work | NO (use ecomode) |
+
+## Activation
+
+This skill spawns the `deep-executor` agent via:
+
+```
+Task(subagent_type="oh-my-claudecode:deep-executor", model="opus", prompt="{{PROMPT}}")
+```
+
+The agent handles all exploration and execution internally. No sub-agents are spawned.

package/skills/ecomode/SKILL.md

@@ -1,142 +1,96 @@
 ---
 name: ecomode
-description: Token-efficient parallel execution mode using Haiku and Sonnet agents
+description: Token-efficient model routing modifier
 ---
 
 # Ecomode Skill
 
-Activates token-efficient parallel execution for pro-plan users who prioritize cost efficiency.
+Token-efficient model routing. This is a **MODIFIER**, not a standalone execution mode.
 
-## When Activated
+## What Ecomode Does
 
-This skill enhances Claude's capabilities by:
+Overrides default model selection to prefer cheaper tiers:
 
-1. **Parallel Execution**: Running multiple agents simultaneously for independent tasks
-2. **Token-Conscious Routing**: Preferring Haiku and Sonnet agents, avoiding Opus
-3. **Background Operations**: Using `run_in_background: true` for long operations
-4. **Persistence Enforcement**: Never stopping until all tasks are verified complete
-5. **Cost Optimization**: Minimizing token usage while maintaining quality
+| Default Tier | Ecomode Override |
+|--------------|------------------|
+| HIGH (opus) | MEDIUM (sonnet), HIGH only if essential |
+| MEDIUM (sonnet) | LOW (haiku) first, MEDIUM if fails |
+| LOW (haiku) | LOW (haiku) - no change |
 
-## Ecomode Routing Rules (CRITICAL)
+## What Ecomode Does NOT Do
 
-**ALWAYS prefer lower tiers. Only escalate when task genuinely requires it.**
-
-| Decision | Rule |
-|----------|------|
-| DEFAULT | Use LOW tier (Haiku) for all tasks |
-| UPGRADE | Use MEDIUM (Sonnet) only when task complexity warrants |
-| AVOID | HIGH tier (Opus) - only use for planning/critique if explicitly essential |
+- **Persistence**: Use `ralph` for "don't stop until done"
+- **Parallel Execution**: Use `ultrawork` for parallel agents
+- **Delegation Enforcement**: Always active via core orchestration
 
-## Smart Model Routing (PREFER LOW TIER)
+## Combining Ecomode with Other Modes
 
-**Choose tier based on task complexity: LOW (haiku) preferred → MEDIUM (sonnet) fallback → HIGH (opus) AVOID**
+Ecomode is a modifier that combines with execution modes:
 
-### Agent Routing Table
+| Combination | Effect |
+|-------------|--------|
+| `eco ralph` | Ralph loop with cheaper agents |
+| `eco ultrawork` | Parallel execution with cheaper agents |
+| `eco autopilot` | Full autonomous with cost optimization |
 
-| Domain | PREFERRED (Haiku) | FALLBACK (Sonnet) | AVOID (Opus) |
-|--------|-------------------|-------------------|--------------|
-| **Analysis** | `architect-low` | `architect-medium` | ~~`architect`~~ |
-| **Execution** | `executor-low` | `executor` | ~~`executor-high`~~ |
-| **Search** | `explore` | `explore-medium` | ~~`explore-high`~~ |
-| **Research** | `researcher-low` | `researcher` | - |
-| **Frontend** | `designer-low` | `designer` | ~~`designer-high`~~ |
-| **Docs** | `writer` | - | - |
-| **Visual** | - | `vision` | - |
-| **Planning** | - | - | `planner` (if essential) |
-| **Critique** | - | - | `critic` (if essential) |
-| **Testing** | - | `qa-tester` | ~~`qa-tester-high`~~ |
-| **Security** | `security-reviewer-low` | - | ~~`security-reviewer`~~ |
-| **Build** | `build-fixer-low` | `build-fixer` | - |
-| **TDD** | `tdd-guide-low` | `tdd-guide` | - |
-| **Code Review** | `code-reviewer-low` | - | ~~`code-reviewer`~~ |
-| **Data Science** | `scientist-low` | `scientist` | ~~`scientist-high`~~ |
+## Ecomode Routing Rules
 
-### Tier Selection Guide (Token-Conscious)
-
-| Task Complexity | Tier | Examples |
-|-----------------|------|----------|
-| Simple lookups | LOW | "What does this function return?", "Find where X is defined" |
-| Standard work | LOW first, MEDIUM if fails | "Add error handling", "Implement this feature" |
-| Complex analysis | MEDIUM | "Debug this issue", "Refactor this module" |
-| Planning only | HIGH (if essential) | "Design architecture for new system" |
+**ALWAYS prefer lower tiers. Only escalate when task genuinely requires it.**
 
-### Routing Examples
+| Decision | Rule |
+|----------|------|
+| DEFAULT | Use LOW tier (Haiku) for all tasks |
+| UPGRADE | Use MEDIUM (Sonnet) only when task complexity warrants |
+| AVOID | HIGH tier (Opus) - only for planning/critique if essential |
 
-**CRITICAL: Always pass `model` parameter explicitly - Claude Code does NOT auto-apply models from agent definitions!**
+## Agent Selection in Ecomode
 
+**FIRST ACTION:** Before delegating any work, read the agent reference file:
 ```
-// Simple question → LOW tier (DEFAULT)
-Task(subagent_type="oh-my-claudecode:architect-low", model="haiku", prompt="What does this function return?")
-
-// Standard implementation → TRY LOW first
-Task(subagent_type="oh-my-claudecode:executor-low", model="haiku", prompt="Add validation to login form")
-
-// If LOW fails, escalate to MEDIUM
-Task(subagent_type="oh-my-claudecode:executor", model="sonnet", prompt="Add error handling to login")
-
-// File lookup → ALWAYS LOW
-Task(subagent_type="oh-my-claudecode:explore", model="haiku", prompt="Find where UserService is defined")
-
-// Only use MEDIUM for complex patterns
-Task(subagent_type="oh-my-claudecode:explore-medium", model="sonnet", prompt="Find all authentication patterns in the codebase")
+Read file: docs/shared/agent-tiers.md
 ```
+This provides the complete agent tier matrix, MCP tool assignments, and selection guidance.
 
-## DELEGATION ENFORCEMENT (CRITICAL)
-
-**YOU ARE AN ORCHESTRATOR, NOT AN IMPLEMENTER.**
-
-| Action | YOU Do | DELEGATE |
-|--------|--------|----------|
-| Read files for context | ✓ | |
-| Track progress (TODO) | ✓ | |
-| Spawn parallel agents | ✓ | |
-| **ANY code change** | ✗ NEVER | executor-low/executor |
-| **UI work** | ✗ NEVER | designer-low/designer |
-| **Docs** | ✗ NEVER | writer |
+**Ecomode preference order:**
 
-**Path Exception**: Only write to `.omc/`, `.claude/`, `CLAUDE.md`, `AGENTS.md`
+```
+// PREFERRED - Use for most tasks
+Task(subagent_type="oh-my-claudecode:executor-low", model="haiku", prompt="...")
+Task(subagent_type="oh-my-claudecode:explore", model="haiku", prompt="...")
+Task(subagent_type="oh-my-claudecode:architect-low", model="haiku", prompt="...")
 
-## Background Execution Rules
+// FALLBACK - Only if LOW fails
+Task(subagent_type="oh-my-claudecode:executor", model="sonnet", prompt="...")
+Task(subagent_type="oh-my-claudecode:architect-medium", model="sonnet", prompt="...")
 
-**Run in Background** (set `run_in_background: true`):
-- Package installation: npm install, pip install, cargo build
-- Build processes: npm run build, make, tsc
-- Test suites: npm test, pytest, cargo test
-- Docker operations: docker build, docker pull
+// AVOID - Only for planning/critique if essential
+Task(subagent_type="oh-my-claudecode:planner", model="opus", prompt="...")
+```
 
-**Run Blocking** (foreground):
-- Quick status checks: git status, ls, pwd
-- File reads (NOT edits - delegate edits to executor-low)
-- Simple commands
+## Delegation Enforcement
 
-## Verification Checklist
+Ecomode maintains all delegation rules from core protocol with cost-optimized routing:
 
-Before stopping, verify:
-- [ ] TODO LIST: Zero pending/in_progress tasks
-- [ ] FUNCTIONALITY: All requested features work
-- [ ] TESTS: All tests pass (if applicable)
-- [ ] ERRORS: Zero unaddressed errors
+| Action | Delegate To | Model |
+|--------|-------------|-------|
+| Code changes | executor-low / executor | haiku / sonnet |
+| Analysis | architect-low | haiku |
+| Search | explore | haiku |
+| Documentation | writer | haiku |
 
-**If ANY checkbox is unchecked, CONTINUE WORKING.**
+### Background Execution
+Long-running commands (install, build, test) run in background. Maximum 5 concurrent.
 
 ## Token Savings Tips
 
 1. **Batch similar tasks** to one agent instead of spawning many
 2. **Use explore (haiku)** for file discovery, not architect
 3. **Prefer executor-low** for simple changes - only upgrade if it fails
-4. **Avoid opus agents** unless the task genuinely requires deep reasoning
-5. **Use writer (haiku)** for all documentation tasks
-
-## STATE CLEANUP ON COMPLETION
+4. **Use writer (haiku)** for all documentation tasks
+5. **Avoid opus agents** unless the task genuinely requires deep reasoning
 
-**IMPORTANT: Delete state files on completion - do NOT just set `active: false`**
+## State Management
 
-When ecomode completes (all verification passes):
-
-```bash
-# Delete ecomode state files
-rm -f .omc/state/ecomode-state.json
-rm -f ~/.claude/ecomode-state.json
-```
+Ecomode state is tracked in `.omc/state/ecomode-state.json`.
 
-This ensures clean state for future sessions. Stale state files with `active: false` should not be left behind.
+When work is complete, run `/oh-my-claudecode:cancel` for clean state cleanup.

package/skills/hud/SKILL.md

@@ -246,7 +246,7 @@ HUD config is stored at: `~/.claude/.omc/hud-config.json`
 
 ## Manual Configuration
 
-You can manually edit the config file:
+You can manually edit the config file. Each option can be set individually - any unset values will use defaults.
 
 ```json
 {
@@ -262,7 +262,8 @@ You can manually edit the config file:
     "backgroundTasks": true,
     "todos": true,
     "showCache": true,
-    "showCost": true
+    "showCost": true,
+    "maxOutputLines": 4
   },
   "thresholds": {
     "contextWarning": 70,