claudecode-omc 5.4.0 → 5.5.1

package/.local/guidelines/CLAUDE.md

@@ -0,0 +1,31 @@
+# Coding Discipline
+
+These are always-on guardrails for non-trivial coding work.
+
+## Think Before Coding
+
+- State assumptions that materially affect design, scope, or behavior.
+- Surface ambiguity instead of silently choosing an interpretation.
+- Ask for clarification when missing detail can change the implementation.
+- Prefer the simpler path when it still satisfies the real goal.
+
+## Simplicity First
+
+- Make the smallest correct change that solves the task.
+- Do not add speculative features, configuration, or extension points.
+- Avoid new abstractions for one-off logic.
+- If the solution expands quickly, step back and simplify it.
+
+## Surgical Changes
+
+- Change only the files and lines required for the task.
+- Match existing patterns unless the task explicitly requires a new one.
+- Do not refactor adjacent code, comments, or formatting as a drive-by edit.
+- Clean up only unused code introduced by your own change unless asked.
+
+## Goal-Driven Execution
+
+- Turn vague requests into concrete success criteria.
+- Verify behavior with tests or explicit checks whenever practical.
+- Tie multi-step work to validation at each step.
+- Do not claim completion without fresh evidence from the workspace.

package/README.md

@@ -19,9 +19,16 @@ omc-manage setup
 | Agents | ~19 | oh-my-claudecode + superpowers |
 | Hooks | ~8 | oh-my-claudecode (standalone) |
 | Commands | ~3 | superpowers |
+| Guidelines | 1 | local coding discipline prompt guidelines |
 
 All artifacts are installed to `~/.claude/` where Claude Code discovers them automatically.
 
+The bundled guidelines install into `~/.claude/CLAUDE.md` and add lightweight
+coding discipline rules
+adapted from [andrej-karpathy-skills](https://github.com/forrestchang/andrej-karpathy-skills):
+think before coding, prefer simple solutions, make surgical changes, and verify
+completion with concrete evidence.
+
 ## Commands
 
 | Command | Description |
@@ -30,9 +37,11 @@ All artifacts are installed to `~/.claude/` where Claude Code discovers them aut
 | `omc-manage doctor` | Health checks |
 | `omc-manage source list` | Show configured sources |
 | `omc-manage source sync` | Update upstream sources to latest |
-| `omc-manage source add <name> <url>` | Add a new source |
+| `omc-manage source add <name> <url>` | Add a new source, including `guidelines` sources |
 | `omc-manage artifact list [--type <type>]` | List merged artifacts |
 | `omc-manage artifact conflicts [--type <type>]` | Show conflict report |
+| `omc-manage guidelines optimize [source...]` | Build maintainer-only guideline optimization artifacts |
+| `omc-manage guidelines apply --result-file <path>` | Apply a maintainer-generated optimization result |
 
 ## Sources & Priority
 
@@ -50,6 +59,53 @@ mkdir -p ~/.omc-manage/local/skills/my-skill
 omc-manage setup --force
 ```
 
+Add a remote guidelines source:
+
+```bash
+omc-manage source add karpathy https://github.com/forrestchang/andrej-karpathy-skills.git \
+  --artifacts guidelines \
+  --mapping guidelines=CLAUDE.md \
+  --role guidelines
+omc-manage source sync karpathy
+omc-manage setup --type guidelines
+```
+
+## Maintainer Guideline Optimization
+
+OMC now treats runtime prompt guidance as a first-class `guidelines` artifact,
+but the semantic optimization workflow is maintainer-only. The optimizer does
+not get installed into user Claude Code configs.
+
+Build an optimization pack for model-assisted synthesis:
+
+```bash
+omc-manage guidelines optimize
+```
+
+This writes maintainer artifacts under `.omc/guidelines/`, including:
+
+- `latest/next-steps.md`
+- `latest/optimizer-input.md`
+- `latest/sections.json`
+- `latest/sources.json`
+- `latest/current-local-guidelines.md`
+
+If you are driving the repo with Claude Code CLI or Codex, read
+`latest/next-steps.md` first. That file points the agent at the relevant
+maintainer workflow and the runtime file to edit.
+
+The repository-only maintainer prompt lives at
+`.maintainer/skills/guideline-optimizer/SKILL.md`. It is intentionally not
+installed into user runtime configs.
+
+After the optimization pass updates `.local/guidelines/CLAUDE.md`, reinstall
+with:
+
+```bash
+omc-manage guidelines apply --result-file /absolute/path/to/result.json
+omc-manage setup --type guidelines
+```
+
 ## Update Upstream
 
 ```bash

package/bundled/manifest.json

@@ -1,8 +1,8 @@
 {
-  "bundledAt": "2026-04-01T09:46:53Z",
+  "bundledAt": "2026-04-23T09:40:23Z",
   "sources": {
     "anthropic-skills": { "artifacts": 2 },
-    "oh-my-claudecode": { "artifacts": 20 },
+    "oh-my-claudecode": { "artifacts": 21 },
     "superpowers": { "artifacts": 8 }
   }
 }

package/bundled/upstream/oh-my-claudecode/agents/analyst.md

@@ -1,7 +1,7 @@
 ---
 name: analyst
 description: Pre-planning consultant for requirements analysis (Opus)
-model: claude-opus-4-6
+model: opus
 level: 3
 disallowedTools: Write, Edit
 ---

package/bundled/upstream/oh-my-claudecode/agents/architect.md

@@ -1,7 +1,7 @@
 ---
 name: architect
 description: Strategic Architecture & Debugging Advisor (Opus, READ-ONLY)
-model: claude-opus-4-6
+model: opus
 level: 3
 disallowedTools: Write, Edit
 ---

package/bundled/upstream/oh-my-claudecode/agents/code-reviewer.md

@@ -1,7 +1,7 @@
 ---
 name: code-reviewer
 description: Expert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategy
-model: claude-opus-4-6
+model: opus
 level: 3
 disallowedTools: Write, Edit
 ---

package/bundled/upstream/oh-my-claudecode/agents/code-simplifier.md

@@ -1,7 +1,7 @@
 ---
 name: code-simplifier
 description: Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
-model: claude-opus-4-6
+model: opus
 level: 3
 ---
 

package/bundled/upstream/oh-my-claudecode/agents/critic.md

@@ -1,7 +1,7 @@
 ---
 name: critic
 description: Work plan and code review expert — thorough, structured, multi-perspective (Opus)
-model: claude-opus-4-6
+model: opus
 level: 3
 disallowedTools: Write, Edit
 ---

package/bundled/upstream/oh-my-claudecode/agents/debugger.md

@@ -1,7 +1,7 @@
 ---
 name: debugger
 description: Root-cause analysis, regression isolation, stack trace analysis, build/compilation error resolution
-model: claude-sonnet-4-6
+model: sonnet
 level: 3
 ---
 

package/bundled/upstream/oh-my-claudecode/agents/designer.md

@@ -1,7 +1,7 @@
 ---
 name: designer
 description: UI/UX Designer-Developer for stunning interfaces (Sonnet)
-model: claude-sonnet-4-6
+model: sonnet
 level: 2
 ---
 

package/bundled/upstream/oh-my-claudecode/agents/document-specialist.md

@@ -1,7 +1,7 @@
 ---
 name: document-specialist
 description: External Documentation & Reference Specialist
-model: claude-sonnet-4-6
+model: sonnet
 level: 2
 disallowedTools: Write, Edit
 ---

package/bundled/upstream/oh-my-claudecode/agents/executor.md

@@ -1,7 +1,7 @@
 ---
 name: executor
 description: Focused task executor for implementation work (Sonnet)
-model: claude-sonnet-4-6
+model: sonnet
 level: 2
 ---
 

package/bundled/upstream/oh-my-claudecode/agents/explore.md

@@ -1,7 +1,7 @@
 ---
 name: explore
 description: Codebase search specialist for finding files and code patterns
-model: claude-haiku-4-5
+model: haiku
 level: 3
 disallowedTools: Write, Edit
 ---

package/bundled/upstream/oh-my-claudecode/agents/git-master.md

@@ -1,7 +1,7 @@
 ---
 name: git-master
 description: Git expert for atomic commits, rebasing, and history management with style detection
-model: claude-sonnet-4-6
+model: sonnet
 level: 3
 ---
 
@@ -62,8 +62,8 @@ level: 3
     - Format: [semantic (feat:, fix:) / plain / short]
 
     ### Commits Created
-    1. `abc1234` - [commit message] - [N files]
-    2. `def5678` - [commit message] - [N files]
+    1. `<commit-sha-1>` - [commit message] - [N files]
+    2. `<commit-sha-2>` - [commit message] - [N files]
 
     ### Verification
     ```

package/bundled/upstream/oh-my-claudecode/agents/planner.md

@@ -1,7 +1,7 @@
 ---
 name: planner
 description: Strategic planning consultant with interview workflow (Opus)
-model: claude-opus-4-6
+model: opus
 level: 4
 ---
 

package/bundled/upstream/oh-my-claudecode/agents/qa-tester.md

@@ -1,7 +1,7 @@
 ---
 name: qa-tester
 description: Interactive CLI testing specialist using tmux for session management
-model: claude-sonnet-4-6
+model: sonnet
 level: 3
 ---
 

package/bundled/upstream/oh-my-claudecode/agents/scientist.md

@@ -1,7 +1,7 @@
 ---
 name: scientist
 description: Data analysis and research execution specialist
-model: claude-sonnet-4-6
+model: sonnet
 level: 3
 disallowedTools: Write, Edit
 ---

package/bundled/upstream/oh-my-claudecode/agents/security-reviewer.md

@@ -1,7 +1,7 @@
 ---
 name: security-reviewer
 description: Security vulnerability detection specialist (OWASP Top 10, secrets, unsafe patterns)
-model: claude-opus-4-6
+model: opus
 level: 3
 disallowedTools: Write, Edit
 ---

package/bundled/upstream/oh-my-claudecode/agents/test-engineer.md

@@ -1,7 +1,7 @@
 ---
 name: test-engineer
 description: Test strategy, integration/e2e coverage, flaky test hardening, TDD workflows
-model: claude-sonnet-4-6
+model: sonnet
 level: 3
 ---
 
@@ -12,23 +12,6 @@ level: 3
     You are not responsible for feature implementation (executor), code quality review (quality-reviewer), or security testing (security-reviewer).
   </Role>
 
-  <Integration_With_Test_Gen_Skill>
-    When user asks to "generate tests" or "add tests", prefer using the `/test-gen` skill:
-
-    - `/test-gen` handles tech stack detection and complexity analysis automatically
-    - For simple code, `/test-gen` generates tests directly using CLI commands
-    - For complex code, `/test-gen` will delegate to test-engineer with enriched context (detected stack, complexity metrics)
-    - For test strategy and planning, use test-engineer directly
-    - For test debugging and flaky test fixes, use test-engineer directly
-
-    When invoked by `/test-gen` for complex code, you will receive:
-    - Detected tech stack (frontend/backend frameworks, test frameworks, databases, APIs)
-    - Complexity analysis (function size, cyclomatic complexity, dependencies)
-    - Generated test framework (basic structure to build upon)
-
-    Use this context to generate comprehensive test cases that cover edge cases, error scenarios, and business logic validation.
-  </Integration_With_Test_Gen_Skill>
-
   <Why_This_Matters>
     Tests are executable documentation of expected behavior. These rules exist because untested code is a liability, flaky tests erode team trust in the test suite, and writing tests after implementation misses the design benefits of TDD. Good tests catch regressions before users do.
   </Why_This_Matters>
@@ -140,60 +123,3 @@ level: 3
     - For TDD: did I write the failing test first?
   </Final_Checklist>
 </Agent_Prompt>
-
-## Enhanced Integration with Test Generation System
-
-### Automatic Context Enrichment
-
-When invoked for test generation, test-engineer receives enriched context:
-
-- **Tech Stack**: Detected frameworks, languages, and test tools
-- **Complexity Analysis**: Metrics including cyclomatic complexity, nesting levels, external dependencies
-- **Suggested Approach**:
-  - `auto-generate`: Simple code, generate tests automatically
-  - `guided`: Complex code, ask user for clarification
-  - `manual`: Very complex, provide framework and guidance only
-
-### Workflow for Complex Code
-
-When complexity is `complex`:
-
-1. **Review Context**: Examine complexity metrics and reasons
-2. **Ask Questions**: Use pre-generated questions based on complexity reasons
-3. **Generate Test Framework**: Create test structure with placeholders
-4. **Fill in Details**: Based on user answers, complete test cases
-5. **Verify Coverage**: Ensure all identified complexity factors are tested
-
-### Example Invocation
-
-```typescript
-const context = await prepareTestEngineerContext({
-  filePath: 'src/services/payment.ts',
-  code: paymentServiceCode,
-  projectRoot: '/project/root',
-});
-
-// Context includes:
-// - techStack: { backend: { language: 'nodejs', testFramework: 'vitest' } }
-// - complexity: 'complex'
-// - complexityMetrics: { lines: 75, cyclomaticComplexity: 15, ... }
-// - suggestedApproach: 'guided'
-// - questionsForUser: ['What payment flows...', 'Should I mock...']
-```
-
-### Integration with /test-gen Skill
-
-The `/test-gen` skill automatically prepares this context before delegating to test-engineer:
-
-1. User runs `/test-gen src/services/payment.ts`
-2. System detects tech stack and analyzes complexity
-3. If complex, prepares questions and delegates to test-engineer
-4. Test-engineer asks questions and generates comprehensive tests
-5. System verifies tests and commits
-
-### Success Criteria
-
-- [ ] Context preparation includes all necessary information
-- [ ] Questions are relevant to complexity reasons
-- [ ] Test-engineer can generate appropriate tests for both simple and complex code
-- [ ] Integration with /test-gen skill is seamless

package/bundled/upstream/oh-my-claudecode/agents/tracer.md

@@ -1,7 +1,7 @@
 ---
 name: tracer
 description: Evidence-driven causal tracing with competing hypotheses, evidence for/against, uncertainty tracking, and next-probe recommendations
-model: claude-sonnet-4-6
+model: sonnet
 level: 3
 ---
 

package/bundled/upstream/oh-my-claudecode/agents/verifier.md

@@ -1,7 +1,7 @@
 ---
 name: verifier
 description: Verification strategy, evidence-based completion checks, test adequacy
-model: claude-sonnet-4-6
+model: sonnet
 level: 3
 ---
 

package/bundled/upstream/oh-my-claudecode/agents/writer.md

@@ -1,7 +1,7 @@
 ---
 name: writer
 description: Technical documentation writer for README, API docs, and comments (Haiku)
-model: claude-haiku-4-5
+model: haiku
 level: 2
 ---
 

package/bundled/upstream/oh-my-claudecode/hooks/hooks.json

@@ -31,6 +31,11 @@
             "type": "command",
             "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/project-memory-session.mjs",
             "timeout": 5
+          },
+          {
+            "type": "command",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/wiki-session-start.mjs",
+            "timeout": 5
           }
         ]
       },
@@ -92,6 +97,11 @@
             "type": "command",
             "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/project-memory-posttool.mjs",
             "timeout": 3
+          },
+          {
+            "type": "command",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/post-tool-rules-injector.mjs",
+            "timeout": 3
           }
         ]
       }
@@ -150,6 +160,11 @@
             "type": "command",
             "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/project-memory-precompact.mjs",
             "timeout": 5
+          },
+          {
+            "type": "command",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/wiki-pre-compact.mjs",
+            "timeout": 3
           }
         ]
       }
@@ -165,7 +180,7 @@
           },
           {
             "type": "command",
-            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/persistent-mode.cjs",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/persistent-mode.mjs",
             "timeout": 10
           },
           {
@@ -184,6 +199,11 @@
             "type": "command",
             "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/session-end.mjs",
             "timeout": 30
+          },
+          {
+            "type": "command",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/wiki-session-end.mjs",
+            "timeout": 30
           }
         ]
       }

package/bundled/upstream/oh-my-claudecode/skills/AGENTS.md

@@ -0,0 +1,200 @@
+<!-- Parent: ../AGENTS.md -->
+<!-- Generated: 2026-01-28 | Updated: 2026-03-02 -->
+
+# skills
+
+30 skill directories for workflow automation and specialized behaviors.
+
+## Purpose
+
+Skills are reusable workflow templates that can be invoked via `/oh-my-claudecode:skill-name`. Each skill provides:
+- Structured prompts for specific workflows
+- Activation triggers (manual or automatic)
+- Integration with execution modes
+
+## Key Files
+
+### Execution Mode Skills
+
+| File | Skill | Purpose |
+|-----------|-------|---------|
+| `autopilot/SKILL.md` | autopilot | Full autonomous execution from idea to working code |
+| `ultrawork/SKILL.md` | ultrawork | Maximum parallel agent execution |
+| `ralph/SKILL.md` | ralph | Persistence until verified complete |
+| `team/SKILL.md` | team | N coordinated agents with task claiming |
+| `ultraqa/SKILL.md` | ultraqa | QA cycling until goal met |
+
+### Planning Skills
+
+| File | Skill | Purpose |
+|-----------|-------|---------|
+| `plan/SKILL.md` | omc-plan | Strategic planning with interview workflow |
+| `ralplan/SKILL.md` | ralplan | Iterative planning (Planner+Architect+Critic) with RALPLAN-DR structured deliberation (`--deliberate` for high-risk) |
+| `deep-interview/SKILL.md` | deep-interview | Socratic deep interview with mathematical ambiguity gating (Ouroboros-inspired) |
+| `ralph-init/SKILL.md` | ralph-init | Initialize PRD for structured ralph |
+
+### Exploration Skills
+
+| File | Skill | Purpose |
+|-----------|-------|---------|
+| `deepinit/SKILL.md` | deepinit | Generate hierarchical AGENTS.md |
+| `sciomc/SKILL.md` | sciomc | Parallel scientist orchestration |
+
+### Visual Skills
+
+| File | Skill | Purpose |
+|-----------|-------|---------|
+| `visual-verdict/SKILL.md` | visual-verdict | Structured visual QA verdict for screenshot/reference comparisons |
+
+### Utility Skills
+
+| File | Skill | Purpose |
+|-----------|-------|---------|
+| `ai-slop-cleaner/SKILL.md` | ai-slop-cleaner | Regression-safe cleanup workflow for AI-generated code slop |
+| `learner/SKILL.md` | learner | Extract reusable skill from session |
+| `ask/SKILL.md` | ask | Ask Claude, Codex, or Gemini via `omc ask` and capture an artifact |
+| `note/SKILL.md` | note | Save notes for compaction resilience |
+| `cancel/SKILL.md` | cancel | Cancel any active OMC mode |
+| `hud/SKILL.md` | hud | Configure HUD display |
+| `omc-doctor/SKILL.md` | omc-doctor | Diagnose installation issues |
+| `setup/SKILL.md` | setup | Unified setup entrypoint for install, diagnostics, and MCP configuration |
+| `omc-setup/SKILL.md` | omc-setup | One-time setup wizard |
+| `omc-help/SKILL.md` | omc-help | Usage guide |
+| `mcp-setup/SKILL.md` | mcp-setup | Configure MCP servers |
+| `skill/SKILL.md` | skill | Manage local skills |
+
+### Domain Skills
+
+| File | Skill | Purpose |
+|-----------|-------|---------|
+| `project-session-manager/SKILL.md` | project-session-manager (+ `psm` alias) | Isolated dev environments |
+| `writer-memory/SKILL.md` | writer-memory | Agentic memory for writers |
+| `release/SKILL.md` | release | Generic release assistant — analyzes repo CI/rules, caches in `.omc/RELEASE_RULE.md`, guides the release |
+
+## For AI Agents
+
+### Working In This Directory
+
+#### Skill Template Format
+
+```markdown
+---
+name: skill-name
+description: Brief description
+triggers:
+  - "keyword1"
+  - "keyword2"
+agent: executor  # Optional: which agent to use
+model: sonnet    # Optional: model override
+pipeline: [skill-name, follow-up-skill]  # Optional: standardized multi-skill flow
+next-skill: follow-up-skill              # Optional: explicit handoff target
+next-skill-args: --direct                # Optional: arguments for the next skill
+handoff: .omc/plans/example.md           # Optional: artifact/context handed to next skill
+---
+
+# Skill Name
+
+## Purpose
+What this skill accomplishes.
+
+## Workflow
+1. Step one
+2. Step two
+3. Step three
+
+## Usage
+How to invoke this skill.
+
+## Configuration
+Any configurable options.
+```
+
+#### Skill Invocation
+
+```bash
+# Manual invocation
+/oh-my-claudecode:skill-name
+
+# With arguments
+/oh-my-claudecode:skill-name arg1 arg2
+
+# Auto-detected from keywords
+"autopilot build me a REST API"  # Triggers autopilot skill
+```
+
+#### Creating a New Skill
+
+1. Create `new-skill/SKILL.md` directory and file with YAML frontmatter
+2. Define purpose, workflow, and usage
+3. Add to skill registry (auto-detected from frontmatter)
+4. Optionally add activation triggers
+5. Create corresponding `commands/new-skill.md` file (mirror)
+6. Update `docs/REFERENCE.md` (Skills section, count)
+7. If execution mode skill, also create `src/hooks/new-skill/` hook
+
+### Common Patterns
+
+**Skill chaining:**
+```markdown
+## Workflow
+1. Invoke `explore` agent for context
+2. Invoke `architect` for analysis
+3. Invoke `executor` for implementation
+4. Invoke `qa-tester` for verification
+```
+
+If `pipeline` / `next-skill` metadata is present, OMC appends a standardized **Skill Pipeline** handoff block to the rendered skill prompt so downstream steps are explicit.
+
+**Conditional behavior:**
+```markdown
+## Workflow
+1. Check if tests exist
+   - If yes: Run tests first
+   - If no: Create test plan
+2. Proceed with implementation
+```
+
+### Testing Requirements
+
+- Skills are verified via integration tests
+- Test skill invocation with `/oh-my-claudecode:skill-name`
+- Verify trigger keywords activate correct skill
+- For git-related skills, follow `templates/rules/git-workflow.md`
+
+## Dependencies
+
+### Internal
+- Loaded by skill bridge (`scripts/build-skill-bridge.mjs`)
+- References agents from `agents/`
+- Uses hooks from `src/hooks/`
+
+### External
+None - pure markdown files.
+
+## Skill Categories
+
+| Category | Skills | Trigger Keywords |
+|----------|--------|------------------|
+| Execution | autopilot, ultrawork, ralph, team, ultraqa | "autopilot", "ulw", "ralph", "team" |
+| Cleanup | ai-slop-cleaner | "deslop", "anti-slop", cleanup/refactor + slop smells |
+| Planning | omc-plan, ralplan, deep-interview, ralph-init | "plan this", "interview me", "ouroboros" |
+| Exploration | deepinit, sciomc, external-context | "deepinit", "research" |
+| Utility | learner, note, cancel, hud, setup, omc-doctor, omc-setup, omc-help, mcp-setup | "stop", "cancel" |
+| Domain | psm, writer-memory, release | psm context |
+
+## Auto-Activation
+
+Some skills activate automatically based on context:
+
+| Skill | Auto-Trigger Condition |
+|-------|----------------------|
+| autopilot | "autopilot", "build me", "I want a" |
+| ultrawork | "ulw", "ultrawork" |
+| ralph | "ralph", "don't stop until" |
+| deep-interview | "deep interview", "interview me", "ouroboros", "don't assume" |
+| cancel | "stop", "cancel", "abort" |
+
+<!-- MANUAL:
+- Team runtime wait semantics: `omc_run_team_wait.timeout_ms` only limits the wait call and does not stop workers.
+- `timeoutSeconds` is removed from `omc_run_team_start`; use explicit `omc_run_team_cleanup` for intentional worker pane termination.
+-->