claudecode-omc 4.8.2 → 4.8.4

package/docs/partials/agent-tiers.md

@@ -8,7 +8,6 @@ This is the single source of truth for all agent tier information. All skill fil
 |--------|-------------|-----------------|-------------|
 | **Analysis** | architect-low | architect-medium | architect |
 | **Execution** | executor-low | executor | executor-high |
-| **Deep Work** | - | - | deep-executor |
 | **Search** | explore | - | explore-high |
 | **Research** | - | document-specialist | - |
 | **Frontend** | designer-low | designer | designer-high |
@@ -19,8 +18,7 @@ This is the single source of truth for all agent tier information. All skill fil
 | **Pre-Planning** | - | - | analyst |
 | **Testing** | - | qa-tester | - |
 | **Security** | security-reviewer-low | - | security-reviewer |
-| **Build** | - | build-fixer | - |
-| **TDD** | tdd-guide-low | tdd-guide | - |
+| **TDD** | test-engineer (model=haiku) | test-engineer | - |
 | **Code Review** | - | - | code-reviewer |
 | **Data Science** | - | scientist | scientist-high |
 
@@ -55,10 +53,10 @@ This is the single source of truth for all agent tier information. All skill fil
 | Interactive CLI testing | qa-tester | MEDIUM |
 | Security review | security-reviewer | HIGH |
 | Quick security scan | security-reviewer-low | LOW |
-| Fix build errors | build-fixer | MEDIUM |
-| Simple build fix | build-fixer (model=haiku) | LOW |
-| TDD workflow | tdd-guide | MEDIUM |
-| Quick test suggestions | tdd-guide-low | LOW |
+| Fix build errors | debugger | MEDIUM |
+| Simple build fix | debugger (model=haiku) | LOW |
+| TDD workflow | test-engineer | MEDIUM |
+| Quick test suggestions | test-engineer (model=haiku) | LOW |
 | Code review | code-reviewer | HIGH |
 | Quick code check | code-reviewer (model=haiku) | LOW |
 | Data analysis/stats | scientist | MEDIUM |
@@ -68,11 +66,11 @@ This is the single source of truth for all agent tier information. All skill fil
 | Get file/workspace symbol outline | explore | LOW |
 | Structural code pattern search | explore | LOW |
 | Structural code transformation | executor-high | HIGH |
-| Project-wide type checking | build-fixer | MEDIUM |
+| Project-wide type checking | debugger | MEDIUM |
 | Check single file for errors | executor-low | LOW |
 | Data analysis / computation | scientist | MEDIUM |
-| Complex autonomous work | deep-executor | HIGH |
-| Deep goal-oriented execution | deep-executor | HIGH |
+| Complex autonomous work | executor-high | HIGH |
+| Deep goal-oriented execution | executor-high | HIGH |
 
 ## Usage
 
@@ -123,10 +121,8 @@ For token savings, prefer lower tiers when the task allows:
 | `executor-low` | yes | - | - | - | - | - | - |
 | `executor` | yes | yes | - | - | - | - | - |
 | `executor-high` | yes | yes | - | - | yes | yes | - |
-| `deep-executor` | yes | yes | - | - | yes | yes | - |
-| `build-fixer` | yes | yes | - | - | - | - | - |
-| `tdd-guide` | yes | - | - | - | - | - | - |
-| `tdd-guide-low` | yes | - | - | - | - | - | - |
+| `debugger` | yes | yes | - | - | - | - | - |
+| `test-engineer` | yes | - | - | - | - | - | - |
 | `code-reviewer` | yes | - | - | - | yes | - | - |
 | `qa-tester` | yes | - | - | - | - | - | - |
 | `scientist` | - | - | - | - | - | - | yes |
@@ -154,7 +150,7 @@ For complex rename or refactoring tasks requiring implementation, delegate to `e
 - **Need to find all usages of a symbol?** Use `lsp_find_references` via `explore-high` (only agent with it)
 - **Need structural code patterns?** (e.g., "find all functions matching X shape") Use `ast_grep_search` via `explore` family, `architect`/`architect-medium`, or `code-reviewer`
 - **Need to transform code structurally?** Use `ast_grep_replace` via `executor-high` (only agent with it)
-- **Need project-wide type checking?** Use `lsp_diagnostics_directory` via `architect`/`architect-medium`, `executor`/`executor-high`, or `build-fixer`
+- **Need project-wide type checking?** Use `lsp_diagnostics_directory` via `architect`/`architect-medium`, `executor`/`executor-high`, or `debugger`
 - **Need single-file error checking?** Use `lsp_diagnostics` via many agents (see matrix)
 - **Need data analysis / computation?** Use `python_repl` via `scientist` or `scientist-high`
 - **Need quick type info or definition lookup?** Use `lsp_hover`/`lsp_goto_definition` directly (orchestrator-direct tools)

package/docs/partials/features.md

@@ -103,8 +103,8 @@ Sequential agent chaining with data passing between stages.
 | Preset | Stages |
 |--------|--------|
 | `review` | explore -> architect -> critic -> executor |
-| `implement` | planner -> executor -> tdd-guide |
-| `debug` | explore -> architect -> build-fixer |
+| `implement` | planner -> executor -> test-engineer |
+| `debug` | explore -> architect -> debugger |
 | `research` | parallel(document-specialist, explore) -> architect -> writer |
 | `refactor` | explore -> architect-medium -> executor-high -> qa-tester |
 | `security` | explore -> security-reviewer -> executor -> security-reviewer-low |

package/docs/partials/mode-selection-guide.md

@@ -29,7 +29,7 @@ Uncertain about requirements or have a vague idea?
 
 Want autonomous execution?
 ├── YES: Is task parallelizable into 3+ independent components?
-│   ├── YES: team N:deep-executor (parallel autonomous with file ownership)
+│   ├── YES: team N:executor (parallel autonomous with file ownership)
 │   └── NO: autopilot (sequential with ralph phases)
 └── NO: Want parallel execution with manual oversight?
     ├── YES: Do you want cost optimization?
@@ -48,7 +48,7 @@ Have many similar independent tasks (e.g., "fix 47 errors")?
 | User Request | Best Mode | Why |
 |--------------|-----------|-----|
 | "Build me a REST API" | autopilot | Single coherent deliverable |
-| "Build frontend, backend, and database" | team 3:deep-executor | Clear component boundaries |
+| "Build frontend, backend, and database" | team 3:executor | Clear component boundaries |
 | "Fix all 47 TypeScript errors" | team 5:executor | Many independent similar tasks |
 | "Refactor auth module thoroughly" | ralph | Need persistence + verification |
 | "Quick parallel execution" | ultrawork | Manual oversight preferred |

package/docs/shared/agent-tiers.md

@@ -8,7 +8,6 @@ This is the single source of truth for all agent tier information. All skill fil
 |--------|-------------|-----------------|-------------|
 | **Analysis** | architect-low | architect-medium | architect |
 | **Execution** | executor-low | executor | executor-high |
-| **Deep Work** | - | - | deep-executor |
 | **Search** | explore | - | explore-high |
 | **Research** | - | document-specialist | - |
 | **Frontend** | designer-low | designer | designer-high |
@@ -19,8 +18,7 @@ This is the single source of truth for all agent tier information. All skill fil
 | **Pre-Planning** | - | - | analyst |
 | **Testing** | - | qa-tester | - |
 | **Security** | security-reviewer-low | - | security-reviewer |
-| **Build** | - | build-fixer | - |
-| **TDD** | tdd-guide-low | tdd-guide | - |
+| **TDD** | test-engineer (model=haiku) | test-engineer | - |
 | **Code Review** | - | - | code-reviewer |
 | **Data Science** | - | scientist | scientist-high |
 
@@ -55,10 +53,10 @@ This is the single source of truth for all agent tier information. All skill fil
 | Interactive CLI testing | qa-tester | MEDIUM |
 | Security review | security-reviewer | HIGH |
 | Quick security scan | security-reviewer-low | LOW |
-| Fix build errors | build-fixer | MEDIUM |
-| Simple build fix | build-fixer (model=haiku) | LOW |
-| TDD workflow | tdd-guide | MEDIUM |
-| Quick test suggestions | tdd-guide-low | LOW |
+| Fix build errors | debugger | MEDIUM |
+| Simple build fix | debugger (model=haiku) | LOW |
+| TDD workflow | test-engineer | MEDIUM |
+| Quick test suggestions | test-engineer (model=haiku) | LOW |
 | Code review | code-reviewer | HIGH |
 | Quick code check | code-reviewer (model=haiku) | LOW |
 | Data analysis/stats | scientist | MEDIUM |
@@ -68,11 +66,11 @@ This is the single source of truth for all agent tier information. All skill fil
 | Get file/workspace symbol outline | explore | LOW |
 | Structural code pattern search | explore | LOW |
 | Structural code transformation | executor-high | HIGH |
-| Project-wide type checking | build-fixer | MEDIUM |
+| Project-wide type checking | debugger | MEDIUM |
 | Check single file for errors | executor-low | LOW |
 | Data analysis / computation | scientist | MEDIUM |
-| Complex autonomous work | deep-executor | HIGH |
-| Deep goal-oriented execution | deep-executor | HIGH |
+| Complex autonomous work | executor-high | HIGH |
+| Deep goal-oriented execution | executor-high | HIGH |
 
 ## Usage
 
@@ -123,10 +121,8 @@ For token savings, prefer lower tiers when the task allows:
 | `executor-low` | yes | - | - | - | - | - | - |
 | `executor` | yes | yes | - | - | - | - | - |
 | `executor-high` | yes | yes | - | - | yes | yes | - |
-| `deep-executor` | yes | yes | - | - | yes | yes | - |
-| `build-fixer` | yes | yes | - | - | - | - | - |
-| `tdd-guide` | yes | - | - | - | - | - | - |
-| `tdd-guide-low` | yes | - | - | - | - | - | - |
+| `debugger` | yes | yes | - | - | - | - | - |
+| `test-engineer` | yes | - | - | - | - | - | - |
 | `code-reviewer` | yes | - | - | - | yes | - | - |
 | `qa-tester` | yes | - | - | - | - | - | - |
 | `scientist` | - | - | - | - | - | - | yes |
@@ -154,7 +150,7 @@ For complex rename or refactoring tasks requiring implementation, delegate to `e
 - **Need to find all usages of a symbol?** Use `lsp_find_references` via `explore-high` (only agent with it)
 - **Need structural code patterns?** (e.g., "find all functions matching X shape") Use `ast_grep_search` via `explore` family, `architect`/`architect-medium`, or `code-reviewer`
 - **Need to transform code structurally?** Use `ast_grep_replace` via `executor-high` (only agent with it)
-- **Need project-wide type checking?** Use `lsp_diagnostics_directory` via `architect`/`architect-medium`, `executor`/`executor-high`, or `build-fixer`
+- **Need project-wide type checking?** Use `lsp_diagnostics_directory` via `architect`/`architect-medium`, `executor`/`executor-high`, or `debugger`
 - **Need single-file error checking?** Use `lsp_diagnostics` via many agents (see matrix)
 - **Need data analysis / computation?** Use `python_repl` via `scientist` or `scientist-high`
 - **Need quick type info or definition lookup?** Use `lsp_hover`/`lsp_goto_definition` directly (orchestrator-direct tools)

package/docs/shared/features.md

@@ -103,8 +103,8 @@ Sequential agent chaining with data passing between stages.
 | Preset | Stages |
 |--------|--------|
 | `review` | explore -> architect -> critic -> executor |
-| `implement` | planner -> executor -> tdd-guide |
-| `debug` | explore -> architect -> build-fixer |
+| `implement` | planner -> executor -> test-engineer |
+| `debug` | explore -> architect -> debugger |
 | `research` | parallel(document-specialist, explore) -> architect -> writer |
 | `refactor` | explore -> architect-medium -> executor-high -> qa-tester |
 | `security` | explore -> security-reviewer -> executor -> security-reviewer-low |

package/docs/shared/mode-selection-guide.md

@@ -29,7 +29,7 @@ Uncertain about requirements or have a vague idea?
 
 Want autonomous execution?
 ├── YES: Is task parallelizable into 3+ independent components?
-│   ├── YES: team N:deep-executor (parallel autonomous with file ownership)
+│   ├── YES: team N:executor (parallel autonomous with file ownership)
 │   └── NO: autopilot (sequential with ralph phases)
 └── NO: Want parallel execution with manual oversight?
     ├── YES: Do you want cost optimization?
@@ -48,7 +48,7 @@ Have many similar independent tasks (e.g., "fix 47 errors")?
 | User Request | Best Mode | Why |
 |--------------|-----------|-----|
 | "Build me a REST API" | autopilot | Single coherent deliverable |
-| "Build frontend, backend, and database" | team 3:deep-executor | Clear component boundaries |
+| "Build frontend, backend, and database" | team 3:executor | Clear component boundaries |
 | "Fix all 47 TypeScript errors" | team 5:executor | Many independent similar tasks |
 | "Refactor auth module thoroughly" | ralph | Need persistence + verification |
 | "Quick parallel execution" | ultrawork | Manual oversight preferred |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claudecode-omc",
-  "version": "4.8.2",
+  "version": "4.8.4",
   "description": "Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode",
   "type": "module",
   "main": "dist/index.js",
@@ -52,6 +52,9 @@
     "dev": "tsc --watch",
     "start": "node dist/index.js",
     "test": "vitest",
+    "bench:prompts": "tsx benchmarks/run-all.ts",
+    "bench:prompts:save": "tsx benchmarks/run-all.ts --save-baseline",
+    "bench:prompts:compare": "tsx benchmarks/run-all.ts --compare",
     "test:ui": "vitest --ui",
     "test:run": "vitest run",
     "test:coverage": "vitest run --coverage",

package/scripts/code-simplifier.mjs

@@ -129,7 +129,7 @@ async function main() {
     }
 
     process.stdout.write(
-      JSON.stringify({ decision: 'block', reason: buildMessage(files) }) + '\n',
+      JSON.stringify({ continue: false, decision: 'block', reason: buildMessage(files) }) + '\n',
     );
   } catch (error) {
     try {

package/scripts/context-guard-stop.mjs

@@ -26,6 +26,7 @@ import { execSync } from 'node:child_process';
 import { readStdin } from './lib/stdin.mjs';
 
 const THRESHOLD = parseInt(process.env.OMC_CONTEXT_GUARD_THRESHOLD || '75', 10);
+const CRITICAL_THRESHOLD = 95;
 const MAX_BLOCKS = 2;
 
 /**
@@ -33,19 +34,22 @@ const MAX_BLOCKS = 2;
  * Mirrors the logic in persistent-mode.cjs to stay consistent.
  */
 function isContextLimitStop(data) {
-  const reason = (data.stop_reason || data.stopReason || '').toLowerCase();
+  const reasons = [
+    data.stop_reason,
+    data.stopReason,
+    data.end_turn_reason,
+    data.endTurnReason,
+    data.reason,
+  ]
+    .filter((value) => typeof value === 'string' && value.trim().length > 0)
+    .map((value) => value.toLowerCase().replace(/[\s-]+/g, '_'));
   const contextPatterns = [
     'context_limit', 'context_window', 'context_exceeded',
     'context_full', 'max_context', 'token_limit',
     'max_tokens', 'conversation_too_long', 'input_too_long',
   ];
 
-  if (contextPatterns.some(p => reason.includes(p))) return true;
-
-  const endTurnReason = (data.end_turn_reason || data.endTurnReason || '').toLowerCase();
-  if (endTurnReason && contextPatterns.some(p => endTurnReason.includes(p))) return true;
-
-  return false;
+  return reasons.some((reason) => contextPatterns.some(p => reason.includes(p)));
 }
 
 /**
@@ -192,6 +196,14 @@ function incrementBlockCount(sessionId) {
   } catch { /* ignore */ }
 }
 
+function buildStopRecoveryAdvice(contextPercent, blockCount) {
+  const severity = contextPercent >= 90 ? 'CRITICAL' : 'HIGH';
+  return `[OMC ${severity}] Context at ${contextPercent}% (threshold: ${THRESHOLD}%). ` +
+    `Run /compact immediately before continuing. If /compact cannot complete, ` +
+    `stop spawning new agents and recover in a fresh session using existing checkpoints ` +
+    `(.omc/state, .omc/notepad.md). (Block ${blockCount}/${MAX_BLOCKS})`;
+}
+
 async function main() {
   try {
     const input = await readStdin();
@@ -214,6 +226,11 @@ async function main() {
     const transcriptPath = resolveTranscriptPath(rawTranscriptPath, data.cwd);
     const pct = estimateContextPercent(transcriptPath);
 
+    if (pct >= CRITICAL_THRESHOLD) {
+      console.log(JSON.stringify({ continue: true, suppressOutput: true }));
+      return;
+    }
+
     if (pct >= THRESHOLD) {
       // Check retry guard
       const blockCount = getBlockCount(sessionId);
@@ -226,10 +243,9 @@ async function main() {
       incrementBlockCount(sessionId);
 
       console.log(JSON.stringify({
+        continue: false,
         decision: 'block',
-        reason: `[OMC] Context at ${pct}% (threshold: ${THRESHOLD}%). ` +
-          `Quality degrades at high context. Run /compact or start a fresh session. ` +
-          `(Block ${blockCount + 1}/${MAX_BLOCKS})`
+        reason: buildStopRecoveryAdvice(pct, blockCount + 1)
       }));
       return;
     }

package/scripts/keyword-detector.mjs

@@ -9,17 +9,18 @@
  * 1. cancelomc/stopomc: Stop active modes
  * 2. ralph: Persistence mode until task completion
  * 3. autopilot: Full autonomous execution
- * 4. team: Coordinated team execution (replaces ultrapilot/swarm)
+ * 4. team: Explicit-only via /team (not auto-triggered)
  * 5. ultrawork/ulw: Maximum parallel execution
- * 6. pipeline: Sequential agent chaining
- * 7. ccg: Claude-Codex-Gemini tri-model orchestration
- * 9. ralplan: Iterative planning with consensus
- * 10. plan: Planning interview mode
- * 11. tdd: Test-driven development
- * 12. research: Research orchestration
- * 13. ultrathink/think: Extended reasoning
- * 14. deepsearch: Codebase search (restricted patterns)
- * 15. analyze: Analysis mode (restricted patterns)
+ * 5. ccg: Claude-Codex-Gemini tri-model orchestration
+ * 6. ralplan: Iterative planning with consensus
+ * 7. deep interview: Socratic interview workflow
+ * 8. ai-slop-cleaner: Cleanup/deslop anti-slop workflow
+ * 9. tdd: Test-driven development
+ * 10. code review: Comprehensive review mode
+ * 11. security review: Security-focused review mode
+ * 12. ultrathink: Extended reasoning
+ * 13. deepsearch: Codebase search (restricted patterns)
+ * 14. analyze: Analysis mode (restricted patterns)
  */
 
 import { writeFileSync, readFileSync, mkdirSync, existsSync, unlinkSync } from 'fs';
@@ -44,6 +45,40 @@ Use your extended thinking capabilities to provide the most thorough and well-re
 ---
 `;
 
+const ANALYZE_MESSAGE = `<analyze-mode>
+ANALYSIS MODE. Gather context before diving deep:
+- Search relevant code paths first
+- Compare working vs broken behavior
+- Synthesize findings before proposing changes
+</analyze-mode>
+
+---
+`;
+
+const TDD_MESSAGE = `<tdd-mode>
+[TDD MODE ACTIVATED]
+Write or update tests first when practical, confirm they fail for the right reason, then implement the minimal fix and re-run verification.
+</tdd-mode>
+
+---
+`;
+
+const CODE_REVIEW_MESSAGE = `<code-review-mode>
+[CODE REVIEW MODE ACTIVATED]
+Perform a comprehensive code review of the relevant changes or target area. Focus on correctness, maintainability, edge cases, regressions, and test adequacy before recommending changes.
+</code-review-mode>
+
+---
+`;
+
+const SECURITY_REVIEW_MESSAGE = `<security-review-mode>
+[SECURITY REVIEW MODE ACTIVATED]
+Perform a focused security review of the relevant changes or target area. Check trust boundaries, auth/authz, data exposure, input validation, command/file access, secrets handling, and escalation risks before recommending changes.
+</security-review-mode>
+
+---
+`;
+
 // Extract prompt from various JSON structures
 function extractPrompt(input) {
   try {
@@ -64,6 +99,15 @@ function extractPrompt(input) {
 }
 
 // Sanitize text to prevent false positives from code blocks, XML tags, URLs, and file paths
+const ANTI_SLOP_EXPLICIT_PATTERN = /\b(ai[\s-]?slop|anti[\s-]?slop|deslop|de[\s-]?slop)\b/i;
+const ANTI_SLOP_ACTION_PATTERN = /\b(clean(?:\s*up)?|cleanup|refactor|simplify|dedupe|de-duplicate|prune)\b/i;
+const ANTI_SLOP_SMELL_PATTERN = /\b(slop|duplicate(?:d|s)?|duplication|dead\s+code|unused\s+code|over[\s-]?abstract(?:ion|ed)?|wrapper\s+layers?|boundary\s+violations?|needless\s+abstractions?|unnecessary\s+abstractions?|ai[\s-]?generated|generated\s+code|tech\s+debt)\b/i;
+
+function isAntiSlopCleanupRequest(text) {
+  return ANTI_SLOP_EXPLICIT_PATTERN.test(text) ||
+    (ANTI_SLOP_ACTION_PATTERN.test(text) && ANTI_SLOP_SMELL_PATTERN.test(text));
+}
+
 function sanitizeForKeywordDetection(text) {
   return text
     // 1. Strip XML-style tag blocks: <tag-name ...>...</tag-name> (multi-line, greedy on tag name)
@@ -88,6 +132,7 @@ function activateState(directory, prompt, stateName, sessionId) {
     started_at: new Date().toISOString(),
     original_prompt: prompt,
     session_id: sessionId || undefined,
+    project_path: directory,
     reinforcement_count: 0,
     last_checked_at: new Date().toISOString()
   };
@@ -261,8 +306,8 @@ function resolveConflicts(matches) {
   // Team keyword detection removed — team is now explicit-only via /team skill.
 
   // Sort by priority order
-  const priorityOrder = ['cancel','ralph','autopilot','team','ultrawork',
-    'pipeline','ccg','ralplan','plan','tdd','research','ultrathink','deepsearch','analyze'];
+  const priorityOrder = ['cancel','ralph','autopilot','ultrawork',
+    'ccg','ralplan','deep-interview','ai-slop-cleaner','tdd','code-review','security-review','ultrathink','deepsearch','analyze'];
   resolved.sort((a, b) => priorityOrder.indexOf(a.name) - priorityOrder.indexOf(b.name));
 
   return resolved;
@@ -353,10 +398,6 @@ async function main() {
     // Team keyword detection removed — team mode is now explicit-only via /team skill.
     // This prevents infinite spawning when Claude workers receive prompts containing "team".
 
-    // Pipeline keywords
-    if (/\b(pipeline)\b/i.test(cleanPrompt) || /\bchain\s+agents\b/i.test(cleanPrompt)) {
-      matches.push({ name: 'pipeline', args: '' });
-    }
 
     // CCG keywords (Claude-Codex-Gemini tri-model orchestration)
     if (/\b(ccg|claude-codex-gemini)\b/i.test(cleanPrompt)) {
@@ -368,6 +409,16 @@ async function main() {
       matches.push({ name: 'ralplan', args: '' });
     }
 
+    // Deep interview keywords
+    if (/\b(deep[\s-]interview|ouroboros)\b/i.test(cleanPrompt)) {
+      matches.push({ name: 'deep-interview', args: '' });
+    }
+
+    // AI slop cleanup keywords
+    if (isAntiSlopCleanupRequest(cleanPrompt)) {
+      matches.push({ name: 'ai-slop-cleaner', args: '' });
+    }
+
     // TDD keywords
     if (/\b(tdd)\b/i.test(cleanPrompt) ||
         /\btest\s+first\b/i.test(cleanPrompt) ||
@@ -375,9 +426,14 @@ async function main() {
       matches.push({ name: 'tdd', args: '' });
     }
 
-    // Sciomc keywords
-    if (/\banalyze\s+data\b/i.test(cleanPrompt)) {
-      matches.push({ name: 'sciomc', args: '' });
+    // Code review keywords
+    if (/\b(code\s+review|review\s+code)\b/i.test(cleanPrompt)) {
+      matches.push({ name: 'code-review', args: '' });
+    }
+
+    // Security review keywords
+    if (/\b(security\s+review|review\s+security)\b/i.test(cleanPrompt)) {
+      matches.push({ name: 'security-review', args: '' });
     }
 
     // Ultrathink keywords
@@ -393,9 +449,7 @@ async function main() {
     }
 
     // Analyze keywords
-    if (/\b(deep\s*analyze)\b/i.test(cleanPrompt) ||
-        /\binvestigate\s+(the|this|why)\b/i.test(cleanPrompt) ||
-        /\bdebug\s+(the|this|why)\b/i.test(cleanPrompt)) {
+    if (/\b(deep[\s-]?analyze|deepanalyze)\b/i.test(cleanPrompt)) {
       matches.push({ name: 'analyze', args: '' });
     }
 
@@ -431,7 +485,7 @@ async function main() {
 
     // Handle cancel specially - clear states and emit
     if (resolved.length > 0 && resolved[0].name === 'cancel') {
-      clearStateFiles(directory, ['ralph', 'autopilot', 'ultrawork', 'swarm', 'pipeline'], sessionId);
+      clearStateFiles(directory, ['ralph', 'autopilot', 'ultrawork', 'swarm'], sessionId);
       console.log(JSON.stringify(createHookOutput(createSkillInvocation('cancel', prompt))));
       return;
     }
@@ -456,27 +510,33 @@ async function main() {
       activateState(directory, prompt, 'ultrawork', sessionId);
     }
 
-    // Handle ultrathink specially - prepend message instead of skill invocation
-    const ultrathinkIndex = resolved.findIndex(m => m.name === 'ultrathink');
-    if (ultrathinkIndex !== -1) {
-      // Remove ultrathink from skill list
-      resolved.splice(ultrathinkIndex, 1);
-
-      // If ultrathink was the only match, emit message
-      if (resolved.length === 0) {
-        console.log(JSON.stringify(createHookOutput(ULTRATHINK_MESSAGE)));
-        return;
+    const additionalContextParts = [];
+    for (const [keywordName, message] of [
+      ['ultrathink', ULTRATHINK_MESSAGE],
+      ['analyze', ANALYZE_MESSAGE],
+      ['tdd', TDD_MESSAGE],
+      ['code-review', CODE_REVIEW_MESSAGE],
+      ['security-review', SECURITY_REVIEW_MESSAGE],
+    ]) {
+      const index = resolved.findIndex(m => m.name === keywordName);
+      if (index !== -1) {
+        resolved.splice(index, 1);
+        additionalContextParts.push(message);
       }
+    }
 
-      // Otherwise, prepend ultrathink message to skill invocation
-      const skillMessage = createMultiSkillInvocation(resolved, prompt);
-      console.log(JSON.stringify(createHookOutput(ULTRATHINK_MESSAGE + skillMessage)));
+    if (resolved.length === 0 && additionalContextParts.length > 0) {
+      console.log(JSON.stringify(createHookOutput(additionalContextParts.join(''))));
       return;
     }
 
-    const skillMatches = resolved;
-    if (skillMatches.length > 0) {
-      console.log(JSON.stringify(createHookOutput(createMultiSkillInvocation(skillMatches, prompt))));
+    if (resolved.length > 0) {
+      additionalContextParts.push(createMultiSkillInvocation(resolved, prompt));
+    }
+
+    if (additionalContextParts.length > 0) {
+      console.log(JSON.stringify(createHookOutput(additionalContextParts.join(''))));
+      return;
     }
   } catch (error) {
     // On any error, allow continuation