knowzcode 0.3.6 → 0.3.7

package/.claude-plugin/marketplace.json

@@ -6,14 +6,14 @@
   },
   "metadata": {
     "description": "Official KnowzCode plugin marketplace - Platform-agnostic AI development methodology",
-    "version": "0.3.6"
+    "version": "0.3.7"
   },
   "plugins": [
     {
       "name": "kc",
       "source": "./",
       "description": "KnowzCode - Platform-agnostic AI development methodology with TDD, quality gates, and structured workflows",
-      "version": "0.3.6",
+      "version": "0.3.7",
       "author": {
         "name": "Alex Headscarf"
       },

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "kc",
   "description": "KnowzCode - Platform-agnostic AI development methodology with TDD, quality gates, and structured workflows",
-  "version": "0.3.6",
+  "version": "0.3.7",
   "author": {
     "name": "Alex Headscarf"
   }

package/README.md

@@ -6,7 +6,7 @@
 
 [![License: MIT + Commons Clause](https://img.shields.io/badge/License-MIT_+_Commons_Clause-yellow.svg)](LICENSE)
 [![Claude Code Plugin](https://img.shields.io/badge/Claude_Code-Plugin-purple)](https://github.com/knowz-io/knowzcode)
-[![Version](https://img.shields.io/badge/version-0.3.6-blue)](https://github.com/knowz-io/knowzcode/releases)
+[![Version](https://img.shields.io/badge/version-0.3.7-blue)](https://github.com/knowz-io/knowzcode/releases)
 
 [Installation](#installation) · [Quick Start](#quick-start) · [When to Use It](#when-to-use-knowzcode) · [How It Works](#how-it-works) · [Commands](#commands) · [Docs](#documentation)
 

package/agents/closer.md

@@ -4,7 +4,7 @@ description: "KnowzCode: Finalization — specs, tracker, log, architecture, lea
 tools: Read, Write, Edit, Glob, Grep
 model: opus
 permissionMode: acceptEdits
-maxTurns: 20
+maxTurns: 25
 ---
 
 # Closer
@@ -16,6 +16,16 @@ Your expertise: Finalization of specs, tracker, log, architecture docs, and lear
 
 Execute the finalization phase after implementation is verified. Update all KnowzCode artifacts to reflect the completed work, then create a final commit.
 
+## Startup MCP Verification
+
+On spawn, verify MCP connectivity before beginning finalization:
+
+1. Read `knowzcode/knowzcode_vaults.md` — check for configured vaults (non-empty ID)
+2. If no configured vaults → skip vault writes (nothing to write to)
+3. If configured vaults exist → call `list_vaults()` to verify MCP connectivity
+   - If succeeds → proceed with vault writes during Learning Capture
+   - If fails → queue all captures to `knowzcode/pending_captures.md` during Learning Capture
+
 ## Finalization Protocol
 
 Follow the steps in `knowzcode_loop.md` section 3.5:
@@ -56,7 +66,7 @@ During finalization:
 
 ## Learning Capture
 
-Scan the WorkGroup for insight-worthy patterns using the signal types from `knowzcode_loop.md` section 7 (Pattern, Decision, Workaround, Performance, Security, Convention).
+Scan the WorkGroup for insight-worthy patterns using the signal types from `knowzcode_loop.md` section 7 (Pattern, Decision, Workaround, Performance, Security, Convention, Integration, Scope).
 
 ### Knowz-Scribe Delegation (Parallel Teams)
 
@@ -68,21 +78,93 @@ If knowz-scribe is active (Parallel Teams mode with MCP connected):
 
 ### Direct Write Fallback (Sequential/Subagent)
 
-If knowz-scribe is NOT active but MCP is configured:
+If knowz-scribe is NOT active but MCP is available (verified at startup):
+
+> **Content Detail Principle**: Vault entries are retrieved via semantic search — write detailed, self-contained content with full reasoning, technology names, and code examples. See `knowzcode/knowzcode_vaults.md` (canonical source for content filters).
+
+#### Step 1: Read Context
+
+1. Read `knowzcode/knowzcode_vaults.md` to discover configured vaults, their IDs, write conditions, and content filters
+2. Skip vault entries with empty ID fields — these haven't been created on the server yet
+3. Treat backwards-compat aliases identically: `research`/`domain`/`platform` = `ecosystem`, `sessions` = `finalizations`
+4. If a single vault is configured (regardless of type), route everything there
+
+#### Step 2: Determine Target Vaults
+
+Use the **Learning Category Routing** table to map each detected learning to the correct vault type:
+
+| Learning Category | Target Vault Type | Title Prefix |
+|-------------------|-------------------|--------------|
+| Pattern | `code` | `Pattern:` |
+| Workaround | `code` | `Workaround:` |
+| Performance | `code` | `Performance:` |
+| Decision | `ecosystem` | `Decision:` |
+| Convention | `ecosystem` | `Convention:` |
+| Security | `ecosystem` | `Security:` |
+| Integration | `ecosystem` | `Integration:` |
+| Scope | `ecosystem` | `Scope:` |
+| Completion record | `finalizations` | `Completion:` |
+| Audit trail | user's enterprise vault (if configured) | `Audit:` |
+
+Only write if the targeted vault is configured — skip gracefully if not.
+
+#### Step 3: Format Content
+
+For each target vault, apply its **Content Filter** as defined in `knowzcode/knowzcode_vaults.md`:
+
+- `code` vault: `[CONTEXT]` / `[PATTERN]` / `[EXAMPLE]` / `[TAGS]`
+- `ecosystem` vault: `[CONTEXT]` / `[INSIGHT]` / `[RATIONALE]` / `[TAGS]`
+- `finalizations` vault: `[GOAL]` / `[OUTCOME]` / `[NODES]` / `[DURATION]` / `[SUMMARY]` / `[TAGS]`
+
+Follow the Content Detail Principle: write self-contained entries with full reasoning, specific technology names, code examples, and file paths. Every entry must be useful without any other context — it will be found via semantic search months later.
+
+- **Title**: Use the prefix from the routing table + descriptive summary with technology names
+- **Tags**: learning category, `phase-3`, domain tags, technology names
+- **Source**: `KnowzCode WorkGroup {wgid}`
+
+#### Step 4: Dedup Check
+
+Before each write, call `search_knowledge(title, vaultId, 3)` on the target vault. If a result with a substantially similar title AND content already exists, skip the write. Log dedup catches in the WorkGroup file.
+
+#### Step 5: Write
+
+Call `create_knowledge` with the formatted payload for each target vault.
+
+#### Phase 3 Extraction Guide
+
+When scanning the WorkGroup for learnings, extract:
+- **Architectural learnings**: Structural discoveries, component relationships that were not obvious, integration patterns that emerged during implementation
+- **Convention patterns established**: New team conventions with full rationale and examples
+- **Consolidation decisions**: What was merged or refactored during finalization and why
+- **Implementation patterns**: Any Pattern/Workaround/Performance insights captured in the WorkGroup during Phase 2A that were not already written by a scribe
+- **Scope decisions**: What was included/excluded and the rationale (from Phase 1A)
+- **Security findings**: From Phase 2B audit, with severity and remediation
+
+#### Enterprise Audit Trail
+
+If `knowzcode/enterprise/compliance_manifest.md` exists and `mcp_compliance_enabled: true`:
+1. Find vault matching type "enterprise" in `knowzcode/knowzcode_vaults.md`
+2. Push completion record with goal, NodeIDs, audit score, and decisions
+3. Push architecture drift findings if any detected during finalization
+
+### MCP Graceful Degradation
 
-> **Content Detail Principle**: Vault entries are retrieved via semantic search — write detailed, self-contained content with full reasoning, technology names, and code examples. See `knowzcode/knowzcode_vaults.md`.
+If MCP calls fail during vault writes (or MCP was unavailable at startup):
 
-1. Read `knowzcode/knowzcode_vaults.md` to discover configured vaults
-2. For each learning type, find the appropriate vault by type:
-   - Pattern/Workaround/Performance → vault with type `code`
-   - Decision/Convention/Security/Integration → vault with type `ecosystem`
-   - Completion records → vault with type `finalizations`
-   - If a single vault covers all types (or only a `research`/`domain`/`platform` alias vault exists), write everything there
-3. Only write if the targeted vault is configured — skip gracefully if not
-4. **Title prefixes**: `Pattern:`, `Decision:`, `Workaround:`, `Performance:`, `Security:`, `Convention:`
-5. For enterprise audit trail: find vault matching type "enterprise", push completion record if configured and compliance is enabled
+1. **Queue locally**: Append each capture to `knowzcode/pending_captures.md`:
+   ```markdown
+   ### {timestamp} — {title}
+   - **Intent**: Phase 3 capture
+   - **Category**: {Pattern|Decision|Workaround|Performance|Security|Convention|Integration|Scope|Completion}
+   - **Target Vault Type**: {code|ecosystem|enterprise|finalizations}
+   - **Source**: closer / WorkGroup {wgid}
+   - **Content**: {full formatted content that would have been written to the vault}
+   ```
+2. Log the MCP failure in the WorkGroup file: `"KnowzCode: MCP unavailable — queued {N} capture(s) to pending_captures.md"`
+3. Note in the finalization report that captures were queued locally
+4. The pending file can be flushed later via `/kc:learn --flush` or by a future scribe instance
 
-If MCP is not available, skip learning capture and audit trail — all other finalization works normally.
+**Never drop knowledge.** If MCP is down, queue it. All other finalization steps (specs, tracker, log, architecture, commit) proceed normally regardless of MCP status.
 
 ## Exit Expectations
 

package/commands/work.md

@@ -313,7 +313,10 @@ When Parallel Teams mode is active, follow these 4 stages instead of spawning on
 3. **MCP Probe** — determine vault availability BEFORE spawning:
    a. Read `knowzcode/knowzcode_vaults.md` — partition entries into CONFIGURED (non-empty ID) and UNCREATED (empty ID)
    b. Call `list_vaults(includeStats=true)` **always** — regardless of whether any IDs exist in the file
-   c. If `list_vaults()` fails → set `MCP_ACTIVE = false`, announce `**MCP Status: Not connected**`, skip to Step 4
+   c. If `list_vaults()` fails:
+      - Check if `knowzcode/knowzcode_vaults.md` has any CONFIGURED entries (non-empty ID)
+      - **If CONFIGURED entries exist**: Set `MCP_ACTIVE = true`, `VAULTS_CONFIGURED = true` — vault agents will verify connectivity independently via their Startup Verification. Announce `**MCP Status: Lead probe failed — delegating verification to vault agents**`. Proceed to Step 4.
+      - **If no CONFIGURED entries** (all empty IDs or no file): Set `MCP_ACTIVE = false`, announce `**MCP Status: Not connected**`, skip Group B spawn
    d. If `list_vaults()` succeeds AND UNCREATED list is non-empty → present the **Vault Creation Prompt**:
 
       ```markdown
@@ -610,6 +613,20 @@ When creating tasks, model the dependency chain with `addBlockedBy` and pre-assi
 
 When using Sequential Teams (`--sequential`) or Subagent Delegation, follow the traditional one-agent-per-phase flow. For each phase below: spawn the agent, create a task, wait for completion, present quality gate, shut down agent, proceed to next phase.
 
+### MCP Probe (Sequential/Subagent)
+
+Determine vault availability before Phase 1A:
+
+1. Read `knowzcode/knowzcode_vaults.md` — check for CONFIGURED entries (non-empty ID)
+2. Attempt `list_vaults(includeStats=true)`
+3. If succeeds AND UNCREATED entries exist → present the **Vault Creation Prompt** (same as Parallel Teams Step 3d). Handle selection identically.
+4. After resolution, announce MCP status to the user:
+   - `list_vaults()` succeeded: `**MCP Status: Connected — N vault(s) available**`
+   - `list_vaults()` failed but configured vaults exist: `**MCP Status: Lead probe failed — closer will verify at Phase 3**`
+   - No configured vaults: `**MCP Status: Not configured**`
+
+The closer agent independently verifies MCP at Phase 3 regardless of this result (see `agents/closer.md` — Startup MCP Verification). This probe is for the user announcement and vault creation opportunity only.
+
 ---
 
 ## Phase Prompt Reference
@@ -752,7 +769,7 @@ Two temporary agents that scan the codebase in parallel with the analyst, broadc
 **Dispatch**:
 - *Parallel Teams*: **Group B** — spawned at Stage 0 if `VAULTS_CONFIGURED = true`, no blockedBy. Persistent — stays alive through the entire workflow. Shut down after Phase 3 capture is complete.
 - *Sequential Teams*: Not applicable (knowz-scribe is Parallel Teams only).
-- *Subagent*: Not applicable — vault writes in subagent mode are handled inline by the lead.
+- *Subagent*: Not applicable — vault writes in subagent mode are handled by the closer during Phase 3 finalization (see Direct Write Fallback in `agents/closer.md`).
 
 ---
 
@@ -1089,7 +1106,7 @@ If MCP is configured and knowz-scribe is active, after audit approval:
 
 **Agent**: `closer` | **Loop.md**: Section 3.5
 
-**Spawn prompt**:
+**Spawn prompt (Parallel Teams)**:
 > You are the **closer** for WorkGroup `{wgid}`.
 > Read `agents/closer.md` for your full role definition.
 >
@@ -1101,13 +1118,28 @@ If MCP is configured and knowz-scribe is active, after audit approval:
 >
 > **Your Task**: #{task-id} — claim immediately (`TaskUpdate(status: "in_progress")`). Mark completed with summary when done.
 > **Conventions**: Update WorkGroup file with results (prefix entries with `KnowzCode:`). If blocked, report blocker and notify lead.
-> **Vault writes**: If knowz-scribe is active, create a capture task (`TaskCreate("Scribe: Capture Phase 3")` → `TaskUpdate(owner: "knowz-scribe")`), then send `"Capture Phase 3: {wgid}. Your task: #{task-id}"` to delegate learning capture and audit trail writes. Do NOT call `create_knowledge` directly.
+> **Vault writes**: Knowz-scribe is active. Create a capture task (`TaskCreate("Scribe: Capture Phase 3")` → `TaskUpdate(owner: "knowz-scribe")`), then send `"Capture Phase 3: {wgid}. Your task: #{task-id}"` to delegate learning capture and audit trail writes. Do NOT call `create_knowledge` directly.
 > **Deliverable**: Atomic finalization — update specs to FINAL, update tracker, write log entry, update architecture if needed, delegate learning capture to knowz-scribe, and create final commit.
 
+**Spawn prompt (Sequential Teams / Subagent)**:
+> You are the **closer** for WorkGroup `{wgid}`.
+> Read `agents/closer.md` for your full role definition.
+>
+> **Goal**: {goal}
+> **Change Set**: {NodeIDs}
+> **Specs**: {list of spec file paths}
+> **Context files**: Read sections 1-2, 3.5, 6, and 7 of `knowzcode/knowzcode_loop.md` (skip other phases), `knowzcode/knowzcode_tracker.md`, `knowzcode/knowzcode_project.md`, `knowzcode/knowzcode_architecture.md`, `knowzcode/knowzcode_log.md`
+> **WorkGroup file**: `knowzcode/workgroups/{wgid}.md`
+>
+> **Your Task**: #{task-id} — claim immediately (`TaskUpdate(status: "in_progress")`). Mark completed with summary when done.
+> **Conventions**: Update WorkGroup file with results (prefix entries with `KnowzCode:`). If blocked, report blocker and notify lead.
+> **Vault writes**: No knowz-scribe — you own all vault writes. Follow the Direct Write Fallback in `agents/closer.md`.
+> **Deliverable**: Atomic finalization — update specs to FINAL, update tracker, write log entry, update architecture if needed, write learnings to vaults, and create final commit.
+
 **Dispatch**:
-- *Parallel Teams*: Spawned at Stage 3 (`addBlockedBy`: last audit/re-audit task). All other agents shut down before closer starts, except knowz-scout and knowz-scribe (stay alive for Phase 3 capture).
-- *Sequential Teams*: Spawn teammate `closer`, create task `Phase 3: Finalize WorkGroup {wgid}`, wait for completion.
-- *Subagent*: `Task(subagent_type="closer", description="Phase 3 finalization", prompt=<above>)`
+- *Parallel Teams*: Spawned at Stage 3 (`addBlockedBy`: last audit/re-audit task). Use the **Parallel Teams** spawn prompt. All other agents shut down before closer starts, except knowz-scout and knowz-scribe (stay alive for Phase 3 capture).
+- *Sequential Teams*: Spawn teammate `closer`, create task `Phase 3: Finalize WorkGroup {wgid}`, wait for completion. Use the **Sequential Teams / Subagent** spawn prompt.
+- *Subagent*: `Task(subagent_type="closer", description="Phase 3 finalization", prompt=<Sequential/Subagent spawn prompt above>)`
 
 ### Phase 3 Output
 

package/knowzcode/knowzcode_loop.md

@@ -338,6 +338,9 @@ During finalization, scan the WorkGroup for insight-worthy patterns:
 | Workaround | "workaround", "limitation", "can't do X so" |
 | Performance | "optimized", "reduced from X to Y", "cache" |
 | Security | "vulnerability", "sanitize", "authentication fix" |
+| Convention | "established convention", "team standard", "naming pattern", "agreed to always" |
+| Integration | "API integration", "upstream API changed", "service dependency", "webhook" |
+| Scope | "included because", "excluded because", "out of scope", "deferred to" |
 
 ### Auto-Capture Triggers
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "knowzcode",
-  "version": "0.3.6",
+  "version": "0.3.7",
   "description": "Platform-agnostic AI development methodology with TDD, quality gates, and structured workflows",
   "type": "module",
   "bin": {

package/skills/alias-resolver.json

@@ -1,15 +1,15 @@
-{
-  "name": "alias-resolver",
-  "version": "0.3.6",
-  "description": "Resolves friendly natural-language aliases to KnowzCode canonical values (phase, audit, plan, workgroup_type).",
-  "parameters": [
-    {"name": "domain", "type": "string", "required": true},
-    {"name": "text", "type": "string", "required": false}
-  ],
-  "actions": [
-    {
-      "type": "python",
-      "code": "domain = (inputs.get('domain') or '').strip().lower()\ntext = (inputs.get('text') or '').strip().lower()\nresult = {'value': None}\nphase_map = {\n    '1a': {'agent': 'analyst', 'prompt': 'knowzcode/prompts/[LOOP_1A]__Propose_Change_Set.md'},\n    '1b': {'agent': 'architect', 'prompt': 'knowzcode/prompts/[LOOP_1B]__Draft_Specs.md'},\n    '2a': {'agent': 'builder', 'prompt': 'knowzcode/prompts/[LOOP_2A]__Implement_Change_Set.md'},\n    '2b': {'agent': 'reviewer', 'prompt': 'knowzcode/prompts/[LOOP_2B]__Verify_Implementation.md'},\n    '3': {'agent': 'closer', 'prompt': 'knowzcode/prompts/[LOOP_3]__Finalize_And_Commit.md'}\n}\nphase_synonyms = {\n    '1a': ['1a','loop 1a','analyze','analysis','impact','scope','change set','proposal'],\n    '1b': ['1b','loop 1b','spec','specs','draft','design','blueprint'],\n    '2a': ['2a','loop 2a','implement','implementation','build','code','develop'],\n    '2b': ['2b','loop 2b','verify','verification','audit','test','qa','review'],\n    '3': ['3','loop 3','final','finalize','finalization','commit','wrap up','close']\n}\naudit_map = {\n    'spec': 'knowzcode/prompts/Spec_Verification_Checkpoint.md',\n    'implementation': 'knowzcode/prompts/[LOOP_2B]__Verify_Implementation.md',\n    'architecture': None,\n    'security': None,\n    'integration': None\n}\naudit_synonyms = {\n    'spec': ['spec','specs','specification','checkpoint'],\n    'implementation': ['implementation','code','verify implementation','loop 2b'],\n    'architecture': ['architecture','arch','diagram','flowchart','structure'],\n    'security': ['security','sec','owasp','vulnerability'],\n    'integration': ['integration','holistic','system','end to end','e2e']\n}\nworkgroup_map = {'feat': 'feat','feature': 'feat','fix': 'fix','bug': 'fix','bugfix': 'fix','refactor': 'refactor','cleanup': 'refactor','issue': 'issue','incident': 'issue'}\nif domain == 'phase':\n    if not text:\n        key = '1a'\n    else:\n        key = None\n        for canonical, synonyms in phase_synonyms.items():\n            if text == canonical or text in synonyms or any(s in text for s in synonyms):\n                key = canonical\n                break\n        if key is None:\n            for canonical in phase_map.keys():\n                if text.replace(' ','') == canonical:\n                    key = canonical\n                    break\n        if key is None:\n            key = '1a'\n    data = phase_map[key]\n    result['value'] = key.upper()\n    result['prompt'] = data['prompt']\n    result['agent'] = data['agent']\n    result['requires_workgroup'] = data['agent'] != 'analyst'\nelif domain == 'audit':\n    if not text:\n        key = 'spec'\n    else:\n        key = None\n        for canonical, synonyms in audit_synonyms.items():\n            if text == canonical or text in synonyms or any(s in text for s in synonyms):\n                key = canonical\n                break\n        if key is None:\n            key = 'spec'\n    result['value'] = key\n    result['prompt'] = audit_map.get(key)\n    result['agent'] = 'reviewer'\nelif domain == 'plan':\n    result['value'] = text or ''\n    result['prompt'] = None\nelif domain == 'workgroup_type':\n    if not text:\n        value = 'feat'\n    else:\n        value = None\n        for key, mapped in workgroup_map.items():\n            if text == key or key in text:\n                value = mapped\n                break\n        if value is None:\n            value = workgroup_map.get(text, 'feat')\n    result['value'] = value\nelse:\n    result['value'] = text or ''\noutputs.update(result)\n"
-    }
-  ]
-}
+{
+  "name": "alias-resolver",
+  "version": "0.3.7",
+  "description": "Resolves friendly natural-language aliases to KnowzCode canonical values (phase, audit, plan, workgroup_type).",
+  "parameters": [
+    {"name": "domain", "type": "string", "required": true},
+    {"name": "text", "type": "string", "required": false}
+  ],
+  "actions": [
+    {
+      "type": "python",
+      "code": "domain = (inputs.get('domain') or '').strip().lower()\ntext = (inputs.get('text') or '').strip().lower()\nresult = {'value': None}\nphase_map = {\n    '1a': {'agent': 'analyst', 'prompt': 'knowzcode/prompts/[LOOP_1A]__Propose_Change_Set.md'},\n    '1b': {'agent': 'architect', 'prompt': 'knowzcode/prompts/[LOOP_1B]__Draft_Specs.md'},\n    '2a': {'agent': 'builder', 'prompt': 'knowzcode/prompts/[LOOP_2A]__Implement_Change_Set.md'},\n    '2b': {'agent': 'reviewer', 'prompt': 'knowzcode/prompts/[LOOP_2B]__Verify_Implementation.md'},\n    '3': {'agent': 'closer', 'prompt': 'knowzcode/prompts/[LOOP_3]__Finalize_And_Commit.md'}\n}\nphase_synonyms = {\n    '1a': ['1a','loop 1a','analyze','analysis','impact','scope','change set','proposal'],\n    '1b': ['1b','loop 1b','spec','specs','draft','design','blueprint'],\n    '2a': ['2a','loop 2a','implement','implementation','build','code','develop'],\n    '2b': ['2b','loop 2b','verify','verification','audit','test','qa','review'],\n    '3': ['3','loop 3','final','finalize','finalization','commit','wrap up','close']\n}\naudit_map = {\n    'spec': 'knowzcode/prompts/Spec_Verification_Checkpoint.md',\n    'implementation': 'knowzcode/prompts/[LOOP_2B]__Verify_Implementation.md',\n    'architecture': None,\n    'security': None,\n    'integration': None\n}\naudit_synonyms = {\n    'spec': ['spec','specs','specification','checkpoint'],\n    'implementation': ['implementation','code','verify implementation','loop 2b'],\n    'architecture': ['architecture','arch','diagram','flowchart','structure'],\n    'security': ['security','sec','owasp','vulnerability'],\n    'integration': ['integration','holistic','system','end to end','e2e']\n}\nworkgroup_map = {'feat': 'feat','feature': 'feat','fix': 'fix','bug': 'fix','bugfix': 'fix','refactor': 'refactor','cleanup': 'refactor','issue': 'issue','incident': 'issue'}\nif domain == 'phase':\n    if not text:\n        key = '1a'\n    else:\n        key = None\n        for canonical, synonyms in phase_synonyms.items():\n            if text == canonical or text in synonyms or any(s in text for s in synonyms):\n                key = canonical\n                break\n        if key is None:\n            for canonical in phase_map.keys():\n                if text.replace(' ','') == canonical:\n                    key = canonical\n                    break\n        if key is None:\n            key = '1a'\n    data = phase_map[key]\n    result['value'] = key.upper()\n    result['prompt'] = data['prompt']\n    result['agent'] = data['agent']\n    result['requires_workgroup'] = data['agent'] != 'analyst'\nelif domain == 'audit':\n    if not text:\n        key = 'spec'\n    else:\n        key = None\n        for canonical, synonyms in audit_synonyms.items():\n            if text == canonical or text in synonyms or any(s in text for s in synonyms):\n                key = canonical\n                break\n        if key is None:\n            key = 'spec'\n    result['value'] = key\n    result['prompt'] = audit_map.get(key)\n    result['agent'] = 'reviewer'\nelif domain == 'plan':\n    result['value'] = text or ''\n    result['prompt'] = None\nelif domain == 'workgroup_type':\n    if not text:\n        value = 'feat'\n    else:\n        value = None\n        for key, mapped in workgroup_map.items():\n            if text == key or key in text:\n                value = mapped\n                break\n        if value is None:\n            value = workgroup_map.get(text, 'feat')\n    result['value'] = value\nelse:\n    result['value'] = text or ''\noutputs.update(result)\n"
+    }
+  ]
+}

package/skills/architecture-diff.json

@@ -1,12 +1,12 @@
-{
-  "name": "architecture-diff",
-  "version": "0.3.6",
-  "description": "Highlights differences between specs and the Mermaid flowchart in knowzcode_architecture.md.",
-  "parameters": [],
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\nimport re\narch = Path('knowzcode/knowzcode_architecture.md').read_text()\nspec_paths = list(Path('knowzcode/specs').glob('*.md'))\nnode_ids = {p.stem for p in spec_paths}\nmermaid_nodes = set(re.findall(r'([A-Z]{2,}_[A-Za-z0-9]+)', arch))\nmissing_in_arch = sorted(node_ids - mermaid_nodes)\nmissing_in_specs = sorted(mermaid_nodes - node_ids)\noutputs['missing_in_architecture'] = missing_in_arch\noutputs['missing_specs'] = missing_in_specs\n"
-    }
-  ]
-}
+{
+  "name": "architecture-diff",
+  "version": "0.3.7",
+  "description": "Highlights differences between specs and the Mermaid flowchart in knowzcode_architecture.md.",
+  "parameters": [],
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\nimport re\narch = Path('knowzcode/knowzcode_architecture.md').read_text()\nspec_paths = list(Path('knowzcode/specs').glob('*.md'))\nnode_ids = {p.stem for p in spec_paths}\nmermaid_nodes = set(re.findall(r'([A-Z]{2,}_[A-Za-z0-9]+)', arch))\nmissing_in_arch = sorted(node_ids - mermaid_nodes)\nmissing_in_specs = sorted(mermaid_nodes - node_ids)\noutputs['missing_in_architecture'] = missing_in_arch\noutputs['missing_specs'] = missing_in_specs\n"
+    }
+  ]
+}

package/skills/check-installation-status.json

@@ -1,14 +1,14 @@
-{
-  "name": "check-installation-status",
-  "version": "0.3.6",
-  "description": "Checks if KnowzCode is initialized in the current project and reports current status",
-
-  "parameters": [],
-
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\n\nknowzcode_dir = Path('knowzcode')\n\nif not knowzcode_dir.exists():\n    outputs['initialized'] = False\n    outputs['commands_count'] = 0\n    outputs['skills_count'] = 0\n    outputs['agents_count'] = 0\n    outputs['has_required_files'] = False\n    exit()\n\n# Check required files exist\nrequired_files = [\n    'knowzcode_loop.md',\n    'knowzcode_tracker.md',\n    'knowzcode_project.md',\n    'knowzcode_architecture.md'\n]\n\nmissing_files = [f for f in required_files if not (knowzcode_dir / f).exists()]\nhas_required_files = len(missing_files) == 0\n\n# Count components from various possible locations\n\n# Check .claude directory\nclaude_dir = Path('.claude')\ncommands_count = 0\nskills_count = 0\nagents_count = 0\n\nif claude_dir.exists():\n    if (claude_dir / 'commands').exists():\n        commands_count = len(list((claude_dir / 'commands').glob('*.md')))\n    if (claude_dir / 'skills').exists():\n        skills_count = len(list((claude_dir / 'skills').glob('*.json')))\n    if (claude_dir / 'agents').exists():\n        agents_count = len(list((claude_dir / 'agents').glob('*.md')))\n    if (claude_dir / 'subagents').exists():\n        agents_count += len(list((claude_dir / 'subagents').glob('*.yaml')))\n\n# Also check top-level directories (plugin installation)\nif Path('commands').exists():\n    commands_count = max(commands_count, len(list(Path('commands').glob('*.md'))))\nif Path('skills').exists():\n    skills_count = max(skills_count, len(list(Path('skills').glob('*.json'))))\nif Path('agents').exists():\n    agents_count = max(agents_count, len(list(Path('agents').glob('*.md'))))\n\noutputs['initialized'] = has_required_files\noutputs['commands_count'] = commands_count\noutputs['skills_count'] = skills_count\noutputs['agents_count'] = agents_count\noutputs['has_required_files'] = has_required_files\noutputs['missing_files'] = missing_files if missing_files else None"
-    }
-  ]
-}
+{
+  "name": "check-installation-status",
+  "version": "0.3.7",
+  "description": "Checks if KnowzCode is initialized in the current project and reports current status",
+
+  "parameters": [],
+
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\n\nknowzcode_dir = Path('knowzcode')\n\nif not knowzcode_dir.exists():\n    outputs['initialized'] = False\n    outputs['commands_count'] = 0\n    outputs['skills_count'] = 0\n    outputs['agents_count'] = 0\n    outputs['has_required_files'] = False\n    exit()\n\n# Check required files exist\nrequired_files = [\n    'knowzcode_loop.md',\n    'knowzcode_tracker.md',\n    'knowzcode_project.md',\n    'knowzcode_architecture.md'\n]\n\nmissing_files = [f for f in required_files if not (knowzcode_dir / f).exists()]\nhas_required_files = len(missing_files) == 0\n\n# Count components from various possible locations\n\n# Check .claude directory\nclaude_dir = Path('.claude')\ncommands_count = 0\nskills_count = 0\nagents_count = 0\n\nif claude_dir.exists():\n    if (claude_dir / 'commands').exists():\n        commands_count = len(list((claude_dir / 'commands').glob('*.md')))\n    if (claude_dir / 'skills').exists():\n        skills_count = len(list((claude_dir / 'skills').glob('*.json')))\n    if (claude_dir / 'agents').exists():\n        agents_count = len(list((claude_dir / 'agents').glob('*.md')))\n    if (claude_dir / 'subagents').exists():\n        agents_count += len(list((claude_dir / 'subagents').glob('*.yaml')))\n\n# Also check top-level directories (plugin installation)\nif Path('commands').exists():\n    commands_count = max(commands_count, len(list(Path('commands').glob('*.md'))))\nif Path('skills').exists():\n    skills_count = max(skills_count, len(list(Path('skills').glob('*.json'))))\nif Path('agents').exists():\n    agents_count = max(agents_count, len(list(Path('agents').glob('*.md'))))\n\noutputs['initialized'] = has_required_files\noutputs['commands_count'] = commands_count\noutputs['skills_count'] = skills_count\noutputs['agents_count'] = agents_count\noutputs['has_required_files'] = has_required_files\noutputs['missing_files'] = missing_files if missing_files else None"
+    }
+  ]
+}

package/skills/environment-guard.json

@@ -1,12 +1,12 @@
-{
-  "name": "environment-guard",
-  "version": "0.3.6",
-  "description": "Verifies that knowzcode/environment_context.md no longer contains placeholder brackets.",
-  "parameters": [],
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\ntext = Path('knowzcode/environment_context.md').read_text()\nplaceholders = [line.strip() for line in text.splitlines() if '[' in line and ']' in line]\nif placeholders:\n    raise ValueError('environment_context.md still contains placeholders: ' + ', '.join(placeholders[:5]))\n"
-    }
-  ]
-}
+{
+  "name": "environment-guard",
+  "version": "0.3.7",
+  "description": "Verifies that knowzcode/environment_context.md no longer contains placeholder brackets.",
+  "parameters": [],
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\ntext = Path('knowzcode/environment_context.md').read_text()\nplaceholders = [line.strip() for line in text.splitlines() if '[' in line and ']' in line]\nif placeholders:\n    raise ValueError('environment_context.md still contains placeholders: ' + ', '.join(placeholders[:5]))\n"
+    }
+  ]
+}

package/skills/generate-workgroup-id.json

@@ -1,25 +1,25 @@
-{
-  "name": "generate-workgroup-id",
-  "version": "0.3.6",
-  "description": "Generates a WorkGroupID following the KnowzCode convention [type]-[slug]-YYYYMMDD-HHMMSS. The slug is a 2-4 word descriptor extracted from the goal.",
-  "parameters": [
-    {
-      "name": "type",
-      "type": "string",
-      "required": true,
-      "description": "One of feat, fix, refactor, issue"
-    },
-    {
-      "name": "slug",
-      "type": "string",
-      "required": false,
-      "description": "A 2-4 word kebab-case descriptor (e.g., 'auth-jwt', 'dark-mode'). If not provided, generates ID without slug."
-    }
-  ],
-  "actions": [
-    {
-      "type": "python",
-      "code": "import datetime\nimport re\nallowed = {'feat', 'fix', 'refactor', 'issue'}\nwg_type = inputs['type']\nif wg_type not in allowed:\n    raise ValueError(f'Invalid type {wg_type!r}, expected one of {sorted(allowed)}')\ntimestamp = datetime.datetime.utcnow().strftime('%Y%m%d-%H%M%S')\nslug = inputs.get('slug', '')\nif slug:\n    # Sanitize slug: lowercase, replace spaces with hyphens, remove non-alphanumeric\n    slug = re.sub(r'[^a-z0-9-]', '', slug.lower().replace(' ', '-'))\n    slug = re.sub(r'-+', '-', slug).strip('-')[:25]  # Max 25 chars\n    outputs['workgroup_id'] = f'{wg_type}-{slug}-{timestamp}'\nelse:\n    outputs['workgroup_id'] = f'{wg_type}-{timestamp}'"
-    }
-  ]
-}
+{
+  "name": "generate-workgroup-id",
+  "version": "0.3.7",
+  "description": "Generates a WorkGroupID following the KnowzCode convention [type]-[slug]-YYYYMMDD-HHMMSS. The slug is a 2-4 word descriptor extracted from the goal.",
+  "parameters": [
+    {
+      "name": "type",
+      "type": "string",
+      "required": true,
+      "description": "One of feat, fix, refactor, issue"
+    },
+    {
+      "name": "slug",
+      "type": "string",
+      "required": false,
+      "description": "A 2-4 word kebab-case descriptor (e.g., 'auth-jwt', 'dark-mode'). If not provided, generates ID without slug."
+    }
+  ],
+  "actions": [
+    {
+      "type": "python",
+      "code": "import datetime\nimport re\nallowed = {'feat', 'fix', 'refactor', 'issue'}\nwg_type = inputs['type']\nif wg_type not in allowed:\n    raise ValueError(f'Invalid type {wg_type!r}, expected one of {sorted(allowed)}')\ntimestamp = datetime.datetime.utcnow().strftime('%Y%m%d-%H%M%S')\nslug = inputs.get('slug', '')\nif slug:\n    # Sanitize slug: lowercase, replace spaces with hyphens, remove non-alphanumeric\n    slug = re.sub(r'[^a-z0-9-]', '', slug.lower().replace(' ', '-'))\n    slug = re.sub(r'-+', '-', slug).strip('-')[:25]  # Max 25 chars\n    outputs['workgroup_id'] = f'{wg_type}-{slug}-{timestamp}'\nelse:\n    outputs['workgroup_id'] = f'{wg_type}-{timestamp}'"
+    }
+  ]
+}

package/skills/install-knowzcode.json

@@ -1,21 +1,21 @@
-{
-  "name": "install-knowzcode",
-  "version": "0.3.6",
-  "description": "Initializes KnowzCode directory structure and required files in the current project",
-
-  "parameters": [
-    {
-      "name": "force",
-      "type": "boolean",
-      "required": false,
-      "description": "Force reinstall even if knowzcode/ exists"
-    }
-  ],
-
-  "actions": [
-    {
-      "type": "python",
-      "code": "import os\nimport json\nfrom pathlib import Path\nfrom datetime import datetime\n\n# Configuration\ntarget_dir = Path('knowzcode')\nforce = inputs.get('force', False)\n\n# Check if target exists\nif target_dir.exists() and not force:\n    outputs['success'] = False\n    outputs['error'] = 'knowzcode/ already exists. Use force=true to reinitialize'\n    outputs['already_installed'] = True\n    exit()\n\n# Create directory structure\ntarget_dir.mkdir(exist_ok=True)\n(target_dir / 'specs').mkdir(exist_ok=True)\n(target_dir / 'workgroups').mkdir(exist_ok=True)\n(target_dir / 'prompts').mkdir(exist_ok=True)\n(target_dir / 'planning').mkdir(exist_ok=True)\n\n# Create .gitignore if it doesn't exist\ngitignore_path = target_dir / '.gitignore'\nif not gitignore_path.exists():\n    gitignore_content = '''# KnowzCode gitignore - protects environment-specific files\n\n# Environment-specific (contains local paths, commands)\nenvironment_context.md\n\n# Session-specific work (can be regenerated)\nworkgroups/\n\n# Personal notes and scratch files\n*.local.md\n.scratch/\n'''\n    with open(gitignore_path, 'w') as f:\n        f.write(gitignore_content)\n\n# Note: The actual template files (knowzcode_loop.md, etc.) should be copied\n# from the plugin template directory or created by the /kc:init command.\n# This skill creates the structure; the command copies the content.\n\noutputs['success'] = True\noutputs['target_dir'] = str(target_dir)\noutputs['directories_created'] = ['specs', 'workgroups', 'prompts', 'planning']\noutputs['gitignore_created'] = not gitignore_path.exists()\noutputs['message'] = f'KnowzCode directory structure created at {target_dir}/'"
-    }
-  ]
-}
+{
+  "name": "install-knowzcode",
+  "version": "0.3.7",
+  "description": "Initializes KnowzCode directory structure and required files in the current project",
+
+  "parameters": [
+    {
+      "name": "force",
+      "type": "boolean",
+      "required": false,
+      "description": "Force reinstall even if knowzcode/ exists"
+    }
+  ],
+
+  "actions": [
+    {
+      "type": "python",
+      "code": "import os\nimport json\nfrom pathlib import Path\nfrom datetime import datetime\n\n# Configuration\ntarget_dir = Path('knowzcode')\nforce = inputs.get('force', False)\n\n# Check if target exists\nif target_dir.exists() and not force:\n    outputs['success'] = False\n    outputs['error'] = 'knowzcode/ already exists. Use force=true to reinitialize'\n    outputs['already_installed'] = True\n    exit()\n\n# Create directory structure\ntarget_dir.mkdir(exist_ok=True)\n(target_dir / 'specs').mkdir(exist_ok=True)\n(target_dir / 'workgroups').mkdir(exist_ok=True)\n(target_dir / 'prompts').mkdir(exist_ok=True)\n(target_dir / 'planning').mkdir(exist_ok=True)\n\n# Create .gitignore if it doesn't exist\ngitignore_path = target_dir / '.gitignore'\nif not gitignore_path.exists():\n    gitignore_content = '''# KnowzCode gitignore - protects environment-specific files\n\n# Environment-specific (contains local paths, commands)\nenvironment_context.md\n\n# Session-specific work (can be regenerated)\nworkgroups/\n\n# Personal notes and scratch files\n*.local.md\n.scratch/\n'''\n    with open(gitignore_path, 'w') as f:\n        f.write(gitignore_content)\n\n# Note: The actual template files (knowzcode_loop.md, etc.) should be copied\n# from the plugin template directory or created by the /kc:init command.\n# This skill creates the structure; the command copies the content.\n\noutputs['success'] = True\noutputs['target_dir'] = str(target_dir)\noutputs['directories_created'] = ['specs', 'workgroups', 'prompts', 'planning']\noutputs['gitignore_created'] = not gitignore_path.exists()\noutputs['message'] = f'KnowzCode directory structure created at {target_dir}/'"
+    }
+  ]
+}

package/skills/load-core-context.json

@@ -1,18 +1,18 @@
-{
-  "name": "load-core-context",
-  "version": "0.3.6",
-  "description": "Loads the KnowzCode project overview, architecture, tracker, log header, and automation manifest for downstream steps.",
-  "parameters": [],
-  "actions": [
-    {
-      "type": "read_file",
-      "paths": [
-        "knowzcode/knowzcode_project.md",
-        "knowzcode/knowzcode_architecture.md",
-        "knowzcode/knowzcode_tracker.md",
-        "knowzcode/knowzcode_log.md",
-        "knowzcode/automation_manifest.md"
-      ]
-    }
-  ]
-}
+{
+  "name": "load-core-context",
+  "version": "0.3.7",
+  "description": "Loads the KnowzCode project overview, architecture, tracker, log header, and automation manifest for downstream steps.",
+  "parameters": [],
+  "actions": [
+    {
+      "type": "read_file",
+      "paths": [
+        "knowzcode/knowzcode_project.md",
+        "knowzcode/knowzcode_architecture.md",
+        "knowzcode/knowzcode_tracker.md",
+        "knowzcode/knowzcode_log.md",
+        "knowzcode/automation_manifest.md"
+      ]
+    }
+  ]
+}

package/skills/log-entry-builder.json

@@ -1,15 +1,15 @@
-{
-  "name": "log-entry-builder",
-  "version": "0.3.6",
-  "description": "Appends structured entries to knowzcode/knowzcode_log.md with KnowzCode formatting.",
-  "parameters": [
-    {"name": "entry_type", "type": "string", "required": true},
-    {"name": "content", "type": "string", "required": true}
-  ],
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\nentry_type = inputs['entry_type']\ncontent = inputs['content'].strip()\npath = Path('knowzcode/knowzcode_log.md')\ntext = path.read_text()\nmarker = '---\n**[NEWEST ENTRIES APPEAR HERE - DO NOT REMOVE THIS MARKER]**'\nidx = text.index(marker) + len(marker)\nnew_entry = f"\n---\n**Type:** {entry_type}\n{content}\n"\nupdated = text[:idx] + new_entry + text[idx:]\npath.write_text(updated)"
-    }
-  ]
-}
+{
+  "name": "log-entry-builder",
+  "version": "0.3.7",
+  "description": "Appends structured entries to knowzcode/knowzcode_log.md with KnowzCode formatting.",
+  "parameters": [
+    {"name": "entry_type", "type": "string", "required": true},
+    {"name": "content", "type": "string", "required": true}
+  ],
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\nentry_type = inputs['entry_type']\ncontent = inputs['content'].strip()\npath = Path('knowzcode/knowzcode_log.md')\ntext = path.read_text()\nmarker = '---\n**[NEWEST ENTRIES APPEAR HERE - DO NOT REMOVE THIS MARKER]**'\nidx = text.index(marker) + len(marker)\nnew_entry = f"\n---\n**Type:** {entry_type}\n{content}\n"\nupdated = text[:idx] + new_entry + text[idx:]\npath.write_text(updated)"
+    }
+  ]
+}

package/skills/spec-quality-check.json

@@ -1,14 +1,14 @@
-{
-  "name": "spec-quality-check",
-  "version": "0.3.6",
-  "description": "Validates KnowzCode spec files for mandatory sections. Supports new 4-section format and legacy numbered format.",
-  "parameters": [
-    {"name": "node_id", "type": "string", "required": true}
-  ],
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\nimport re\nnode_id = inputs['node_id']\npath = Path('knowzcode/specs') / f'{node_id}.md'\nif not path.exists():\n    raise FileNotFoundError(f'Spec for {node_id} not found')\ntext = path.read_text()\n\n# Check new format first\nnew_sections = ['## Rules & Decisions', '## Interfaces', '## Verification Criteria', '## Debt & Gaps']\nlegacy_sections = ['## 1. Purpose', '## 2. Dependencies & Triggers', '## 3. Interfaces', '## 4. Core Logic & Processing Steps', '## 5. Data Structures', '## 6. ARC Verification Criteria', '## 7. Technical Debt']\n\nnew_missing = [s for s in new_sections if s not in text]\nlegacy_missing = [s for s in legacy_sections if s not in text]\n\n# Use whichever format has fewer missing sections\nif len(new_missing) <= len(legacy_missing):\n    outputs['format'] = 'v2'\n    outputs['missing_sections'] = new_missing\nelse:\n    outputs['format'] = 'legacy'\n    outputs['missing_sections'] = legacy_missing\n    outputs['deprecation_warning'] = 'Spec uses old numbered format. New specs should use: Rules & Decisions, Interfaces, Verification Criteria, Debt & Gaps'\n"
-    }
-  ]
-}
+{
+  "name": "spec-quality-check",
+  "version": "0.3.7",
+  "description": "Validates KnowzCode spec files for mandatory sections. Supports new 4-section format and legacy numbered format.",
+  "parameters": [
+    {"name": "node_id", "type": "string", "required": true}
+  ],
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\nimport re\nnode_id = inputs['node_id']\npath = Path('knowzcode/specs') / f'{node_id}.md'\nif not path.exists():\n    raise FileNotFoundError(f'Spec for {node_id} not found')\ntext = path.read_text()\n\n# Check new format first\nnew_sections = ['## Rules & Decisions', '## Interfaces', '## Verification Criteria', '## Debt & Gaps']\nlegacy_sections = ['## 1. Purpose', '## 2. Dependencies & Triggers', '## 3. Interfaces', '## 4. Core Logic & Processing Steps', '## 5. Data Structures', '## 6. ARC Verification Criteria', '## 7. Technical Debt']\n\nnew_missing = [s for s in new_sections if s not in text]\nlegacy_missing = [s for s in legacy_sections if s not in text]\n\n# Use whichever format has fewer missing sections\nif len(new_missing) <= len(legacy_missing):\n    outputs['format'] = 'v2'\n    outputs['missing_sections'] = new_missing\nelse:\n    outputs['format'] = 'legacy'\n    outputs['missing_sections'] = legacy_missing\n    outputs['deprecation_warning'] = 'Spec uses old numbered format. New specs should use: Rules & Decisions, Interfaces, Verification Criteria, Debt & Gaps'\n"
+    }
+  ]
+}

package/skills/spec-template.json

@@ -1,15 +1,15 @@
-{
-  "name": "spec-template",
-  "version": "0.3.6",
-  "description": "Seeds or repairs KnowzCode spec files with the lean 4-section template.",
-  "parameters": [
-    {"name": "node_id", "type": "string", "required": true},
-    {"name": "label", "type": "string", "required": true}
-  ],
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\nfrom datetime import datetime\nnode_id = inputs['node_id']\nlabel = inputs['label']\npath = Path('knowzcode/specs') / f'{node_id}.md'\nnow = datetime.utcnow().strftime('%Y-%m-%d %H:%M:%SZ')\ntemplate_lines = [\n    f'# {node_id}: {label}',\n    '',\n    f'**Updated:** {now}',\n    '**Status:** Draft',\n    '',\n    '## Rules & Decisions',\n    '- [Key architectural decisions, business rules, constraints, and purpose]',\n    '',\n    '## Interfaces',\n    '- [Public contracts: inputs, outputs, API signatures, dependencies, events]',\n    '',\n    '## Verification Criteria',\n    '- VERIFY: [testable assertion 1]',\n    '- VERIFY: [testable assertion 2]',\n    '',\n    '## Debt & Gaps',\n    '- [Known limitations and future work, or \"None\"]',\n    ''\n]\ntemplate = '\\n'.join(template_lines)\nif not path.exists():\n    path.write_text(template + '\\n')\n    outputs['created'] = True\nelse:\n    text = path.read_text()\n    new_sections = ['## Rules & Decisions', '## Interfaces', '## Verification Criteria', '## Debt & Gaps']\n    if all(section in text for section in new_sections):\n        outputs['created'] = False\n    else:\n        merged = text.strip() + '\\n\\n<!-- Template sections restored -->\\n' + template + '\\n'\n        path.write_text(merged)\n        outputs['created'] = False"
-    }
-  ]
-}
+{
+  "name": "spec-template",
+  "version": "0.3.7",
+  "description": "Seeds or repairs KnowzCode spec files with the lean 4-section template.",
+  "parameters": [
+    {"name": "node_id", "type": "string", "required": true},
+    {"name": "label", "type": "string", "required": true}
+  ],
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\nfrom datetime import datetime\nnode_id = inputs['node_id']\nlabel = inputs['label']\npath = Path('knowzcode/specs') / f'{node_id}.md'\nnow = datetime.utcnow().strftime('%Y-%m-%d %H:%M:%SZ')\ntemplate_lines = [\n    f'# {node_id}: {label}',\n    '',\n    f'**Updated:** {now}',\n    '**Status:** Draft',\n    '',\n    '## Rules & Decisions',\n    '- [Key architectural decisions, business rules, constraints, and purpose]',\n    '',\n    '## Interfaces',\n    '- [Public contracts: inputs, outputs, API signatures, dependencies, events]',\n    '',\n    '## Verification Criteria',\n    '- VERIFY: [testable assertion 1]',\n    '- VERIFY: [testable assertion 2]',\n    '',\n    '## Debt & Gaps',\n    '- [Known limitations and future work, or \"None\"]',\n    ''\n]\ntemplate = '\\n'.join(template_lines)\nif not path.exists():\n    path.write_text(template + '\\n')\n    outputs['created'] = True\nelse:\n    text = path.read_text()\n    new_sections = ['## Rules & Decisions', '## Interfaces', '## Verification Criteria', '## Debt & Gaps']\n    if all(section in text for section in new_sections):\n        outputs['created'] = False\n    else:\n        merged = text.strip() + '\\n\\n<!-- Template sections restored -->\\n' + template + '\\n'\n        path.write_text(merged)\n        outputs['created'] = False"
+    }
+  ]
+}

package/skills/spec-validator.json

@@ -1,25 +1,25 @@
-{
-  "name": "spec-validator",
-  "version": "0.3.6",
-  "description": "Validates NodeID specification completeness and quality. Supports new 4-section format (preferred) and legacy numbered sections (deprecated).",
-  "parameters": [
-    {
-      "name": "spec_path",
-      "type": "string",
-      "required": true,
-      "description": "Absolute path to the spec file to validate"
-    },
-    {
-      "name": "node_id",
-      "type": "string",
-      "required": true,
-      "description": "NodeID being validated (for error reporting)"
-    }
-  ],
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\nimport re\n\nspec_path = Path(inputs['spec_path'])\nnode_id = inputs['node_id']\n\nif not spec_path.exists():\n    outputs['valid'] = False\n    outputs['errors'] = [f'Spec file does not exist: {spec_path}']\n    outputs['warnings'] = []\n    outputs['score'] = 0\n    outputs['node_id'] = node_id\n    outputs['format'] = 'missing'\n    exit()\n\ncontent = spec_path.read_text()\n\nerrors = []\nwarnings = []\nscore = 100\n\n# Detect format: new 4-section or legacy numbered\nnew_sections = {\n    'rules': r'##\\s*Rules\\s*(&|and)\\s*Decisions',\n    'interfaces': r'##\\s*Interfaces',\n    'verification': r'##\\s*Verification\\s*Criteria',\n    'debt': r'##\\s*Debt\\s*(&|and)\\s*Gaps'\n}\nlegacy_sections = {\n    'purpose': r'##\\s*1\\.\\s*Purpose',\n    'deps': r'##\\s*2\\.\\s*Dependencies',\n    'interfaces': r'##\\s*3\\.\\s*Interfaces',\n    'logic': r'##\\s*4\\.\\s*Core\\s*Logic',\n    'arc': r'##\\s*(6\\.\\s*Error\\s*Handling|7\\.\\s*ARC\\s*Verification)'\n}\n\nnew_count = sum(1 for p in new_sections.values() if re.search(p, content, re.IGNORECASE))\nlegacy_count = sum(1 for p in legacy_sections.values() if re.search(p, content, re.IGNORECASE))\n\nif new_count >= legacy_count:\n    spec_format = 'v2'\n    # Validate new 4-section format\n    required = [\n        (new_sections['rules'], 'Missing \"Rules & Decisions\" section'),\n        (new_sections['interfaces'], 'Missing \"Interfaces\" section'),\n        (new_sections['verification'], 'Missing \"Verification Criteria\" section'),\n        (new_sections['debt'], 'Missing \"Debt & Gaps\" section')\n    ]\n    for pattern, error_msg in required:\n        if not re.search(pattern, content, re.IGNORECASE):\n            errors.append(error_msg)\n            score -= 15\n    \n    # Check VERIFY: statements (minimum 2)\n    verify_section = re.search(r'##\\s*Verification\\s*Criteria(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if verify_section:\n        verify_content = verify_section.group(1)\n        verify_count = len(re.findall(r'VERIFY:', verify_content))\n        if verify_count < 2:\n            errors.append(f'Only {verify_count} VERIFY: statements found (minimum 2 required)')\n            score -= 15\n    else:\n        errors.append('Verification Criteria section is empty or malformed')\n        score -= 20\n    \n    # Check Rules has content\n    rules_section = re.search(r'##\\s*Rules\\s*(&|and)\\s*Decisions(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if rules_section:\n        rules_content = rules_section.group(2).strip()\n        if len(rules_content) < 20 or re.search(r'^\\s*-\\s*\\[', rules_content):\n            warnings.append('Rules & Decisions section appears to have only placeholder content')\n            score -= 10\n    \n    # Check Interfaces has content\n    iface_section = re.search(r'##\\s*Interfaces(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if iface_section:\n        iface_content = iface_section.group(1).strip()\n        if len(iface_content) < 20 or re.search(r'^\\s*-\\s*\\[', iface_content):\n            warnings.append('Interfaces section appears to have only placeholder content')\n            score -= 10\nelse:\n    spec_format = 'legacy'\n    warnings.append('DEPRECATED: Spec uses old numbered format. Will be migrated when next touched during finalization.')\n    \n    # Validate legacy format\n    required = [\n        (legacy_sections['purpose'], 'Missing \"1. Purpose\" section'),\n        (legacy_sections['deps'], 'Missing \"2. Dependencies\" section'),\n        (legacy_sections['interfaces'], 'Missing \"3. Interfaces\" section'),\n        (legacy_sections['logic'], 'Missing \"4. Core Logic\" section'),\n        (legacy_sections['arc'], 'Missing ARC/Error Handling section')\n    ]\n    for pattern, error_msg in required:\n        if not re.search(pattern, content, re.IGNORECASE):\n            errors.append(error_msg)\n            score -= 15\n    \n    # Check ARC criteria (legacy format)\n    arc_section = re.search(r'##\\s*7\\.\\s*ARC\\s*Verification\\s*Criteria(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if arc_section:\n        arc_content = arc_section.group(1)\n        criteria_count = len(re.findall(r'ARC_[A-Z]+_\\d+:', arc_content))\n        if criteria_count < 3:\n            errors.append(f'Only {criteria_count} testable ARC criteria found (minimum 3 required)')\n            score -= 15\n    else:\n        errors.append('ARC Verification Criteria section is empty or malformed')\n        score -= 20\n\n# Check for placeholder text (both formats)\nplaceholder_patterns = [\n    (r'\\[Agent:', 'Contains [Agent: placeholder'),\n    (r'\\[TODO', 'Contains [TODO] placeholder'),\n    (r'\\[FILL', 'Contains [FILL] placeholder'),\n    (r'\\[TBD\\]', 'Contains [TBD] placeholder'),\n    (r'\\[INSERT', 'Contains [INSERT] placeholder')\n]\nfor pattern, msg in placeholder_patterns:\n    if re.search(pattern, content, re.IGNORECASE):\n        errors.append(msg)\n        score -= 20\n        break\n\n# Calculate final validation\noutputs['valid'] = (score >= 70 and len(errors) == 0)\noutputs['score'] = max(0, score)\noutputs['errors'] = errors\noutputs['warnings'] = warnings\noutputs['node_id'] = node_id\noutputs['spec_path'] = str(spec_path)\noutputs['format'] = spec_format"
-    }
-  ]
-}
+{
+  "name": "spec-validator",
+  "version": "0.3.7",
+  "description": "Validates NodeID specification completeness and quality. Supports new 4-section format (preferred) and legacy numbered sections (deprecated).",
+  "parameters": [
+    {
+      "name": "spec_path",
+      "type": "string",
+      "required": true,
+      "description": "Absolute path to the spec file to validate"
+    },
+    {
+      "name": "node_id",
+      "type": "string",
+      "required": true,
+      "description": "NodeID being validated (for error reporting)"
+    }
+  ],
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\nimport re\n\nspec_path = Path(inputs['spec_path'])\nnode_id = inputs['node_id']\n\nif not spec_path.exists():\n    outputs['valid'] = False\n    outputs['errors'] = [f'Spec file does not exist: {spec_path}']\n    outputs['warnings'] = []\n    outputs['score'] = 0\n    outputs['node_id'] = node_id\n    outputs['format'] = 'missing'\n    exit()\n\ncontent = spec_path.read_text()\n\nerrors = []\nwarnings = []\nscore = 100\n\n# Detect format: new 4-section or legacy numbered\nnew_sections = {\n    'rules': r'##\\s*Rules\\s*(&|and)\\s*Decisions',\n    'interfaces': r'##\\s*Interfaces',\n    'verification': r'##\\s*Verification\\s*Criteria',\n    'debt': r'##\\s*Debt\\s*(&|and)\\s*Gaps'\n}\nlegacy_sections = {\n    'purpose': r'##\\s*1\\.\\s*Purpose',\n    'deps': r'##\\s*2\\.\\s*Dependencies',\n    'interfaces': r'##\\s*3\\.\\s*Interfaces',\n    'logic': r'##\\s*4\\.\\s*Core\\s*Logic',\n    'arc': r'##\\s*(6\\.\\s*Error\\s*Handling|7\\.\\s*ARC\\s*Verification)'\n}\n\nnew_count = sum(1 for p in new_sections.values() if re.search(p, content, re.IGNORECASE))\nlegacy_count = sum(1 for p in legacy_sections.values() if re.search(p, content, re.IGNORECASE))\n\nif new_count >= legacy_count:\n    spec_format = 'v2'\n    # Validate new 4-section format\n    required = [\n        (new_sections['rules'], 'Missing \"Rules & Decisions\" section'),\n        (new_sections['interfaces'], 'Missing \"Interfaces\" section'),\n        (new_sections['verification'], 'Missing \"Verification Criteria\" section'),\n        (new_sections['debt'], 'Missing \"Debt & Gaps\" section')\n    ]\n    for pattern, error_msg in required:\n        if not re.search(pattern, content, re.IGNORECASE):\n            errors.append(error_msg)\n            score -= 15\n    \n    # Check VERIFY: statements (minimum 2)\n    verify_section = re.search(r'##\\s*Verification\\s*Criteria(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if verify_section:\n        verify_content = verify_section.group(1)\n        verify_count = len(re.findall(r'VERIFY:', verify_content))\n        if verify_count < 2:\n            errors.append(f'Only {verify_count} VERIFY: statements found (minimum 2 required)')\n            score -= 15\n    else:\n        errors.append('Verification Criteria section is empty or malformed')\n        score -= 20\n    \n    # Check Rules has content\n    rules_section = re.search(r'##\\s*Rules\\s*(&|and)\\s*Decisions(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if rules_section:\n        rules_content = rules_section.group(2).strip()\n        if len(rules_content) < 20 or re.search(r'^\\s*-\\s*\\[', rules_content):\n            warnings.append('Rules & Decisions section appears to have only placeholder content')\n            score -= 10\n    \n    # Check Interfaces has content\n    iface_section = re.search(r'##\\s*Interfaces(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if iface_section:\n        iface_content = iface_section.group(1).strip()\n        if len(iface_content) < 20 or re.search(r'^\\s*-\\s*\\[', iface_content):\n            warnings.append('Interfaces section appears to have only placeholder content')\n            score -= 10\nelse:\n    spec_format = 'legacy'\n    warnings.append('DEPRECATED: Spec uses old numbered format. Will be migrated when next touched during finalization.')\n    \n    # Validate legacy format\n    required = [\n        (legacy_sections['purpose'], 'Missing \"1. Purpose\" section'),\n        (legacy_sections['deps'], 'Missing \"2. Dependencies\" section'),\n        (legacy_sections['interfaces'], 'Missing \"3. Interfaces\" section'),\n        (legacy_sections['logic'], 'Missing \"4. Core Logic\" section'),\n        (legacy_sections['arc'], 'Missing ARC/Error Handling section')\n    ]\n    for pattern, error_msg in required:\n        if not re.search(pattern, content, re.IGNORECASE):\n            errors.append(error_msg)\n            score -= 15\n    \n    # Check ARC criteria (legacy format)\n    arc_section = re.search(r'##\\s*7\\.\\s*ARC\\s*Verification\\s*Criteria(.+?)(?=##|$)', content, re.DOTALL | re.IGNORECASE)\n    if arc_section:\n        arc_content = arc_section.group(1)\n        criteria_count = len(re.findall(r'ARC_[A-Z]+_\\d+:', arc_content))\n        if criteria_count < 3:\n            errors.append(f'Only {criteria_count} testable ARC criteria found (minimum 3 required)')\n            score -= 15\n    else:\n        errors.append('ARC Verification Criteria section is empty or malformed')\n        score -= 20\n\n# Check for placeholder text (both formats)\nplaceholder_patterns = [\n    (r'\\[Agent:', 'Contains [Agent: placeholder'),\n    (r'\\[TODO', 'Contains [TODO] placeholder'),\n    (r'\\[FILL', 'Contains [FILL] placeholder'),\n    (r'\\[TBD\\]', 'Contains [TBD] placeholder'),\n    (r'\\[INSERT', 'Contains [INSERT] placeholder')\n]\nfor pattern, msg in placeholder_patterns:\n    if re.search(pattern, content, re.IGNORECASE):\n        errors.append(msg)\n        score -= 20\n        break\n\n# Calculate final validation\noutputs['valid'] = (score >= 70 and len(errors) == 0)\noutputs['score'] = max(0, score)\noutputs['errors'] = errors\noutputs['warnings'] = warnings\noutputs['node_id'] = node_id\noutputs['spec_path'] = str(spec_path)\noutputs['format'] = spec_format"
+    }
+  ]
+}

package/skills/tracker-scan.json

@@ -1,12 +1,12 @@
-{
-  "name": "tracker-scan",
-  "version": "0.3.6",
-  "description": "Extracts NodeID statuses and WorkGroup assignments from the KnowzCode tracker.",
-  "parameters": [],
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\ntext = Path('knowzcode/knowzcode_tracker.md').read_text()\nrows = []\nfor line in text.splitlines():\n    if line.startswith('|') and '`' in line:\n        cols = [c.strip() for c in line.strip('|').split('|')]\n        if len(cols) >= 9 and cols[2] != 'Node ID':\n            rows.append({'status': cols[0], 'workgroup_id': cols[1], 'node_id': cols[2].strip('`'), 'notes': cols[8]})\noutputs['rows'] = rows\n"
-    }
-  ]
-}
+{
+  "name": "tracker-scan",
+  "version": "0.3.7",
+  "description": "Extracts NodeID statuses and WorkGroup assignments from the KnowzCode tracker.",
+  "parameters": [],
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\ntext = Path('knowzcode/knowzcode_tracker.md').read_text()\nrows = []\nfor line in text.splitlines():\n    if line.startswith('|') and '`' in line:\n        cols = [c.strip() for c in line.strip('|').split('|')]\n        if len(cols) >= 9 and cols[2] != 'Node ID':\n            rows.append({'status': cols[0], 'workgroup_id': cols[1], 'node_id': cols[2].strip('`'), 'notes': cols[8]})\noutputs['rows'] = rows\n"
+    }
+  ]
+}

package/skills/tracker-update.json

@@ -1,28 +1,28 @@
-{
-  "name": "tracker-update",
-  "version": "0.3.6",
-  "description": "Applies validated updates to knowzcode/knowzcode_tracker.md while preserving table structure.",
-  "parameters": [
-    {
-      "name": "updates",
-      "type": "array",
-      "items": {
-        "type": "object",
-        "properties": {
-          "node_id": {"type": "string"},
-          "status": {"type": "string"},
-          "workgroup_id": {"type": "string"},
-          "notes": {"type": "string"}
-        },
-        "required": ["node_id"]
-      },
-      "required": true
-    }
-  ],
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\npath = Path('knowzcode/knowzcode_tracker.md')\ntext = path.read_text()\nlines = text.splitlines()\nheader_idx = next(i for i, line in enumerate(lines) if line.startswith('| Status |'))\ntable = lines[header_idx:]\nrows = [line for line in table if line.startswith('|')]\nupdates = {u['node_id']: u for u in inputs['updates']}\nnew_rows = []\nfor row in rows:\n    parts = [p.strip() for p in row.strip('|').split('|')]\n    if not parts or parts[2] == 'Node ID':\n        new_rows.append(row)\n        continue\n    node_id = parts[2].strip('`')\n    if node_id in updates:\n        upd = updates[node_id]\n        status = upd.get('status', parts[0].strip())\n        workgroup = upd.get('workgroup_id', parts[1].strip())\n        notes = upd.get('notes', parts[8].strip())\n        new_row = f\"| {status} | {workgroup} | `{node_id}` | {parts[3]} | {parts[4]} | {parts[5]} | {parts[6]} | {parts[7]} | {notes} |\"\n        new_rows.append(new_row)\n        updates.pop(node_id)\n    else:\n        new_rows.append(row)\nif updates:\n    missing = ', '.join(sorted(updates.keys()))\n    raise ValueError(f\"NodeIDs {missing} not found in tracker table\")\nlines[header_idx:] = new_rows + lines[header_idx + len(rows):]\npath.write_text('\\n'.join(lines) + '\\n')"
-    }
-  ]
-}
+{
+  "name": "tracker-update",
+  "version": "0.3.7",
+  "description": "Applies validated updates to knowzcode/knowzcode_tracker.md while preserving table structure.",
+  "parameters": [
+    {
+      "name": "updates",
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "node_id": {"type": "string"},
+          "status": {"type": "string"},
+          "workgroup_id": {"type": "string"},
+          "notes": {"type": "string"}
+        },
+        "required": ["node_id"]
+      },
+      "required": true
+    }
+  ],
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\npath = Path('knowzcode/knowzcode_tracker.md')\ntext = path.read_text()\nlines = text.splitlines()\nheader_idx = next(i for i, line in enumerate(lines) if line.startswith('| Status |'))\ntable = lines[header_idx:]\nrows = [line for line in table if line.startswith('|')]\nupdates = {u['node_id']: u for u in inputs['updates']}\nnew_rows = []\nfor row in rows:\n    parts = [p.strip() for p in row.strip('|').split('|')]\n    if not parts or parts[2] == 'Node ID':\n        new_rows.append(row)\n        continue\n    node_id = parts[2].strip('`')\n    if node_id in updates:\n        upd = updates[node_id]\n        status = upd.get('status', parts[0].strip())\n        workgroup = upd.get('workgroup_id', parts[1].strip())\n        notes = upd.get('notes', parts[8].strip())\n        new_row = f\"| {status} | {workgroup} | `{node_id}` | {parts[3]} | {parts[4]} | {parts[5]} | {parts[6]} | {parts[7]} | {notes} |\"\n        new_rows.append(new_row)\n        updates.pop(node_id)\n    else:\n        new_rows.append(row)\nif updates:\n    missing = ', '.join(sorted(updates.keys()))\n    raise ValueError(f\"NodeIDs {missing} not found in tracker table\")\nlines[header_idx:] = new_rows + lines[header_idx + len(rows):]\npath.write_text('\\n'.join(lines) + '\\n')"
+    }
+  ]
+}

package/skills/validate-installation.json

@@ -1,14 +1,14 @@
-{
-  "name": "validate-installation",
-  "version": "0.3.6",
-  "description": "Validates that KnowzCode installation completed successfully with required directories and files",
-
-  "parameters": [],
-
-  "actions": [
-    {
-      "type": "python",
-      "code": "from pathlib import Path\nimport json\n\n# Check for knowzcode directory (the primary installation target)\nknowzcode_dir = Path('knowzcode')\nerrors = []\nwarnings = []\n\n# Check directory exists\nif not knowzcode_dir.exists():\n    errors.append('knowzcode/ directory not found')\n    outputs['valid'] = False\n    outputs['errors'] = errors\n    outputs['warnings'] = warnings\n    outputs['commands_count'] = 0\n    outputs['skills_count'] = 0\n    outputs['agents_count'] = 0\n    exit()\n\n# Check required knowzcode files\nrequired_files = [\n    'knowzcode_loop.md',\n    'knowzcode_tracker.md',\n    'knowzcode_project.md',\n    'knowzcode_architecture.md'\n]\n\nfor required_file in required_files:\n    if not (knowzcode_dir / required_file).exists():\n        errors.append(f'Missing required file: knowzcode/{required_file}')\n\n# Check required subdirectories\nrequired_dirs = [\n    'specs',\n    'workgroups',\n    'prompts'\n]\n\nfor subdir in required_dirs:\n    if not (knowzcode_dir / subdir).exists():\n        warnings.append(f'Missing directory: knowzcode/{subdir}')\n\n# Check .claude directory for commands/agents (plugin or local installation)\nclaude_dir = Path('.claude')\ncommands_count = 0\nskills_count = 0\nagents_count = 0\n\nif claude_dir.exists():\n    if (claude_dir / 'commands').exists():\n        commands_count = len(list((claude_dir / 'commands').glob('*.md')))\n    if (claude_dir / 'skills').exists():\n        skills_count = len(list((claude_dir / 'skills').glob('*.json')))\n    if (claude_dir / 'agents').exists():\n        agents_count = len(list((claude_dir / 'agents').glob('*.md')))\n    if (claude_dir / 'subagents').exists():\n        agents_count += len(list((claude_dir / 'subagents').glob('*.yaml')))\n\n# Also check top-level commands/skills/agents (plugin installation)\nif Path('commands').exists():\n    commands_count = max(commands_count, len(list(Path('commands').glob('*.md'))))\nif Path('skills').exists():\n    skills_count = max(skills_count, len(list(Path('skills').glob('*.json'))))\nif Path('agents').exists():\n    agents_count = max(agents_count, len(list(Path('agents').glob('*.md'))))\n\n# Expected minimums\nif commands_count < 5:\n    warnings.append(f'Expected at least 5 commands, found {commands_count}')\nif agents_count < 10:\n    warnings.append(f'Expected at least 10 agents, found {agents_count}')\n\noutputs['valid'] = len(errors) == 0\noutputs['errors'] = errors\noutputs['warnings'] = warnings\noutputs['commands_count'] = commands_count\noutputs['skills_count'] = skills_count\noutputs['agents_count'] = agents_count"
-    }
-  ]
-}
+{
+  "name": "validate-installation",
+  "version": "0.3.7",
+  "description": "Validates that KnowzCode installation completed successfully with required directories and files",
+
+  "parameters": [],
+
+  "actions": [
+    {
+      "type": "python",
+      "code": "from pathlib import Path\nimport json\n\n# Check for knowzcode directory (the primary installation target)\nknowzcode_dir = Path('knowzcode')\nerrors = []\nwarnings = []\n\n# Check directory exists\nif not knowzcode_dir.exists():\n    errors.append('knowzcode/ directory not found')\n    outputs['valid'] = False\n    outputs['errors'] = errors\n    outputs['warnings'] = warnings\n    outputs['commands_count'] = 0\n    outputs['skills_count'] = 0\n    outputs['agents_count'] = 0\n    exit()\n\n# Check required knowzcode files\nrequired_files = [\n    'knowzcode_loop.md',\n    'knowzcode_tracker.md',\n    'knowzcode_project.md',\n    'knowzcode_architecture.md'\n]\n\nfor required_file in required_files:\n    if not (knowzcode_dir / required_file).exists():\n        errors.append(f'Missing required file: knowzcode/{required_file}')\n\n# Check required subdirectories\nrequired_dirs = [\n    'specs',\n    'workgroups',\n    'prompts'\n]\n\nfor subdir in required_dirs:\n    if not (knowzcode_dir / subdir).exists():\n        warnings.append(f'Missing directory: knowzcode/{subdir}')\n\n# Check .claude directory for commands/agents (plugin or local installation)\nclaude_dir = Path('.claude')\ncommands_count = 0\nskills_count = 0\nagents_count = 0\n\nif claude_dir.exists():\n    if (claude_dir / 'commands').exists():\n        commands_count = len(list((claude_dir / 'commands').glob('*.md')))\n    if (claude_dir / 'skills').exists():\n        skills_count = len(list((claude_dir / 'skills').glob('*.json')))\n    if (claude_dir / 'agents').exists():\n        agents_count = len(list((claude_dir / 'agents').glob('*.md')))\n    if (claude_dir / 'subagents').exists():\n        agents_count += len(list((claude_dir / 'subagents').glob('*.yaml')))\n\n# Also check top-level commands/skills/agents (plugin installation)\nif Path('commands').exists():\n    commands_count = max(commands_count, len(list(Path('commands').glob('*.md'))))\nif Path('skills').exists():\n    skills_count = max(skills_count, len(list(Path('skills').glob('*.json'))))\nif Path('agents').exists():\n    agents_count = max(agents_count, len(list(Path('agents').glob('*.md'))))\n\n# Expected minimums\nif commands_count < 5:\n    warnings.append(f'Expected at least 5 commands, found {commands_count}')\nif agents_count < 10:\n    warnings.append(f'Expected at least 10 agents, found {agents_count}')\n\noutputs['valid'] = len(errors) == 0\noutputs['errors'] = errors\noutputs['warnings'] = warnings\noutputs['commands_count'] = commands_count\noutputs['skills_count'] = skills_count\noutputs['agents_count'] = agents_count"
+    }
+  ]
+}