feat: Add self-contained orchestration templates and guide

Makes Mosaic Stack self-contained for orchestration - no external dependencies.

New files:
- docs/claude/orchestrator.md - Platform-specific orchestrator protocol
- docs/templates/ - Bootstrap templates for tasks.md, learnings, reports

Templates:
- orchestrator/tasks.md.template - Task tracking scaffold
- orchestrator/orchestrator-learnings.json.template - Variance tracking
- orchestrator/orchestrator-learnings.schema.md - JSON schema docs
- orchestrator/phase-issue-body.md.template - Gitea issue body
- orchestrator/compaction-summary.md.template - 60% checkpoint format
- reports/review-report-scaffold.sh - Creates report directory
- scratchpad.md.template - Per-task working document

Updated CLAUDE.md:
- References local docs/claude/orchestrator.md instead of ~/.claude/
- Added Platform Templates section pointing to docs/templates/

This enables deployment without requiring user-level ~/.claude/ configuration.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

docs/templates/orchestrator/compaction-summary.md.template

@@ -0,0 +1,51 @@
+## Compaction Summary
+
+**Project:** ${PROJECT}
+**Milestone:** ${MILESTONE}
+**Time:** ${CURRENT_DATETIME}
+**Context at compaction:** ${CONTEXT_PERCENT}%
+
+---
+
+### Completed Tasks
+
+| Task | Description | Tokens | Variance |
+|------|-------------|--------|----------|
+| ${TASK_1_ID} | ${TASK_1_DESC} | ${TASK_1_USED} | ${TASK_1_VARIANCE} |
+
+**Phase progress:** ${COMPLETED_COUNT}/${TOTAL_COUNT} tasks
+
+---
+
+### Quality Status
+
+- **Tests:** ${TEST_STATUS}
+- **Lint:** ${LINT_STATUS}
+- **Typecheck:** ${TYPECHECK_STATUS}
+- **Regressions:** ${REGRESSION_COUNT}
+
+---
+
+### Learnings Captured
+
+<!-- Include if variance > 50% on any task -->
+- ${LEARNING_1}
+
+---
+
+### Remaining Tasks
+
+| Task | Description | Status | Estimate |
+|------|-------------|--------|----------|
+| ${NEXT_TASK_ID} | ${NEXT_TASK_DESC} | ready | ${NEXT_TASK_EST} |
+
+---
+
+### Resuming With
+
+**Next task:** ${NEXT_TASK_ID}
+**Reason:** First unblocked task in queue
+
+---
+
+*Context reduced from ${CONTEXT_BEFORE}% to ~25-30%*

docs/templates/orchestrator/orchestrator-learnings.json.template

@@ -0,0 +1,10 @@
+{
+  "schema_version": "1.0",
+  "project": "${PROJECT}",
+  "milestone": "${MILESTONE}",
+  "created_at": "${CURRENT_DATETIME}",
+  "learnings": [],
+  "phase_summaries": [],
+  "proposed_adjustments": [],
+  "investigation_queue": []
+}

docs/templates/orchestrator/orchestrator-learnings.schema.md

@@ -0,0 +1,113 @@
+# Orchestrator Learnings JSON Schema
+
+Reference documentation for `orchestrator-learnings.json` structure.
+
+## Root Object
+
+```json
+{
+  "schema_version": "1.0",
+  "project": "string - Project identifier",
+  "milestone": "string - Milestone identifier",
+  "created_at": "ISO8601 - When file was created",
+  "learnings": [],
+  "phase_summaries": [],
+  "proposed_adjustments": [],
+  "investigation_queue": []
+}
+```
+
+## Learning Entry
+
+Captured when |variance| > 50%.
+
+```json
+{
+  "task_id": "string - Matches task ID from tasks.md (e.g., MS-SEC-001)",
+  "task_type": "enum - See Task Types below",
+  "estimate_k": "number - Estimated tokens in thousands",
+  "actual_k": "number - Actual tokens used in thousands",
+  "variance_pct": "number - ((actual - estimate) / estimate) * 100",
+  "characteristics": {
+    "file_count": "number - Files modified",
+    "keywords": ["array - Descriptive tags for pattern matching"]
+  },
+  "analysis": "string - Human/AI explanation of variance",
+  "flags": ["array - CRITICAL | NEEDS_INVESTIGATION | ANOMALY"],
+  "captured_at": "ISO8601 - When learning was recorded"
+}
+```
+
+### Task Types
+
+| Type                     | Description                                | Base Estimate    |
+| ------------------------ | ------------------------------------------ | ---------------- |
+| `STYLE_FIX`              | Formatting, prettier, lint fixes           | 3-5K             |
+| `BULK_CLEANUP`           | Multi-file cleanup (unused vars, warnings) | file_count × 550 |
+| `GUARD_ADD`              | Add guards, decorators, validation         | 5-8K             |
+| `AUTH_ADD`               | Authentication implementation              | 15-25K           |
+| `ERROR_HANDLING`         | Error handling improvements                | 8-12K            |
+| `CONFIG_DEFAULT_CHANGE`  | Config default changes                     | 5-10K            |
+| `CONFIG_EXTERNALIZATION` | Move hardcoded values to env vars          | 8-12K            |
+| `INPUT_VALIDATION`       | Input sanitization, allowlists             | 5-8K             |
+| `BUG_FIX_SIMPLE`         | Simple bug fixes (single file)             | 3-8K             |
+| `REFACTOR`               | Code refactoring                           | 10-15K           |
+| `COMPLEX_REFACTOR`       | Multi-file architectural changes           | 25-40K           |
+| `TEST_ADD`               | Adding test coverage                       | 15-25K           |
+
+## Phase Summary
+
+Generated after phase verification task.
+
+```json
+{
+  "phase": "number - Phase number",
+  "tasks_completed": "number",
+  "tasks_total": "number",
+  "estimate_total_k": "number - Sum of estimates",
+  "actual_total_k": "number - Sum of actual usage",
+  "variance_avg_pct": "number - Average variance",
+  "pattern": "enum - SYSTEMATIC_UNDERESTIMATE | ACCURATE | OVERESTIMATE",
+  "notes": "string - Summary observations"
+}
+```
+
+## Proposed Adjustment
+
+Heuristic improvement proposals.
+
+```json
+{
+  "category": "string - Task type category",
+  "current_heuristic": "string - Current estimation formula",
+  "proposed_heuristic": "string - Improved formula",
+  "confidence": "enum - HIGH | MEDIUM | LOW",
+  "evidence": ["array - Task IDs supporting this"],
+  "variance_if_applied": "string - Expected improvement",
+  "notes": "string - Additional context"
+}
+```
+
+## Investigation Queue
+
+Tasks requiring manual review.
+
+```json
+{
+  "task_id": "string",
+  "question": "string - What needs investigation",
+  "priority": "enum - HIGH | MEDIUM | LOW",
+  "status": "enum - OPEN | IN_PROGRESS | CLOSED",
+  "resolution": "string - Outcome when closed",
+  "verified_at": "ISO8601 - When investigation completed"
+}
+```
+
+## Variance Thresholds
+
+| Variance | Action                                |
+| -------- | ------------------------------------- |
+| 0-30%    | Log only (acceptable)                 |
+| 30-50%   | Flag for review                       |
+| 50-100%  | Capture learning                      |
+| >100%    | CRITICAL — review task classification |

docs/templates/orchestrator/phase-issue-body.md.template

@@ -0,0 +1,43 @@
+## Phase ${PHASE_NUMBER}: ${PHASE_NAME}
+
+**Milestone:** ${MILESTONE}
+**Branch:** `${PHASE_BRANCH}`
+**Estimate:** ${PHASE_ESTIMATE_K}K tokens
+
+---
+
+### Scope
+
+${PHASE_SCOPE}
+
+### Tasks
+
+<!-- Generated from findings -->
+- [ ] Task 1
+- [ ] Task 2
+
+### Acceptance Criteria
+
+- [ ] All quality gates pass (lint, typecheck, tests)
+- [ ] No regressions from baseline
+- [ ] Code review approved
+- [ ] tasks.md updated with actual token usage
+
+### Dependencies
+
+**Blocked by:** ${BLOCKED_BY}
+**Blocks:** ${BLOCKS}
+
+### Quality Gates
+
+```bash
+# Run before marking tasks complete
+pnpm lint
+pnpm typecheck
+pnpm test
+```
+
+---
+
+**Tracking:** docs/tasks.md
+**Learnings:** docs/orchestrator-learnings.json

docs/templates/orchestrator/tasks.md.template

@@ -0,0 +1,62 @@
+# Tasks
+
+<!--
+  Project: ${PROJECT}
+  Milestone: ${MILESTONE}
+  Created: ${CURRENT_DATETIME}
+
+  IMPORTANT: This file is owned by the orchestrator. Workers NEVER modify it.
+-->
+
+<!--
+## Column Reference
+
+| Column | Type | Description |
+|--------|------|-------------|
+| id | string | Unique task ID (format: PREFIX-NNN, e.g., MS-SEC-001) |
+| status | enum | not-started, in-progress, done, blocked |
+| description | string | Brief task description with finding ID reference |
+| issue | string | Gitea issue reference (e.g., #337) |
+| repo | string | Target app/package (e.g., api, web, orchestrator) |
+| branch | string | Feature branch for this phase |
+| depends_on | string | Task IDs this depends on (comma-separated) |
+| blocks | string | Task IDs blocked by this (comma-separated) |
+| agent | string | Worker agent identifier (e.g., worker-1) |
+| started_at | ISO8601 | When work began |
+| completed_at | ISO8601 | When work finished |
+| estimate | string | Token estimate (e.g., 15K) |
+| used | string | Actual tokens used (e.g., 12.5K) |
+
+## Status Workflow
+
+  not-started → in-progress → done
+                     ↓
+                  blocked → in-progress (when unblocked)
+
+## Task ID Convention
+
+  {PROJECT_PREFIX}-{PHASE}-{NUMBER}
+
+  Phase prefixes:
+  - SEC: Security (Critical/High)
+  - HIGH: High priority non-security
+  - CQ: Code quality (Medium)
+  - TEST: Test coverage (Low)
+  - PERF: Performance
+  - V01: Verification task
+
+  Examples: MS-SEC-001, MS-HIGH-015, MS-CQ-V01
+-->
+
+| id | status | description | issue | repo | branch | depends_on | blocks | agent | started_at | completed_at | estimate | used |
+|----|--------|-------------|-------|------|--------|------------|--------|-------|------------|--------------|----------|------|
+| ${TASK_PREFIX}-001 | not-started | First task description | ${PHASE_ISSUE} | ${FIRST_REPO} | ${PHASE_BRANCH} | | ${TASK_PREFIX}-002 | | | | | |
+
+<!--
+  Add tasks above this line.
+
+  Dependency rules:
+  1. All Phase N tasks depend on Phase N-1 verification task
+  2. Same-file tasks should be sequential (earlier blocks later)
+  3. Each phase ends with a verification task (e.g., MS-SEC-V01)
+-->