Merge branch 'alpha' into devel

.claude/commands/handoff.md

@@ -0,0 +1,8 @@
+Write a session handoff file for the current session.
+
+Steps:
+1. Read `templates/claude-templates.md` and find the Session Handoff template (Template 4). Use the Light Handoff if this is a small project (under 5 sessions), Full Handoff otherwise.
+2. Fill in every field based on what was accomplished in this session. Be specific — include exact file paths for every output, exact numbers discovered, and conditional logic established.
+3. Write the handoff to `./docs/summaries/handoff-[today's date]-[topic].md`.
+4. If a previous handoff file exists in `./docs/summaries/`, move it to `./docs/archive/handoffs/`.
+5. Tell me the file path of the new handoff and summarize what it contains.

.claude/commands/process-doc.md

@@ -0,0 +1,13 @@
+Process an input document into a structured source summary.
+
+Steps:
+1. Read `templates/claude-templates.md` and find the Source Document Summary template (Template 1). Use the Light Source Summary if this is a small project (under 5 sessions), Full Source Summary otherwise.
+2. Read the document at: $ARGUMENTS
+3. Extract all information into the template format. Pay special attention to:
+   - EXACT numbers — do not round or paraphrase
+   - Requirements in IF/THEN/BUT/EXCEPT format
+   - Decisions with rationale and rejected alternatives
+   - Open questions marked as OPEN, ASSUMED, or MISSING
+4. Write the summary to `./docs/summaries/source-[filename].md`.
+5. Move the original document to `./docs/archive/`.
+6. Tell me: what was extracted, what's unclear, and what needs follow-up.

.claude/commands/status.md

@@ -0,0 +1,13 @@
+Report on the current project state.
+
+Steps:
+1. Read `./docs/summaries/00-project-brief.md` for project context.
+2. Find and read the latest `handoff-*.md` file in `./docs/summaries/` for current state.
+3. List all files in `./docs/summaries/` to understand what's been processed.
+4. Report:
+   - **Project:** name and type from the project brief
+   - **Current phase:** based on the project phase tracker
+   - **Last session:** what was accomplished (from the latest handoff)
+   - **Next steps:** what the next session should do (from the latest handoff)
+   - **Open questions:** anything unresolved
+   - **Summary file count:** how many files in docs/summaries/ (warn if approaching 15)

CLAUDE.md

@@ -0,0 +1,51 @@
+# CLAUDE.md
+
+## Session Start
+
+Read the latest handoff in docs/summaries/ if one exists. Load only the files that handoff references — not all summaries. If no handoff exists, ask: what is the project, what type of work, what is the target deliverable.
+
+Before starting work, state: what you understand the project state to be, what you plan to do this session, and any open questions.
+
+## Identity
+
+You work with Patrick, a Solutions Architect, on the OYS Borrow a Boat (bab-app) project — a Quasar/Vue 3 app for managing a Borrow a Boat program for a Yacht Club. Backend is Appwrite.
+
+## Project Overview
+
+- **App**: OYS Borrow a Boat (oys_bab)
+- **Stack**: Quasar (Vue 3), TypeScript, Appwrite (BaaS)
+- **Purpose**: Manage a Borrow a Boat program for a Yacht Club
+- **Docs**: docs/planning/ contains personas, user/role/permission model, and time-based logic
+
+## Rules
+
+1. Do not mix unrelated project contexts in one session.
+2. Write state to disk, not conversation. After completing meaningful work, write a summary to docs/summaries/ using templates from templates/claude-templates.md. Include: decisions with rationale, exact numbers, file paths, open items.
+3. Before compaction or session end, write to disk: every number, every decision with rationale, every open question, every file path, exact next action.
+4. When switching work types (research → writing → review), write a handoff to docs/summaries/handoff-[date]-[topic].md and suggest a new session.
+5. Do not silently resolve open questions. Mark them OPEN or ASSUMED.
+6. Do not bulk-read documents. Process one at a time: read, summarize to disk, release from context before reading next. For the detailed protocol, read docs/context/processing-protocol.md.
+7. Sub-agent returns must be structured, not free-form prose. Use output contracts from templates/claude-templates.md.
+
+## Where Things Live
+
+- templates/claude-templates.md — summary, handoff, decision, analysis, task, output contract templates (read on demand)
+- docs/summaries/ — active session state (latest handoff + project brief + decision records + source summaries)
+- docs/context/ — reusable domain knowledge, loaded only when relevant to the current task
+  - processing-protocol.md — full document processing steps
+  - archive-rules.md — summary lifecycle and file archival rules
+  - subagent-rules.md — rules for structured sub-agent outputs
+- docs/planning/ — original planning documents (personas, roles/permissions, time logic)
+- docs/archive/ — processed raw files. Do not read unless explicitly told.
+- output/deliverables/ — final outputs
+- src/ — Quasar/Vue app source
+- src-pwa/ — PWA config
+- appwrite.json — Appwrite project config
+
+## Error Recovery
+
+If context degrades or auto-compact fires unexpectedly: write current state to docs/summaries/recovery-[date].md, tell the user what may have been lost, suggest a fresh session.
+
+## Before Delivering Output
+
+Verify: exact numbers preserved, open questions marked OPEN, output matches what was requested (not assumed), claims backed by specific data, output consistent with stored decisions in docs/context/, summary written to disk for this session's work.

docs/context/archive-rules.md

@@ -0,0 +1,16 @@
+# Archive Rules
+
+## Raw File Archival
+
+After creating a Source Document Summary for any raw file:
+1. Move the raw file to `docs/archive/`
+2. Record the move in the source summary's header: `Archived From: [original path]`
+3. Do not read from `docs/archive/` unless the user explicitly says "go back to the original [filename]"
+
+## Summary Lifecycle Rules
+
+1. **Session handoffs expire**: After a new handoff is written, the previous handoff moves to `docs/archive/handoffs/`. Only the latest handoff stays in `docs/summaries/`.
+2. **Decision records persist**: Decision records (DR-*) stay in `docs/summaries/` permanently — they are institutional memory.
+3. **Source summaries persist**: Source document summaries stay until the project ends — they replace raw documents.
+4. **Analysis summaries**: Keep only the latest version. If re-run, the new one replaces the old (archive the old one).
+5. **Maximum active summaries**: If `docs/summaries/` exceeds 15 files, consolidate older source summaries into a single `project-digest.md` and archive the originals.

docs/context/processing-protocol.md

@@ -0,0 +1,23 @@
+# Document Processing Protocol
+
+Use this whenever you need to process multiple documents or large files.
+
+## For 1-3 Short Documents (< 2K words each)
+
+Read sequentially. After each document, write a Source Document Summary (Template 1 from `templates/claude-templates.md`) to disk. Then proceed with work using summaries only.
+
+## For 4+ Documents OR Any Document > 2K Words
+
+**Step 1:** List all documents with file sizes. Present to user for prioritization.
+
+**Step 2:** Process each document individually:
+- Read one document
+- Extract into Source Document Summary format
+- Write to `./docs/summaries/source-[filename].md`
+- Release the document from active consideration before reading the next
+
+**Step 3:** After all documents are processed, read only the summaries to form your working context.
+
+**Step 4:** Cross-reference summaries for contradictions or dependencies. Note these explicitly.
+
+**Step 5:** Proceed with the actual task using summaries as your reference.

docs/context/subagent-rules.md

@@ -0,0 +1,18 @@
+# Subagent Deployment Rules
+
+## When to Use Subagent vs. Main Agent
+
+| Situation | Approach | Why |
+|-----------|----------|-----|
+| Reading/analyzing documents | Subagent | Keeps source content out of main context |
+| Research and competitive analysis | Subagent | Heavy reading, return summary only |
+| Writing deliverables | Main agent | Needs full decision-making context |
+| Schema/architecture design | Main agent | Needs holistic project understanding |
+| Code generation | Subagent | Isolated implementation, return result |
+| Review and QA | Subagent | Fresh perspective, no bias from writing |
+
+## Output Requirements
+
+Subagent output must conform to the Output Contracts in `templates/claude-templates.md`. No free-form prose returns.
+
+Optimal subagent return size: 1,000-2,000 tokens of structured summary. Longer returns consume main agent context without proportional benefit.

src/layouts/MainLayout.vue

@@ -1,5 +1,6 @@
 <template>
   <q-layout view="hHh Lpr fFf">
+    <ToolbarComponent :pageTitle="route.meta.title as string" />
     <q-page-container>
       <router-view />
     </q-page-container>
@@ -11,9 +12,12 @@
 
 <script setup lang="ts">
 import { useQuasar } from 'quasar';
+import { useRoute } from 'vue-router';
 import BottomNavComponent from 'src/components/BottomNavComponent.vue';
+import ToolbarComponent from 'src/components/ToolbarComponent.vue';
 
 const q = useQuasar();
+const route = useRoute();
 // q.fullscreen.request();
 q.addressbarColor.set('#14539a');
 </script>

src/pages/IndexPage.vue

@@ -1,5 +1,4 @@
 <template>
-  <ToolbarComponent />
   <q-page class="row justify-center">
     <q-img alt="OYS Logo" src="~assets/oysqn_logo.png" fit="scale-down" />
     <q-list class="full-width mobile-only">
@@ -24,5 +23,4 @@
 
 <script lang="ts" setup>
 import { enabledLinks } from 'src/router/navlinks.js';
-import ToolbarComponent from 'components/ToolbarComponent.vue';
 </script>

src/pages/ProfilePage.vue

@@ -1,5 +1,4 @@
 <template>
-  <toolbar-component pageTitle="Member Profile" />
   <q-page
     padding
     class="row">
@@ -76,7 +75,6 @@
 </template>
 
 <script setup lang="ts">
-import ToolbarComponent from 'src/components/ToolbarComponent.vue';
 import { useAuthStore } from 'src/stores/auth';
 import { ref } from 'vue';
 

src/pages/schedule/BoatReservationPage.vue

@@ -1,5 +1,7 @@
 <template>
+  <q-page>
     <BoatReservationComponent v-model="newReservation" />
+  </q-page>
 </template>
 
 <script setup lang="ts">

src/pages/schedule/ListReservationsPage.vue

@@ -1,4 +1,5 @@
 <template>
+  <q-page>
   <q-tabs
     v-model="tab"
     inline-label
@@ -57,6 +58,7 @@
       </div>
     </q-tab-panel>
   </q-tab-panels>
+  </q-page>
 </template>
 <script setup lang="ts">
 import { useReservationStore } from 'src/stores/reservation';

src/pages/schedule/ManageCalendar.vue

@@ -126,7 +126,6 @@
           :model-value="template" />
       </q-list>
     </div>
-  </div>
     <q-dialog v-model="alert">
       <q-card>
         <q-card-section>
@@ -151,6 +150,7 @@
         </q-card-actions>
       </q-card>
     </q-dialog>
+  </div>
 </template>
 
 <script setup lang="ts">
@@ -208,8 +208,8 @@ const filteredIntervals = (date: Timestamp, boat: Boat) => {
 const sortedIntervals = (date: Timestamp, boat: Boat) => {
   return computed(() =>
     filteredIntervals(date, boat).value.sort(
-      (a, b) => Date.parse(a.start) - Date.parse(b.start)
-    )
+      (a, b) => Date.parse(a.start) - Date.parse(b.start),
+    ),
   );
 };
 
@@ -235,14 +235,14 @@ function getIntervals(date: Timestamp, boat: Boat) {
 function intervalsFromTemplate(
   boat: Boat,
   templateId: string,
-  date: string
+  date: string,
 ): Interval[] {
   const template = intervalTemplateStore
     .getIntervalTemplates()
     .value.find((t) => t.$id === templateId);
   return template
     ? template.timeTuples.map((timeTuple: TimeTuple) =>
-        buildInterval(boat, timeTuple, date)
+        buildInterval(boat, timeTuple, date),
       )
     : [];
 }
@@ -279,7 +279,7 @@ function onDrop(
   //TODO: Move all overlap checking to the store.  This is too messy right now.
   e: DragEvent,
   type: string,
-  scope: { resource: Boat; timestamp: Timestamp }
+  scope: { resource: Boat; timestamp: Timestamp },
 ) {
   if (e.target instanceof HTMLDivElement)
     e.target.classList.remove('bg-secondary');
@@ -294,9 +294,9 @@ function onDrop(
       .map((boat) =>
         intervalsOverlapped(
           existingIntervals.value.concat(
-            intervalsFromTemplate(boat, templateId, date)
-          )
-        )
+            intervalsFromTemplate(boat, templateId, date),
+          ),
+        ),
       )
       .flat(1);
     if (overlapped.value.length === 0) {

src/pages/schedule/ModifyBoatReservation.vue

@@ -1,5 +1,7 @@
 <template>
+  <q-page>
     <BoatReservationComponent v-model="reservation" />
+  </q-page>
 </template>
 
 <script setup lang="ts">

src/pages/schedule/SchedulePageView.vue

@@ -1,8 +1,6 @@
 <template>
-  <toolbar-component pageTitle="Schedule" />
   <router-view />
 </template>
 
 <script setup lang="ts">
-import ToolbarComponent from 'src/components/ToolbarComponent.vue';
 </script>

src/router/routes.ts

@@ -13,16 +13,19 @@ const routes: RouteRecordRaw[] = [
         // component: () => import('pages/IndexPage.vue'),
         component: () => import('src/pages/IndexPage.vue'),
         name: 'index',
+        meta: { title: 'OYS Borrow a Boat' },
       },
       {
         path: '/boat',
         component: () => import('src/pages/BoatPage.vue'),
         name: 'boat',
+        meta: { title: 'Boats' },
       },
       {
         path: '/schedule',
         component: () => import('pages/schedule/SchedulePageView.vue'),
         name: 'schedule',
+        meta: { title: 'Schedule' },
         children: [
           {
             path: '',
@@ -64,10 +67,12 @@ const routes: RouteRecordRaw[] = [
         path: '/certification',
         component: () => import('src/pages/CertificationPage.vue'),
         name: 'certification',
+        meta: { title: 'Certifications' },
       },
       {
         path: '/task',
         name: 'task',
+        meta: { title: 'Tasks' },
         children: [
           {
             path: '',
@@ -85,16 +90,19 @@ const routes: RouteRecordRaw[] = [
         path: '/checklist',
         component: () => import('pages/ChecklistPage.vue'),
         name: 'checklist',
+        meta: { title: 'Checklist' },
       },
       {
         path: '/profile',
         component: () => import('src/pages/ProfilePage.vue'),
         name: 'profile',
+        meta: { title: 'Member Profile' },
       },
       {
         path: '/reference',
         component: () => import('src/pages/reference/ReferencePage.vue'),
         name: 'reference',
+        meta: { title: 'Reference' },
         children: [
           {
             path: '',
@@ -103,7 +111,7 @@ const routes: RouteRecordRaw[] = [
             name: 'reference-index',
           },
           {
-            path: '/reference/:id/view',
+            path: 'reference/:id/view',
             component: () =>
               import('src/pages/reference/ReferenceItemPage.vue'),
           },
@@ -117,12 +125,12 @@ const routes: RouteRecordRaw[] = [
     meta: { requiredRoles: ['admin'] },
     children: [
       {
-        path: '/user',
+        path: 'user',
         component: () => import('pages/admin/UserAdminPage.vue'),
         name: 'useradmin',
       },
       {
-        path: '/boat',
+        path: 'boat',
         component: () => import('pages/admin/BoatAdminPage.vue'),
         name: 'boatadmin',
       },
@@ -144,14 +152,6 @@ const routes: RouteRecordRaw[] = [
       publicRoute: true,
     },
   },
-  {
-    path: '/login',
-    component: () => import('pages/LoginPage.vue'),
-    name: 'login',
-    meta: {
-      publicRoute: true,
-    },
-  },
   {
     path: '/terms-of-service',
     component: () => import('pages/TermsOfServicePage.vue'),

src/stores/auth.ts

@@ -100,7 +100,7 @@ export const useAuthStore = defineStore('auth', () => {
   }
 
   function logout() {
-    return account.deleteSession('current').then((currentUser.value = null));
+    return account.deleteSession('current').then(() => { currentUser.value = null; });
   }
 
   async function updateName(name: string) {

src/stores/reference.ts

@@ -113,7 +113,7 @@ export const useReferenceStore = defineStore('reference', {
 
   getters: {
     getCategory(state) {
-      (category: string) => {
+      return (category: string) => {
         return state.allItems.filter((c) => c.category === category);
       };
     },

templates/claude-templates.md

@@ -0,0 +1,490 @@
+# Claude Templates — On-Demand Reference
+
+> **Do NOT read this file at session start.** Read it only when you need to write a summary, handoff, decision record, or subagent output. This file is referenced from CLAUDE.md.
+
+---
+
+## Template 1: Source Document Summary
+
+**Use when:** Processing any input document (client brief, research report, requirements doc, existing proposal)
+
+**Write to:** `./docs/summaries/source-[filename].md`
+
+```markdown
+# Source Summary: [Original Document Name]
+**Processed:** [YYYY-MM-DD]
+**Source Path:** [exact file path]
+**Archived From:** [original path, if moved to docs/archive/]
+**Document Type:** [brief / requirements / research / proposal / transcript / other]
+**Confidence:** [high = I understood everything / medium = some interpretation needed / low = significant gaps]
+
+## Exact Numbers & Metrics
+<!-- List EVERY specific number, dollar amount, percentage, date, count, measurement.
+     Do NOT round. Do NOT paraphrase. Copy exactly as stated in source. -->
+- [metric]: [exact value] (page/section reference if available)
+- [metric]: [exact value]
+
+## Key Facts (Confirmed)
+<!-- Only include facts explicitly stated in the document. Tag source. -->
+- [fact] — stated in [section/page]
+- [fact] — stated in [section/page]
+
+## Requirements & Constraints
+<!-- Use IF/THEN/BUT/EXCEPT format to preserve conditional logic -->
+- REQUIREMENT: [what is needed]
+  - CONDITION: [when/if this applies]
+  - CONSTRAINT: [limitation or exception]
+  - PRIORITY: [must-have / should-have / nice-to-have / stated by whom]
+
+## Decisions Referenced
+<!-- Any decisions mentioned in the document -->
+- DECISION: [what was decided]
+  - RATIONALE: [why, as stated in document]
+  - ALTERNATIVES MENTIONED: [what else was considered]
+  - DECIDED BY: [who, if stated]
+
+## Relationships to Other Documents
+<!-- How this document connects to other known project documents -->
+- SUPPORTS: [other document/decision it reinforces]
+- CONTRADICTS: [other document/decision it conflicts with]
+- DEPENDS ON: [other document/decision it requires]
+- UPDATES: [other document/decision it supersedes]
+
+## Open Questions & Ambiguities
+<!-- Things that are NOT resolved in this document -->
+- UNCLEAR: [what is ambiguous] — needs clarification from [whom]
+- ASSUMED: [interpretation made] — verify with [whom]
+- MISSING: [information referenced but not provided]
+
+## Verbatim Quotes Worth Preserving
+<!-- 2-5 direct quotes that capture stakeholder language, priorities, or constraints
+     These are critical for proposals — use the client's own words back to them -->
+- "[exact quote]" — [speaker/author], [context]
+```
+
+---
+
+## Template 2: Analysis / Research Summary
+
+**Use when:** Completing competitive analysis, market research, technical evaluation
+
+**Write to:** `./docs/summaries/analysis-[topic].md`
+
+```markdown
+# Analysis Summary: [Topic]
+**Completed:** [YYYY-MM-DD]
+**Analysis Type:** [competitive / market / technical / financial / feasibility]
+**Sources Used:** [list source paths or URLs]
+**Confidence:** [high / medium / low — and WHY this confidence level]
+
+## Core Finding (One Sentence)
+[Single sentence: the most important conclusion]
+
+## Evidence Base
+<!-- Specific data points supporting the finding. Exact numbers only. -->
+| Data Point | Value | Source | Date of Data |
+|-----------|-------|--------|-------------|
+| [metric]  | [exact value] | [source] | [date] |
+
+## Detailed Findings
+### Finding 1: [Name]
+- WHAT: [the finding]
+- SO WHAT: [why it matters for this project]
+- EVIDENCE: [specific supporting data]
+- CONFIDENCE: [high/medium/low]
+
+### Finding 2: [Name]
+[same structure]
+
+## Conditional Conclusions
+<!-- Use IF/THEN format -->
+- IF [condition], THEN [conclusion], BECAUSE [evidence]
+- IF [alternative condition], THEN [different conclusion]
+
+## What This Analysis Does NOT Cover
+<!-- Explicit scope boundaries to prevent future sessions from over-interpreting -->
+- [topic not addressed and why]
+- [data not available]
+
+## Recommended Next Steps
+1. [action] — priority [high/medium/low], depends on [what]
+2. [action]
+```
+
+---
+
+## Template 3: Decision Record
+
+**Use when:** Any significant decision is made during a session
+
+**Write to:** `./docs/summaries/decision-[number]-[topic].md`
+
+```markdown
+# Decision Record: [Short Title]
+**Decision ID:** DR-[sequential number]
+**Date:** [YYYY-MM-DD]
+**Status:** CONFIRMED / PROVISIONAL / REQUIRES_VALIDATION
+
+## Decision
+[One clear sentence: what was decided]
+
+## Context
+[2-3 sentences: what situation prompted this decision]
+
+## Rationale
+- CHOSE [option] BECAUSE: [specific reasons with data]
+- REJECTED [alternative 1] BECAUSE: [specific reasons]
+- REJECTED [alternative 2] BECAUSE: [specific reasons]
+
+## Quantified Impact
+- [metric affected]: [expected change with numbers]
+- [cost/time/resource implication]: [specific figures]
+
+## Conditions & Constraints
+- VALID IF: [conditions under which this decision holds]
+- REVISIT IF: [triggers that should cause reconsideration]
+- DEPENDS ON: [upstream decisions or facts this relies on]
+
+## Stakeholder Input
+- [name/role]: [their stated position, if known]
+
+## Downstream Effects
+- AFFECTS: [what other decisions, documents, or deliverables this impacts]
+- REQUIRES UPDATE TO: [specific files or deliverables that need revision]
+```
+
+---
+
+## Template 4: Session Handoff
+
+**Use when:** A session is ending (context limit approaching OR phase complete)
+
+**Write to:** `./docs/summaries/handoff-[YYYY-MM-DD]-[topic].md`
+
+**LIFECYCLE**: After writing a new handoff, move the PREVIOUS handoff to `docs/archive/handoffs/`.
+
+```markdown
+# Session Handoff: [Topic]
+**Date:** [YYYY-MM-DD]
+**Session Duration:** [approximate]
+**Session Focus:** [one sentence]
+**Context Usage at Handoff:** [estimated percentage if known]
+
+## What Was Accomplished
+<!-- Be specific. Include file paths for every output. -->
+1. [task completed] → output at `[file path]`
+2. [task completed] → output at `[file path]`
+
+## Exact State of Work in Progress
+<!-- If anything is mid-stream, describe exactly where it stopped -->
+- [work item]: completed through [specific point], next step is [specific action]
+- [work item]: blocked on [specific issue]
+
+## Decisions Made This Session
+<!-- Reference decision records if created, otherwise summarize here -->
+- DR-[number]: [decision] (see `./docs/summaries/decision-[file]`)
+- [Ad-hoc decision]: [what] BECAUSE [why] — STATUS: [confirmed/provisional]
+
+## Key Numbers Generated or Discovered This Session
+<!-- Every metric, estimate, or figure produced. Exact values. -->
+- [metric]: [value] — [context for where/how this was derived]
+
+## Conditional Logic Established
+<!-- Any IF/THEN/BUT/EXCEPT reasoning that future sessions must respect -->
+- IF [condition] THEN [approach] BECAUSE [rationale]
+
+## Files Created or Modified
+| File Path | Action | Description |
+|-----------|--------|-------------|
+| `[path]`  | Created | [what it contains] |
+| `[path]`  | Modified | [what changed and why] |
+
+## What the NEXT Session Should Do
+<!-- Ordered, specific instructions. The next session starts by reading this. -->
+1. **First**: [specific action with file paths]
+2. **Then**: [specific action]
+3. **Then**: [specific action]
+
+## Open Questions Requiring User Input
+<!-- Do NOT proceed on these without explicit user confirmation -->
+- [ ] [question] — impacts [what downstream deliverable]
+- [ ] [question]
+
+## Assumptions That Need Validation
+<!-- Things treated as true this session but not confirmed -->
+- ASSUMED: [assumption] — validate by [method/person]
+
+## What NOT to Re-Read
+<!-- Prevent the next session from wasting context on already-processed material -->
+- `[file path]` — already summarized in `[summary file path]`
+
+## Files to Load Next Session
+<!-- Explicit index of what the next session should read. Acts as progressive disclosure index layer. -->
+- `[file path]` — needed for [reason]
+- `[file path]` — needed for [reason]
+```
+
+---
+
+## Template 5: Project Brief (Initial Setup)
+
+**Use when:** Creating the 00-project-brief.md at project start
+
+**Write to:** `./docs/summaries/00-project-brief.md`
+
+```markdown
+# Project Brief: [Project Name]
+**Created:** [YYYY-MM-DD]
+**Last Updated:** [YYYY-MM-DD]
+
+## Client
+- **Name:** [client name]
+- **Industry:** [industry]
+- **Size:** [employee count / revenue if known]
+- **Relationship:** [through AutomatonsX / Lagrange Data / direct / other]
+- **Key Contacts:** [names and roles if known]
+
+## Engagement
+- **Type:** [proposal / workshop / competitive analysis / agent development / hybrid]
+- **Scope:** [one paragraph description]
+- **Target Deliverable:** [specific output expected]
+- **Timeline:** [deadline if known]
+- **Budget Context:** [if known — exact figures]
+
+## Input Documents
+| Document | Path | Processed? | Summary At |
+|----------|------|-----------|------------|
+| [name]   | `[path]` | Yes/No | `[summary path]` |
+
+## Success Criteria
+- [criterion 1]
+- [criterion 2]
+
+## Known Constraints
+- [constraint 1]
+- [constraint 2]
+
+## Project Phase Tracker
+| Phase | Status | Summary File | Date |
+|-------|--------|-------------|------|
+| Discovery | Not Started / In Progress / Complete | `[path]` | |
+| Strategy | Not Started / In Progress / Complete | `[path]` | |
+| Deliverable Draft | Not Started / In Progress / Complete | `[path]` | |
+| Review & Polish | Not Started / In Progress / Complete | `[path]` | |
+```
+
+---
+
+## Template 6: Task Definition
+
+**Use when:** Defining a discrete unit of work before starting execution
+
+```markdown
+## Task: [name]
+**Date:** [YYYY-MM-DD]
+**Client:** [if applicable]
+**Work Type:** [proposal / workshop / analysis / content / agent development]
+
+### Context Files to Load
+- `[file path]` — [why needed]
+
+### Action
+[What to produce. Be specific about format, length, and scope.]
+
+### Verify
+- [ ] Numbers match source data exactly
+- [ ] Open questions marked OPEN
+- [ ] Output matches what was requested, not what was assumed
+- [ ] Claims backed by specific data
+- [ ] Consistent with stored decisions in docs/context/
+
+### Done When
+- [ ] Output file exists at `[specific path]`
+- [ ] Summary written to `docs/summaries/[specific file]`
+```
+
+---
+
+## Subagent Output Contracts
+
+**CRITICAL: When subagents return results to the main agent, unstructured prose causes information loss. These output contracts define the EXACT format subagents must return.**
+
+### Contract for Document Analysis Subagent
+
+```
+=== DOCUMENT ANALYSIS OUTPUT ===
+SOURCE: [file path]
+TYPE: [document type]
+CONFIDENCE: [high/medium/low]
+
+NUMBERS:
+- [metric]: [exact value]
+[repeat for all numbers found]
+
+REQUIREMENTS:
+- REQ: [requirement] | CONDITION: [if any] | PRIORITY: [level] | CONSTRAINT: [if any]
+[repeat]
+
+DECISIONS_REFERENCED:
+- DEC: [what] | WHY: [rationale] | BY: [who]
+[repeat]
+
+CONTRADICTIONS:
+- [this document says X] CONTRADICTS [other known fact Y]
+[repeat or NONE]
+
+OPEN:
+- [unresolved item] | NEEDS: [who/what to resolve]
+[repeat or NONE]
+
+QUOTES:
+- "[verbatim]" — [speaker], [context]
+[repeat, max 5]
+
+=== END OUTPUT ===
+```
+
+### Contract for Research/Analysis Subagent
+
+```
+=== RESEARCH OUTPUT ===
+QUERY: [what was researched]
+SOURCES: [list]
+CONFIDENCE: [high/medium/low] BECAUSE [reason]
+
+CORE_FINDING: [one sentence]
+
+EVIDENCE:
+- [data point]: [exact value] | SOURCE: [where] | DATE: [when]
+[repeat]
+
+CONCLUSIONS:
+- IF [condition] THEN [conclusion] | EVIDENCE: [reference]
+[repeat]
+
+GAPS:
+- [what was not found or not covered]
+[repeat or NONE]
+
+NEXT_STEPS:
+- [recommended action] | PRIORITY: [level]
+[repeat]
+
+=== END OUTPUT ===
+```
+
+### Contract for Review/QA Subagent
+
+```
+=== REVIEW OUTPUT ===
+REVIEWED: [file path or deliverable name]
+AGAINST: [what standard — spec, requirements, style guide]
+
+PASS: [yes/no/partial]
+
+ISSUES:
+- SEVERITY: [critical/major/minor] | ITEM: [description] | LOCATION: [where in document] | FIX: [suggested resolution]
+[repeat]
+
+MISSING:
+- [expected content/section not found] | REQUIRED_BY: [which requirement]
+[repeat or NONE]
+
+INCONSISTENCIES:
+- [item A says X] BUT [item B says Y] | RESOLUTION: [suggested]
+[repeat or NONE]
+
+STRENGTHS:
+- [what works well — for positive reinforcement in iteration]
+[max 3]
+
+=== END OUTPUT ===
+```
+
+---
+
+## Phase-Based Workflow Templates
+
+### Template A: Enterprise Sales Deliverable
+
+```
+Phase 1: Discovery & Input Processing
+├── Process all client documents → Source Document Summaries
+├── Identify gaps in information → flag as OPEN items
+├── Create Decision Records for any choices made
+├── Write: ./docs/summaries/01-discovery-complete.md (Handoff Template)
+├── → Suggest new session for Phase 2
+
+Phase 2: Strategy & Positioning
+├── Read summaries only (NOT source documents)
+├── Competitive positioning analysis → Analysis Summary
+├── Value proposition development
+├── ROI framework construction with EXACT numbers
+├── Write: ./docs/summaries/02-strategy-complete.md (Handoff Template)
+├── → Suggest new session for Phase 3
+
+Phase 3: Deliverable Creation
+├── Read strategy summary + project brief only
+├── Draft deliverable (proposal / deck / workshop plan)
+├── Output to: ./output/deliverables/
+├── Write: ./docs/summaries/03-deliverable-draft.md (Handoff Template)
+├── → Suggest new session for Phase 4
+
+Phase 4: Review & Polish
+├── Read draft deliverable + strategy summary
+├── Quality review using Review/QA Output Contract
+├── Final edits and formatting
+├── Output final version to: ./output/deliverables/
+```
+
+### Template B: Agent/Application Development
+
+```
+Phase 1: Requirements → Spec
+├── Process all input documents → Source Document Summaries
+├── Generate structured specification
+├── Output: ./output/SPEC.md
+├── Write: ./docs/summaries/01-spec-complete.md (Handoff Template)
+├── → Suggest new session for Phase 2
+
+Phase 2: Architecture → Schema
+├── Read SPEC.md + summaries only
+├── Design data model
+├── Define agent behaviors and workflows
+├── Output: ./output/schemas/data-model.yaml
+├── Output: ./output/schemas/agent-definitions.yaml
+├── Write: ./docs/summaries/02-architecture-complete.md (Handoff Template)
+├── → Suggest new session for Phase 3
+
+Phase 3: Prompts → Integration
+├── Read schemas + spec only
+├── Write system prompts for each agent
+├── Map API integrations and data flows
+├── Output: ./output/prompts/[agent-name].md (one per agent)
+├── Output: ./output/schemas/integration-map.yaml
+├── Write: ./docs/summaries/03-prompts-complete.md (Handoff Template)
+├── → Suggest new session for Phase 4
+
+Phase 4: Assembly → Package
+├── Read all output files
+├── Assemble complete application package
+├── Generate deployment/setup instructions
+├── Output: ./output/deliverables/[project]-complete-package/
+├── QA check against original spec using Review/QA Output Contract
+```
+
+### Template C: Hybrid (Sales + Agent Development)
+
+```
+Phase 1: Client Discovery → Summaries
+Phase 2: Solution Design → Architecture + Schema
+Phase 3a: Client-Facing Deliverable (proposal/deck)
+Phase 3b: Internal Technical Package (schemas/prompts)
+Phase 4: Review both tracks against each other for consistency
+```
+
+---
+
+## End of Templates
+
+**Return to your task after reading the template(s) you need. Do not keep this file in active context.**