wayfind 0.0.1 → 2.0.0

package/specializations/cursor/README.md

@@ -0,0 +1,120 @@
+# Cursor Integration — Wayfind
+
+Full setup guide for Cursor users.
+
+## Quick Setup
+
+Install Wayfind globally, then run the Cursor initializer:
+```bash
+npm install -g wayfind
+wayfind init-cursor
+```
+
+Or use the shell installer directly: `bash setup.sh --tool cursor`. Manual steps below.
+
+## How It Works
+
+Cursor injects rule files into the AI context at session start. The memory kit hooks into this system to load your state files automatically.
+
+### Memory Directory
+
+The Cursor specialization uses `~/.ai-memory/` as the memory root (tool-agnostic, not tied to Cursor's config location):
+
+```
+~/.ai-memory/
+  global.md              # Always loaded — thin index of all state
+  state.md               # Admin/non-repo work
+  memory/
+    <topic>.md           # Loaded on demand
+    journal/
+      YYYY-MM-DD.md      # Daily session log
+```
+
+### Per-Repo Files
+
+```
+<repo>/.cursor/
+  rules/
+    memory.mdc           # Repo-level memory rules (committed to git)
+```
+
+### Session Flow
+
+**Session start:** Cursor reads `.cursor/rules/memory.mdc` → AI loads `~/.ai-memory/global.md` + repo state
+
+**Session end (manual):** Say "done for today, update state files" — the AI updates the state files and appends a journal entry
+
+## Setup
+
+### Step 1: Memory directory
+
+```bash
+mkdir -p ~/.ai-memory/memory/journal
+```
+
+### Step 2: Global index
+
+```bash
+cp templates/global.md ~/.ai-memory/global.md
+# Edit with your preferences, projects, team context
+```
+
+### Step 3: Global Cursor rules
+
+Cursor supports global rules in `~/.cursor/rules/`. Create the memory rule:
+
+```bash
+mkdir -p ~/.cursor/rules
+cp specializations/cursor/global-rule.mdc ~/.cursor/rules/ai-memory.mdc
+```
+
+### Step 4: Initialize a repo
+
+In any repo you work in with Cursor, run:
+
+```bash
+bash setup.sh --tool cursor --repo .
+# Or manually:
+mkdir -p .cursor/rules
+cp specializations/cursor/repo-rule.mdc .cursor/rules/memory.mdc
+```
+
+Edit `.cursor/rules/memory.mdc` to reflect the repo name and what it's about.
+
+### Step 5: Fill in your global index
+
+Open `~/.ai-memory/global.md` and fill in:
+- Your preferences and working style
+- Active projects table
+- Team context (using the examples as a guide)
+
+## Session End Triggers
+
+Since Cursor has no native hooks, use these natural language triggers to end a session:
+
+- "done for today" — triggers state file updates + journal entry
+- "stop, update memory" — same
+- "save session state" — same
+
+The rule file instructs the AI to perform all updates when it hears these phrases.
+
+## What Gets Committed
+
+- `.cursor/rules/memory.mdc` — **commit this** (shared context for any AI tool that reads the repo)
+- `~/.ai-memory/` files — **never commit** (personal memory, lives outside the repo)
+
+## Limitations vs. Claude Code
+
+| Feature | Claude Code | Cursor |
+|---------|------------|--------|
+| Auto session-start | ✓ Hook fires automatically | ✓ Rule file injected automatically |
+| Auto session-end | ✓ Hook triggers on stop | ✗ Manual trigger required |
+| `/init-memory` command | ✓ | ✗ Use `wayfind init-cursor` or `setup.sh --tool cursor --repo .` |
+| Team commands (`/init-team`) | ✓ | ✗ Not available |
+| Context sync | ✓ | ✗ Not available |
+| Deploy | ✓ | ✗ Not available |
+| Bot | ✓ | ✗ Not available |
+| Digest reactions | ✓ | ✗ Not available |
+| Telemetry | ✓ (opt-in) | ✗ Not available |
+| Prompts | ✓ | ✗ Not available |
+| Global memory path | `~/.claude/` | `~/.ai-memory/` |

package/specializations/cursor/global-rule.mdc

@@ -0,0 +1,53 @@
+---
+description: Wayfind — Session Protocol (Global)
+alwaysApply: true
+---
+
+## Session State Protocol
+
+**Memory system:** Hierarchical plain-markdown files at `~/.ai-memory/`. No CLI tools, no databases.
+
+### File Hierarchy
+
+```
+~/.ai-memory/
+  global.md            # Thin index — ALWAYS load at session start
+  state.md             # Admin/non-repo work
+  memory/              # Topic files — load on demand
+    <topic>.md
+    journal/YYYY-MM-DD.md  # Daily log
+```
+
+### Session Start (REQUIRED)
+
+1. Read `~/.ai-memory/global.md`
+2. Read `.cursor/rules/memory.mdc` in the current repo for repo-specific context
+3. Check the Memory Files table in `global.md` — load any `~/.ai-memory/memory/` files whose keywords match this session's topic
+4. Summarize current state, then ask: **"What's the goal for this session? What does success look like?"**
+
+### Mid-Session
+
+If work drifts from the stated goal, flag it: *"Quick check — we set out to [goal]. This feels like [tangent]. Stay the course or pivot?"*
+
+### Session End Triggers
+
+When the user says "done", "stop", "done for today", "save session state", or "update memory":
+
+1. Update `<repo>/.cursor/rules/memory.mdc` with current branch, status, next steps
+2. Update the Active Projects row in `~/.ai-memory/global.md`
+3. Create/update topic files in `~/.ai-memory/memory/` for significant new cross-repo context
+4. Append to `~/.ai-memory/memory/journal/YYYY-MM-DD.md`:
+   ```
+   ## [Repo] — [Title]
+   **Why:** [Stated goal]
+   **What:** [What was done]
+   **Outcome:** [Did we hit it?]
+   **On track?:** [Focused or drift?]
+   **Lessons:** [Cross-session learnings]
+   ```
+5. Confirm: **"State saved. Say 'let's continue' next time."**
+
+### Rules
+
+- Keep `global.md` under 80 lines. Detail goes in `~/.ai-memory/memory/` files.
+- Do NOT use any CLI memory tools — plain markdown files only.

package/specializations/cursor/repo-rule.mdc

@@ -0,0 +1,25 @@
+---
+description: Wayfind — Repo State ([REPO_NAME])
+alwaysApply: true
+---
+
+## Repo State: [REPO_NAME]
+
+Last updated: YYYY-MM-DD
+
+### Current Branch
+[branch]
+
+### Current Status
+[what's happening in this repo]
+
+### What's Next
+[concrete next action]
+
+### Gotchas
+[anything to know before diving in]
+
+---
+
+*This file is maintained by the AI. Update it at session end.*
+*Global memory lives at `~/.ai-memory/global.md`.*

package/specializations/generic/README.md

@@ -0,0 +1,47 @@
+# Generic Specialization
+## Any AI Tool with System Prompt Support
+
+If your tool doesn't have a file-based instruction system, you can still use this kit by pasting the session protocol into your system prompt or the beginning of each conversation.
+
+## Option 1: System Prompt Injection
+
+Paste the contents of `../../templates/session-protocol-fragment.md` into your tool's system prompt field. Adjust the memory directory path from `~/.ai-memory/` to wherever you want to store the files.
+
+## Option 2: Conversation Starter
+
+If your tool has no persistent system prompt, start each session with:
+
+```
+Before we begin: read ~/.ai-memory/global.md and .ai-memory/state.md in this repo.
+Summarize where we left off, then ask what the goal is for this session.
+```
+
+## Memory Directory
+
+Use `~/.ai-memory/` as a tool-neutral memory root:
+
+```bash
+mkdir -p ~/.ai-memory/memory/journal
+cp ../../templates/global.md ~/.ai-memory/global.md
+```
+
+## Session End
+
+Since there are no hooks, you must explicitly trigger the state update:
+
+> "We're done for today. Please update the state files."
+
+The AI will update `.ai-memory/state.md` and append to the journal. Do NOT update `~/.ai-memory/global.md` at session end — it is rebuilt automatically by `wayfind status`.
+
+## Limitations
+
+- No automatic session-start file loading (must be in system prompt or triggered manually)
+- No hook support for automation
+- No custom commands
+
+## What Still Works
+
+- All the file templates
+- The protocol itself (session goals, drift checks, journal)
+- Topic memory files
+- Cross-session continuity (as long as the AI reads the files)

package/templates/autopilot/design.md

@@ -0,0 +1,22 @@
+# Design Persona — Autopilot Prompt
+
+You are the Design persona for this team. You scan session journals and signal data to surface what a design lead needs to know — and nothing else.
+
+## Your job
+
+Find the 5 most consequential design items from this period. "Consequential" means: UX consistency broke, user-facing changes shipped without design review, accessibility regressed, or design debt is accumulating in a way that will compound.
+
+## Rules
+
+- **Maximum 5 items.** If fewer than 5 things matter, output fewer. Never pad.
+- **Rank by consequence, not category.** Lead with the item that most affects user experience.
+- **No category headers.** No "UX Consistency" / "Accessibility" sections. Just a ranked list.
+- **Each item: bold headline + one sentence of context.** The headline should make someone stop scrolling. The context sentence explains what the user impact is or what needs design attention.
+- **Include the "so what?"** Don't just state facts — say what breaks for the user or what gets harder to fix later.
+- **Skip anything routine.** If the UI change is minor and consistent, it's not digest-worthy.
+- **Reference specifics** — features, screens, PRs, interaction patterns.
+- **Do not include a title or header line.** The digest system adds its own header.
+
+## Tone
+
+Write for someone scrolling Slack on their phone. Observational, specific, zero filler. Every word earns its place.

package/templates/autopilot/engineering.md

@@ -0,0 +1,22 @@
+# Engineering Persona — Autopilot Prompt
+
+You are the Engineering persona for this team. You scan session journals and signal data to surface what an engineering lead needs to know — and nothing else.
+
+## Your job
+
+Find the 5 most consequential engineering items from this period. "Consequential" means: something broke, something risky shipped, a pattern is forming that will bite us, or a decision was made that the team should know about.
+
+## Rules
+
+- **Maximum 5 items.** If fewer than 5 things matter, output fewer. Never pad.
+- **Rank by consequence, not category.** Lead with the most surprising or highest-risk item.
+- **No category headers.** No "Technical Debt" / "Architecture" sections. Just a ranked list.
+- **Each item: bold headline + one sentence of context.** The headline should make someone stop scrolling. The context sentence explains why it matters or what's at risk.
+- **Include the "so what?"** Don't just state facts — say what breaks, slows down, or gets harder if this isn't addressed.
+- **Skip anything routine.** If it shipped on schedule with no issues, it's not digest-worthy.
+- **Reference specifics** — PR numbers, issue titles, repo names, session entries.
+- **Do not include a title or header line.** The digest system adds its own header.
+
+## Tone
+
+Write for someone scrolling Slack on their phone. Direct, technical, zero filler. Every word earns its place.

package/templates/autopilot/product.md

@@ -0,0 +1,22 @@
+# Product Persona — Autopilot Prompt
+
+You are the Product persona for this team. You scan session journals and signal data to surface what a product leader needs to know — and nothing else.
+
+## Your job
+
+Find the 5 most consequential product items from this period. "Consequential" means: priorities shifted without discussion, customer pain surfaced, scope drifted, a product decision was made without PM input, or what shipped doesn't match what was planned.
+
+## Rules
+
+- **Maximum 5 items.** If fewer than 5 things matter, output fewer. Never pad.
+- **Rank by consequence, not category.** Lead with the item that most affects customers or roadmap.
+- **No category headers.** No "Scope Drift" / "Customer Issues" sections. Just a ranked list.
+- **Each item: bold headline + one sentence of context.** The headline should make someone stop scrolling. The context sentence explains why it matters or what to do about it.
+- **Include the "so what?"** Don't just state facts — say what's at risk for the user, the roadmap, or the business.
+- **Skip anything routine.** If it shipped as planned with no surprises, it's not digest-worthy.
+- **Reference specifics** — issue titles, feature names, customer signals, data points.
+- **Do not include a title or header line.** The digest system adds its own header.
+
+## Tone
+
+Write for someone scrolling Slack on their phone. Concise, actionable, zero filler. Every word earns its place.

package/templates/autopilot/strategy.md

@@ -0,0 +1,22 @@
+# Strategy Persona — Autopilot Prompt
+
+You are the Strategy persona for this team. You scan session journals and signal data to surface what a CTO or founder needs to know — and nothing else.
+
+## Your job
+
+Find the 5 most consequential strategic items from this period. "Consequential" means: competitive positioning changed, effort isn't mapping to business goals, cross-team patterns suggest an organizational issue, or day-to-day work is drifting from strategic objectives.
+
+## Rules
+
+- **Maximum 5 items.** If fewer than 5 things matter, output fewer. Never pad.
+- **Rank by consequence, not category.** Lead with the item that most affects the business trajectory.
+- **No category headers.** No "Competitive" / "Strategic Drift" sections. Just a ranked list.
+- **Each item: bold headline + one sentence of context.** The headline should make someone stop scrolling. The context sentence connects the dots — why this pattern matters at the company level.
+- **Include the "so what?"** Don't just state facts — say what's at risk strategically or what opportunity is being missed.
+- **Skip anything routine.** If it's business as usual, it's not digest-worthy.
+- **Reference specifics** — repos, team patterns, data points, timelines.
+- **Do not include a title or header line.** The digest system adds its own header.
+
+## Tone
+
+Write for someone scrolling Slack on their phone. High-level but specific, pattern-oriented, zero filler. Every word earns its place.

package/templates/autopilot/unified.md

@@ -0,0 +1,24 @@
+# Unified Digest — Autopilot Prompt
+
+You are a team digest generator. You scan session journals and signal data across all disciplines — engineering, product, design, and strategy — to surface what the team needs to know this week.
+
+## Your job
+
+Find the 5 most consequential things from this period. Pick from any discipline. "Consequential" means: something that changes plans, reveals risk, creates an opportunity, or would surprise someone who wasn't paying attention.
+
+## Rules
+
+- **Maximum 5 items.** If fewer than 5 things matter, output fewer. Never pad.
+- **Rank by consequence.** Lead with the item most likely to change what someone does tomorrow.
+- **Each item: bold headline (under 10 words) + one sentence of context.** The headline makes someone stop scrolling. The sentence says why it matters.
+- **Include the "so what?"** — what breaks, stalls, or gets missed if nobody acts.
+- **Skip anything routine.** On-schedule, on-plan work is not digest-worthy.
+- **Cross-discipline is fine.** If the top 5 are all engineering items, so be it. Don't force balance.
+- **Reference specifics** — PR numbers, issue titles, repo names, metrics, dates.
+- **Do not repeat items from the previous digest** unless there is a meaningful update or status change. Surface what changed, not what's still true.
+- **Consider the author's role** when assessing consequence. A CTO flagging a strategic risk carries different weight than routine engineering notes. Use team member context to calibrate importance.
+- **Do not include a title or header line.** The digest system adds its own.
+
+## Tone
+
+Write for someone scrolling Slack on their phone between meetings. Crisp, specific, zero filler. Every word earns its place.

package/templates/deploy/.env.example

@@ -0,0 +1,110 @@
+# Wayfind — Docker environment configuration
+# Copy to .env and fill in your values: cp .env.example .env
+
+# ── Required ──────────────────────────────────────────────────────────────────
+
+# Slack bot tokens — from the Slack app you created using slack-app-manifest.json.
+# Go to api.slack.com/apps → your Wayfind app → OAuth & Permissions for the bot token,
+# and Basic Information → App-Level Tokens for the app token.
+SLACK_BOT_TOKEN=xoxb-your-bot-token
+SLACK_APP_TOKEN=xapp-your-app-token
+
+# Anthropic API key (for digests and bot answers)
+# Get one at console.anthropic.com
+ANTHROPIC_API_KEY=sk-ant-your-key
+
+# GitHub token (for pulling team journals and signal data from repos)
+# Auto-detected from `gh auth token` during deploy init, or set manually.
+# Needs read access to the team-context repo.
+GITHUB_TOKEN=
+
+# ── Digest delivery ───────────────────────────────────────────────────────────
+# Primary: bot token + channel. The bot posts digests via chat.postMessage,
+# which enables reaction tracking and threaded feedback.
+# Fallback: webhook. Used only if bot delivery fails.
+
+# Slack channel for digest delivery (channel ID, not name)
+# Right-click channel in Slack → View channel details → copy the ID at bottom
+# SLACK_DIGEST_CHANNEL=C0123456789
+
+# Slack webhook — fallback for digest delivery if bot token is unavailable
+# TEAM_CONTEXT_SLACK_WEBHOOK=https://hooks.slack.com/services/T.../B.../...
+
+# ── Optional ──────────────────────────────────────────────────────────────────
+
+# Tenant identifier (prefixes storage paths)
+# TEAM_CONTEXT_TENANT_ID=my-team
+
+# Exclude repos from digests and bot queries (comma-separated, case-insensitive)
+# Useful when engineers work on repos belonging to different teams on the same machine
+# TEAM_CONTEXT_EXCLUDE_REPOS=wayfind,personal-project
+
+# Encryption key — generate with: openssl rand -base64 32
+# TEAM_CONTEXT_ENCRYPTION_KEY=
+
+# Author slug for CLI telemetry attribution
+# TEAM_CONTEXT_AUTHOR=greg
+
+# ── LLM models ───────────────────────────────────────────────────────────────
+
+# Model for digest generation and onboarding packs (default: claude-sonnet-4-5-20250929)
+# TEAM_CONTEXT_LLM_MODEL=claude-sonnet-4-5-20250929
+
+# Model for conversation transcript extraction (default: claude-sonnet-4-5-20250929)
+# TEAM_CONTEXT_EXTRACTION_MODEL=claude-sonnet-4-5-20250929
+
+# ── Embeddings (without these, bot uses keyword search only) ─────────────────
+# Option A: OpenAI
+# OPENAI_API_KEY=sk-your-openai-key
+# Option B: Azure OpenAI (if you have an AOAI deployment)
+# AZURE_OPENAI_EMBEDDING_ENDPOINT=https://your-resource.openai.azure.com/
+# AZURE_OPENAI_EMBEDDING_KEY=your-key
+# AZURE_OPENAI_EMBEDDING_DEPLOYMENT=text-embedding-3-small
+
+# ── Path overrides ───────────────────────────────────────────────────────────
+
+# Override content store path (default: ~/.claude/team-context/content-store)
+# TEAM_CONTEXT_STORE_PATH=/data/content-store
+
+# Override signals directory (default: ~/.claude/team-context/signals)
+# TEAM_CONTEXT_SIGNALS_DIR=/data/signals
+
+# Override conversations directory (default: ~/.claude/projects)
+# TEAM_CONTEXT_CONVERSATIONS_DIR=/data/conversations
+
+# ── Schedules ────────────────────────────────────────────────────────────────
+
+# Digest schedule (cron, default: daily 12pm UTC / 7am ET)
+# TEAM_CONTEXT_DIGEST_SCHEDULE=0 12 * * *
+
+# Signal pull schedule (cron, default: daily 6am UTC)
+# TEAM_CONTEXT_SIGNAL_SCHEDULE=0 6 * * *
+
+# Reindex schedule (cron, default: hourly)
+# TEAM_CONTEXT_REINDEX_SCHEDULE=0 * * * *
+
+# ── Signal sources ───────────────────────────────────────────────────────────
+
+# GitHub repos to pull signals from (comma-separated, org/repo format)
+# TEAM_CONTEXT_GITHUB_REPOS=myorg/repo1,myorg/repo2
+
+# Intercom API token for support signal ingestion
+# INTERCOM_TOKEN=your-intercom-token
+
+# Filter Intercom conversations by tags (comma-separated)
+# TEAM_CONTEXT_INTERCOM_TAGS=bug,feature-request
+
+# Notion integration token for page/database signal ingestion
+# Create at: https://www.notion.so/my-integrations
+# NOTION_TOKEN=ntn_your-integration-token
+
+# Specific Notion database IDs to monitor (comma-separated, or blank for all shared pages)
+# TEAM_CONTEXT_NOTION_DATABASES=db_id1,db_id2
+
+# ── Monitoring ───────────────────────────────────────────────────────────────
+
+# Health check port (default: 3141)
+# TEAM_CONTEXT_HEALTH_PORT=3141
+
+# Telemetry — opt-in anonymous usage data to help improve Wayfind
+# TEAM_CONTEXT_TELEMETRY=true

package/templates/deploy/docker-compose.yml

@@ -0,0 +1,63 @@
+# Wayfind — self-hosted deployment for your team context repo.
+# Run: docker compose up -d
+# Docs: https://github.com/usewayfind/wayfind
+
+services:
+  wayfind:
+    image: ghcr.io/usewayfind/wayfind:latest
+    container_name: wayfind
+    restart: unless-stopped
+    environment:
+      TEAM_CONTEXT_MODE: all-in-one
+      TEAM_CONTEXT_TENANT_ID: ${TEAM_CONTEXT_TENANT_ID:-my-team}
+      TEAM_CONTEXT_AUTHOR: ${TEAM_CONTEXT_AUTHOR:-}
+
+      # Slack
+      SLACK_BOT_TOKEN: ${SLACK_BOT_TOKEN}
+      SLACK_APP_TOKEN: ${SLACK_APP_TOKEN}
+      SLACK_DIGEST_CHANNEL: ${SLACK_DIGEST_CHANNEL:-}
+      TEAM_CONTEXT_SLACK_WEBHOOK: ${TEAM_CONTEXT_SLACK_WEBHOOK:-}
+
+      # Exclude repos from digests/queries (comma-separated, case-insensitive)
+      TEAM_CONTEXT_EXCLUDE_REPOS: ${TEAM_CONTEXT_EXCLUDE_REPOS:-}
+
+      # Telemetry (opt-in, sends anonymous usage data to improve Wayfind)
+      TEAM_CONTEXT_TELEMETRY: ${TEAM_CONTEXT_TELEMETRY:-false}
+
+      # GitHub signals
+      GITHUB_TOKEN: ${GITHUB_TOKEN:-}
+
+      # Intercom signals
+      INTERCOM_TOKEN: ${INTERCOM_TOKEN:-}
+      TEAM_CONTEXT_INTERCOM_TAGS: ${TEAM_CONTEXT_INTERCOM_TAGS:-}
+
+      # LLM
+      ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY}
+      TEAM_CONTEXT_LLM_MODEL: ${TEAM_CONTEXT_LLM_MODEL:-claude-sonnet-4-5-20250929}
+
+      # Embeddings (for semantic search — falls back to keyword search without these)
+      # Option A: OpenAI
+      OPENAI_API_KEY: ${OPENAI_API_KEY:-}
+      # Option B: Azure OpenAI
+      AZURE_OPENAI_EMBEDDING_ENDPOINT: ${AZURE_OPENAI_EMBEDDING_ENDPOINT:-}
+      AZURE_OPENAI_EMBEDDING_KEY: ${AZURE_OPENAI_EMBEDDING_KEY:-}
+      AZURE_OPENAI_EMBEDDING_DEPLOYMENT: ${AZURE_OPENAI_EMBEDDING_DEPLOYMENT:-text-embedding-3-small}
+
+      # Encryption — generate with: openssl rand -base64 32
+      TEAM_CONTEXT_ENCRYPTION_KEY: ${TEAM_CONTEXT_ENCRYPTION_KEY:-}
+
+      # Scheduling
+      TEAM_CONTEXT_DIGEST_SCHEDULE: ${TEAM_CONTEXT_DIGEST_SCHEDULE:-0 8 * * 1}
+      TEAM_CONTEXT_SIGNAL_SCHEDULE: ${TEAM_CONTEXT_SIGNAL_SCHEDULE:-0 6 * * *}
+
+      # Team context repo (mounted at /data/team-context for git pull)
+      TEAM_CONTEXT_TEAM_CONTEXT_DIR: /data/team-context
+      TEAM_CONTEXT_JOURNALS_DIR: /data/team-context/journals
+    volumes:
+      - ${TEAM_CONTEXT_TEAM_CONTEXT_PATH:-..}:/data/team-context
+      - wayfind-data:/home/node/.claude/team-context
+    ports:
+      - "3141:3141"
+
+volumes:
+  wayfind-data:

package/templates/deploy/slack-app-manifest.json

@@ -0,0 +1,45 @@
+{
+    "display_information": {
+        "name": "Wayfind",
+        "description": "Team context layer — persona digests from engineering journals and signal channels.",
+        "background_color": "#1a1a2e"
+    },
+    "features": {
+        "bot_user": {
+            "display_name": "Wayfind",
+            "always_online": false
+        }
+    },
+    "oauth_config": {
+        "scopes": {
+            "bot": [
+                "app_mentions:read",
+                "channels:history",
+                "chat:write",
+                "im:write",
+                "users:read",
+                "groups:history",
+                "incoming-webhook",
+                "reactions:read",
+                "reactions:write"
+            ]
+        }
+    },
+    "settings": {
+        "event_subscriptions": {
+            "bot_events": [
+                "app_mention",
+                "message.channels",
+                "message.groups",
+                "reaction_added",
+                "reaction_removed"
+            ]
+        },
+        "interactivity": {
+            "is_enabled": true
+        },
+        "org_deploy_enabled": false,
+        "socket_mode_enabled": true,
+        "token_rotation_enabled": false
+    }
+}

package/templates/github-actions/meridian-digest.yml

@@ -0,0 +1,85 @@
+# Wayfind Digest — GitHub Actions workflow
+# Generates and delivers persona-based digests on a schedule.
+# No Docker container needed — runs directly via npx.
+#
+# Setup:
+#   1. Copy this file to .github/workflows/meridian-digest.yml in your team-context repo
+#   2. Add these secrets to the repo (Settings → Secrets → Actions):
+#      - ANTHROPIC_API_KEY: Your Anthropic API key
+#      - SLACK_WEBHOOK_URL: Slack incoming webhook URL (optional — digests are also committed to the repo)
+#   3. Adjust the cron schedule below (default: Monday 8am UTC)
+#   4. Push — the workflow runs on schedule and can be triggered manually
+
+name: Wayfind Digest
+
+on:
+  schedule:
+    # Every Monday at 8:00 AM UTC — adjust to your team's timezone
+    - cron: '0 8 * * 1'
+  workflow_dispatch:
+    inputs:
+      persona:
+        description: 'Persona to generate (empty = all configured)'
+        required: false
+        default: ''
+
+permissions:
+  contents: write
+
+jobs:
+  digest:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout team-context repo
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+
+      - name: Install Wayfind
+        run: npm install -g wayfind
+
+      - name: Generate digest
+        env:
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          TEAM_CONTEXT_TEAM_CONTEXT_DIR: ${{ github.workspace }}
+          TEAM_CONTEXT_JOURNALS_DIR: ${{ github.workspace }}/journals
+          TEAM_CONTEXT_SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK_URL }}
+        run: |
+          # Configure wayfind to use this repo as team context
+          wayfind context init "${{ github.workspace }}" 2>/dev/null || true
+
+          # Build flags
+          FLAGS=""
+          PERSONA="${{ github.event.inputs.persona }}"
+          if [ -n "$PERSONA" ]; then
+            FLAGS="--persona $PERSONA"
+          fi
+
+          # Add --deliver if webhook is configured
+          if [ -n "$TEAM_CONTEXT_SLACK_WEBHOOK" ]; then
+            FLAGS="$FLAGS --deliver"
+          fi
+
+          wayfind digest $FLAGS
+
+      - name: Commit digest to repo
+        run: |
+          DIGEST_DIR="$HOME/.claude/team-context/digests"
+          REPO_DIGEST_DIR="digests"
+
+          if [ -d "$DIGEST_DIR" ]; then
+            mkdir -p "$REPO_DIGEST_DIR"
+            cp -r "$DIGEST_DIR"/* "$REPO_DIGEST_DIR/" 2>/dev/null || true
+
+            git config user.name "Wayfind Bot"
+            git config user.email "wayfind@noreply.github.com"
+            git add "$REPO_DIGEST_DIR/"
+            DATE=$(date +%Y-%m-%d)
+            git diff --cached --quiet || git commit -m "Digest: $DATE"
+            git push
+          fi