npm - wayfind - Versions diffs - 2.0.70 → 2.0.72 - Mend

wayfind 2.0.70 → 2.0.72

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (4) hide show

package/README.md +74 -137
package/package.json +1 -1
package/plugin/.claude-plugin/plugin.json +1 -1
package/setup.sh +62 -108

package/README.md CHANGED Viewed

@@ -1,68 +1,55 @@
 # Wayfind
-**Team decision trail for AI-assisted development.**
+**Team memory for AI-assisted engineering.**
-> AI makes individual engineers faster. Nobody has solved coherent, maintainable software built by a *team* over time. Every handoff loses context. Wayfind captures it.
+Your AI coding assistant forgets everything between sessions. Wayfind gives it a memory — for you and your whole team.
+Plain markdown files. No infrastructure. Works with any MCP client.
 [![CI](https://github.com/usewayfind/wayfind/actions/workflows/ci.yml/badge.svg)](https://github.com/usewayfind/wayfind/actions/workflows/ci.yml)
-[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE)
 [![npm](https://img.shields.io/npm/v/wayfind)](https://www.npmjs.com/package/wayfind)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE)
----
-## Install
-### Claude Code plugin (recommended)
+**Works with:** Claude Code | Cursor | Any MCP client
-In a Claude Code session:
+---
-```
-/plugin marketplace add usewayfind/wayfind
-/plugin install wayfind@usewayfind
-```
+## The Problem
-Then initialize a repo:
+AI coding assistants are stateless. Every session starts cold. The decisions you made yesterday, the architecture you agreed on last week, the reason you chose Postgres over Mongo — gone. You re-explain, or the AI guesses wrong.
-```
-/wayfind:init-memory
-```
+Now multiply that across a team. Five engineers, each with their own AI sessions, none of them aware of what the others decided. Your PM reads the standup notes, but the AI that writes the code doesn't.
-Your AI sessions now resume where you left off instead of cold-starting.
+## What Wayfind Does
-### npm CLI
+**For you:** Sessions resume where they left off. Decisions are extracted automatically and become searchable history. Drift detection flags when work veers from the stated goal.
-The plugin includes the CLI, but you can also install it standalone:
+**For your team:** A daily digest summarizes what everyone shipped, decided, and discovered — tailored per role (engineering, product, design, strategy). Team members who use AI tools get session memory directly. Everyone else gets a Slack digest.
-```bash
-npm install -g wayfind
-wayfind init
-```
+**For your AI tools:** An MCP server exposes your team's full decision history as tools. Claude, Cursor, or any MCP client can search decisions, browse by date, and retrieve context — no file reading or guessing.
-The CLI is required for digest generation, Slack bot, signal connectors, and team management. The plugin handles session hooks and slash commands.
+<!-- TODO: demo GIF here — see #175 -->
 ---
-## What It Does
+## Quick Start
-### For You (solo engineer)
+### Option A: Claude Code plugin
-- **Persistent memory** — sessions pick up where the last one ended
-- **Automatic journal** — decisions and rationale extracted from every session
-- **Searchable history** — `wayfind search-journals "auth refactor"`
-- **Drift detection** — AI flags when work drifts from the stated goal
-### For Your Team
-- **Digests** — weekly summaries tailored per role (engineering, product, design, strategy)
-- **Slack bot** — anyone on the team asks `@wayfind` and gets answers from the decision trail
-- **Signal connectors** — pull context from GitHub, Intercom, and Notion into digests
-- **Context shift detection** — surfaces significant pivots and architecture changes
+```
+/plugin marketplace add usewayfind/wayfind
+/plugin install wayfind@usewayfind
+/wayfind:init-memory
+```
-Only the engineer installs anything. Everyone else sees a Slack digest.
+### Option B: npm (works with any AI tool)
+```bash
+npm install -g wayfind
+wayfind init
 ```
-/wayfind:init-team     # Set up team context, journals, and digests
-```
+Your next AI session has memory. That's it.
 ---
@@ -85,118 +72,72 @@ All context is plain markdown in directories you control:
 No proprietary formats. No vendor lock-in. `grep` works if Wayfind breaks.
-### The Session Protocol
-**Start:** AI reads state files, summarizes context, asks "What's the goal?"
-**Mid-session:** If work drifts from the goal, the AI flags it.
+### The Session Loop
-**End:** Decisions are extracted, written as journal entries, and synced to the team repo — automatically via hooks.
+1. **Start** — AI reads state files, summarizes context, asks "What's the goal?"
+2. **Mid-session** — If work drifts from the goal, the AI flags it.
+3. **End** — Decisions are extracted, written as journal entries, and synced to the team repo — automatically via hooks.
-### Digests
+### Team Digests
-Each role sees the same underlying data through a different lens:
+Each role sees the same data through a different lens:
-- **Engineering**: What shipped, what drifted, patterns
+- **Engineering**: What shipped, what drifted, what patterns emerged
 - **Product**: What shipped vs. planned, discovery signals
-- **Design**: UX decisions, implementation gaps vs. design intent
 - **Strategy**: Cross-team patterns, drift trends, capability gaps
-### Signal Connectors
+The digest posts to Slack. Anyone on the team — engineer, PM, CEO — who uses an AI tool gets session memory. Everyone else gets the digest.
-```bash
-wayfind pull github       # Issues, PRs, Actions status
-wayfind pull intercom     # Support conversations, tags, response times
-wayfind pull notion       # Pages, databases, comments
-wayfind pull --all        # All configured channels
-```
+### MCP Server
----
+Wayfind includes an MCP server that exposes team context to any MCP-compatible AI tool. Auto-registered during `wayfind init`.
-## Commands
-### Plugin skills (in Claude Code)
-| Skill | Description |
-|-------|-------------|
-| `/wayfind:init-memory` | Initialize context for the current repo |
-| `/wayfind:init-team` | Set up team context, journals, and digests |
-| `/wayfind:doctor` | Check installation health |
-| `/wayfind:standup` | Daily standup summary |
-| `/wayfind:journal` | Weekly journal digest and drift detection |
-| `/wayfind:review-prs` | Review overnight PRs |
-### CLI commands
-| Command | Description |
-|---------|-------------|
-| `wayfind init` | Install for your AI tool |
-| `wayfind doctor` | Check installation health |
-| `wayfind update` | Update hooks and commands |
-| `wayfind status` | Cross-project status |
-| `wayfind team create` | Create a new team |
-| `wayfind team join` | Join an existing team |
-| `wayfind digest` | Generate persona-specific digests |
-| `wayfind digest --deliver` | Generate and post to Slack |
-| `wayfind bot` | Start the Slack bot |
-| `wayfind reindex` | Index journals + conversations |
-| `wayfind search-journals <q>` | Search decision history |
-| `wayfind pull <channel>` | Pull signals from a source |
-| `wayfind journal sync` | Sync journals to team repo |
-| `wayfind onboard <repo>` | Generate onboarding context pack |
-| `wayfind deploy init` | Scaffold Docker deployment |
-| `wayfind deploy --team <id>` | Scaffold per-team Docker deployment |
-| `wayfind deploy set-endpoint <url>` | Set container endpoint for team search |
-| `wayfind deploy list` | List running team containers |
-| `wayfind deploy status` | Check container health |
-| `wayfind migrate-to-plugin` | Remove old hooks (after plugin install) |
-Run `wayfind help` for the full list.
+**Tools:**
----
+| Tool | What it does |
+|------|-------------|
+| `search_context` | Search decisions by query, date range, author, or repo. Semantic or browse mode. |
+| `get_entry` | Retrieve the full content of a specific entry. |
+| `get_signals` | Recent GitHub, Intercom, and Notion activity. |
+| `get_team_status` | Current team state: who's working on what, active projects, blockers. |
+| `add_context` | Capture a decision or blocker from the current session. |
+| `record_feedback` | Rate whether a result was useful (improves future retrieval). |
-## MCP Server
+Each team member's MCP server searches their local content store — journals synced from the shared team repo, with local embeddings generated automatically. No infrastructure required.
-Wayfind includes an MCP server (`wayfind-mcp`) that exposes team context to any MCP-compatible AI tool.
+---
-**Tools:** `search_context`, `get_entry`, `list_recent`, `get_signals`, `get_team_status`, `get_personas`, `record_feedback`, `add_context`
+## Signal Connectors
-Auto-registered during `wayfind init`. When a team container is running, the local MCP server proxies semantic search to it automatically — no config needed beyond the team-context repo.
+Pull external context into digests:
----
-## Environment Variables
+```bash
+wayfind pull github       # Issues, PRs, Actions status
+wayfind pull intercom     # Support conversations, tags, response times
+wayfind pull notion       # Pages, databases, comments
+wayfind pull --all        # All configured channels
+```
-### For digests and bot
+---
-| Variable | Description |
-|----------|-------------|
-| `ANTHROPIC_API_KEY` | Digest generation and bot answers |
-| `SLACK_BOT_TOKEN` | Slack bot token (`xoxb-...`) |
-| `SLACK_APP_TOKEN` | Slack app-level token (`xapp-...`) |
-| `GITHUB_TOKEN` | Signal data and journal sync |
+## Team Setup
-### Optional
+```
+/wayfind:init-team
+```
-| Variable | Description |
-|----------|-------------|
-| `OPENAI_API_KEY` | Upgrade semantic search to OpenAI embeddings (Xenova local model is used by default — no key needed) |
-| `TEAM_CONTEXT_LLM_MODEL` | LLM for digests (default: `claude-sonnet-4-5-20250929`) |
-| `TEAM_CONTEXT_DIGEST_SCHEDULE` | Cron schedule (default: `0 8 * * 1` — Monday 8am) |
-| `TEAM_CONTEXT_EXCLUDE_REPOS` | Repos to exclude from digests |
-| `TEAM_CONTEXT_TELEMETRY` | `true` for anonymous usage telemetry |
+This walks you through creating a team, setting up profiles, creating a shared team-context repo, and configuring Slack digest delivery. Multi-team support built in — bind repos to different teams, each with isolated context.
 ---
 ## Tool Support
-| Tool | Status | Setup |
-|------|--------|-------|
-| Claude Code | Full support (plugin) | `/plugin marketplace add usewayfind/wayfind` |
-| Claude Code | Full support (npm) | `wayfind init` |
-| Cursor | Session protocol | `wayfind init-cursor` |
-| Generic | Manual | See `specializations/generic/` |
-| Any MCP client | Full support (MCP) | `wayfind init` auto-registers |
+| Tool | How | Setup |
+|------|-----|-------|
+| **Claude Code** | Plugin (full support) | `/plugin marketplace add usewayfind/wayfind` |
+| **Cursor** | MCP server | `wayfind init` auto-registers |
+| **Any MCP client** | MCP server | `wayfind init` auto-registers |
+| **Slack** | Bot + digests | `wayfind bot --configure` |
 ---
@@ -206,27 +147,23 @@ Everything that runs on your machine is open source (Apache 2.0).
 | Open Source (this repo) | Commercial (future) |
 |---|---|
-| CLI and all commands | Cloud-hosted team aggregation |
+| CLI, plugin, and all commands | Cloud-hosted team aggregation |
 | Session protocol and journal extraction | Managed digest delivery |
-| Content store and search | Web dashboard |
+| Content store, semantic search, MCP server | Web dashboard |
 | Signal connectors (GitHub, Intercom, Notion) | SSO and tenant isolation |
 | Digest generation (your API key) | |
 | Slack bot (self-hosted) | |
 | Multi-team support | |
-| MCP server (local + container proxy) | |
-| Per-team content store isolation | |
-See [LICENSING.md](LICENSING.md) for details.
 ---
 ## Architecture
 - [Data Flow](docs/architecture/data-flow.md) — sessions to digests
-- [Principles](docs/architecture/architecture-principles.md) — the eight constraints
+- [Query Path](docs/architecture/query-path.md) — how queries reach the content store
 - [Content Store](docs/architecture/content-store.md) — indexing, search, schema
+- [Principles](docs/architecture/architecture-principles.md) — the eight constraints
 - [Signal Channels](docs/architecture/architecture-signal-channels.md) — connector architecture
-- [Signal Roadmap](docs/architecture/signal-source-roadmap.md) — planned connectors
 ---
@@ -242,4 +179,4 @@ See [CONTRIBUTING.md](CONTRIBUTING.md). Good first contributions:
 ## License
-Apache 2.0. See [LICENSE](LICENSE) and [LICENSING.md](LICENSING.md).
+Apache 2.0. See [LICENSE](LICENSE).

package/package.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "name": "wayfind",
-  "version": "2.0.70",
+  "version": "2.0.72",
   "description": "Team decision trail for AI-assisted development. The connective tissue between product, engineering, and strategy.",
   "bin": {
     "wayfind": "./bin/team-context.js",

package/plugin/.claude-plugin/plugin.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "name": "wayfind",
-  "version": "2.0.70",
+  "version": "2.0.72",
   "description": "Team decision trail for AI-assisted development. Session memory, decision journals, and team digests.",
   "author": {
     "name": "Wayfind",

package/setup.sh CHANGED Viewed

@@ -145,7 +145,6 @@ if [ ! -d "$SPEC_DIR" ]; then
 fi
 echo ""
-echo "Installing Wayfind for: $TOOL"
 [ "$DRY_RUN" = true ] && warn "Dry-run mode — no files will be modified"
 [ "$UPDATE" = true ] && warn "Update mode: overwriting hook scripts and commands (memory files untouched)"
@@ -184,23 +183,24 @@ case "$TOOL" in
         ;;
 esac
-# ── Step 1: Directories ────────────────────────────────────────────────────────
+# ── Counters for aggregate output ─────────────────────────────────────────────
+CONFIG_FILES=0
+HOOKS_INSTALLED=0
+COMMANDS_INSTALLED=0
+MCP_OK=false
-header "Creating directories"
+# ── Step 1: Directories ────────────────────────────────────────────────────────
 run mkdir -p "$MEMORY_SUBDIR/journal"
-log "Memory directories: $MEMORY_SUBDIR/journal"
 if [ "$TOOL" = "claude-code" ]; then
     run mkdir -p "$HOME/.claude/hooks"
     run mkdir -p "$HOME/.claude/commands"
-    log "Claude Code hooks and commands directories"
 fi
 # ── Step 2: Global state file ─────────────────────────────────────────────────
-header "Global state file"
 if [ ! -f "$GLOBAL_STATE" ]; then
     if [ "$TOOL" = "claude-code" ]; then
         if [ "$DRY_RUN" = false ]; then
@@ -214,30 +214,18 @@ if [ ! -f "$GLOBAL_STATE" ]; then
     else
         run cp "$SCRIPT_DIR/templates/global.md" "$GLOBAL_STATE"
     fi
-    log "Created $GLOBAL_STATE"
-    warn "Edit $GLOBAL_STATE to add your name, preferences, and projects"
-else
-    info "Already exists: $GLOBAL_STATE — skipped"
+    CONFIG_FILES=$((CONFIG_FILES + 1))
 fi
 # ── Step 3: Admin state file (team/personal split) ───────────────────────────
-# For team repos, use templates/team-state.md (committed, shared context).
-# For personal notes, use templates/personal-state.md (gitignored, private).
-# The admin state file at ADMIN_STATE is the non-repo catch-all (email, admin, misc).
-header "Admin state file"
 if [ ! -f "$ADMIN_STATE" ]; then
     run cp "$SCRIPT_DIR/templates/repo-state.md" "$ADMIN_STATE"
-    log "Created $ADMIN_STATE"
-else
-    info "Already exists: $ADMIN_STATE — skipped"
+    CONFIG_FILES=$((CONFIG_FILES + 1))
 fi
 # ── Step 3b: Persona configuration ────────────────────────────────────────────
-header "Persona configuration"
 case "$TOOL" in
     claude-code) PERSONAS_DIR="$HOME/.claude/team-context" ;;
     *)           PERSONAS_DIR="$HOME/.ai-memory/team-context" ;;
@@ -247,15 +235,11 @@ PERSONAS_DEST="$PERSONAS_DIR/personas.json"
 if [ ! -f "$PERSONAS_DEST" ]; then
     run mkdir -p "$PERSONAS_DIR"
     run cp "$SCRIPT_DIR/templates/personas.json" "$PERSONAS_DEST"
-    log "Created $PERSONAS_DEST (default personas — edit to customize)"
-else
-    info "Already exists: $PERSONAS_DEST — skipped (your customizations are preserved)"
+    CONFIG_FILES=$((CONFIG_FILES + 1))
 fi
 # ── Step 4: Tool-specific files ───────────────────────────────────────────────
-header "Tool-specific files ($TOOL)"
 case "$TOOL" in
     claude-code)
         # Global CLAUDE.md fragment
@@ -264,9 +248,10 @@ case "$TOOL" in
                 info "[dry-run] Would append Session State Protocol to $GLOBAL_CLAUDE_MD"
             else
                 touch "$GLOBAL_CLAUDE_MD"
-                append_if_missing "Session State Protocol" \
-                    "$(cat "$SPEC_DIR/CLAUDE.md-global-fragment.md")" \
-                    "$GLOBAL_CLAUDE_MD"
+                if ! grep -qF "Session State Protocol" "$GLOBAL_CLAUDE_MD" 2>/dev/null; then
+                    cat "$SPEC_DIR/CLAUDE.md-global-fragment.md" >> "$GLOBAL_CLAUDE_MD"
+                    CONFIG_FILES=$((CONFIG_FILES + 1))
+                fi
             fi
         fi
@@ -275,88 +260,63 @@ case "$TOOL" in
         if [ ! -f "$HOOK_DEST" ] || [ "$UPDATE" = true ]; then
             run cp "$SPEC_DIR/hooks/check-global-state.sh" "$HOOK_DEST"
             run chmod +x "$HOOK_DEST"
-            log "Installed hook: $HOOK_DEST"
-        else
-            info "Hook already exists: $HOOK_DEST — skipped"
+            HOOKS_INSTALLED=$((HOOKS_INSTALLED + 1))
         fi
         SESSION_END_DEST="$HOME/.claude/hooks/session-end.sh"
         if [ ! -f "$SESSION_END_DEST" ] || [ "$UPDATE" = true ]; then
             run cp "$SPEC_DIR/hooks/session-end.sh" "$SESSION_END_DEST"
             run chmod +x "$SESSION_END_DEST"
-            log "Installed hook: $SESSION_END_DEST"
-        else
-            info "Hook already exists: $SESSION_END_DEST — skipped"
+            HOOKS_INSTALLED=$((HOOKS_INSTALLED + 1))
         fi
-        # init-memory command
+        # Commands
         CMD_DEST="$HOME/.claude/commands/init-memory.md"
         if [ ! -f "$CMD_DEST" ] || [ "$UPDATE" = true ]; then
             run cp "$SPEC_DIR/commands/init-memory.md" "$CMD_DEST"
-            log "Installed command: /init-memory"
-        else
-            info "/init-memory command already exists — skipped"
+            COMMANDS_INSTALLED=$((COMMANDS_INSTALLED + 1))
         fi
-        # doctor command
         DOCTOR_CMD_DEST="$HOME/.claude/commands/doctor.md"
         if [ ! -f "$DOCTOR_CMD_DEST" ] || [ "$UPDATE" = true ]; then
             run cp "$SPEC_DIR/commands/doctor.md" "$DOCTOR_CMD_DEST"
-            log "Installed command: /doctor"
-        else
-            info "/doctor command already exists — skipped"
+            COMMANDS_INSTALLED=$((COMMANDS_INSTALLED + 1))
         fi
-        # doctor.sh script
+        # Support scripts
         run mkdir -p "$HOME/.claude/team-context"
         DOCTOR_DEST="$HOME/.claude/team-context/doctor.sh"
         if [ ! -f "$DOCTOR_DEST" ] || [ "$UPDATE" = true ]; then
             run cp "$SCRIPT_DIR/doctor.sh" "$DOCTOR_DEST"
             run chmod +x "$DOCTOR_DEST"
-            log "Installed doctor script: $DOCTOR_DEST"
-        else
-            info "doctor.sh already exists: $DOCTOR_DEST — skipped"
         fi
-        # journal-summary.sh script
         JOURNAL_DEST="$HOME/.claude/team-context/journal-summary.sh"
         if [ ! -f "$JOURNAL_DEST" ] || [ "$UPDATE" = true ]; then
             run cp "$SCRIPT_DIR/journal-summary.sh" "$JOURNAL_DEST"
             run chmod +x "$JOURNAL_DEST"
-            log "Installed journal summary script: $JOURNAL_DEST"
-        else
-            info "journal-summary.sh already exists: $JOURNAL_DEST — skipped"
         fi
-        # /journal command
         JOURNAL_CMD_DEST="$HOME/.claude/commands/journal.md"
         if [ ! -f "$JOURNAL_CMD_DEST" ] || [ "$UPDATE" = true ]; then
             run cp "$SPEC_DIR/commands/journal.md" "$JOURNAL_CMD_DEST"
-            log "Installed command: /journal"
-        else
-            info "/journal command already exists — skipped"
+            COMMANDS_INSTALLED=$((COMMANDS_INSTALLED + 1))
         fi
-        # /init-team command
         TEAM_CMD_DEST="$HOME/.claude/commands/init-team.md"
         if [ ! -f "$TEAM_CMD_DEST" ] || [ "$UPDATE" = true ]; then
             if [ -f "$SPEC_DIR/commands/init-team.md" ]; then
                 run cp "$SPEC_DIR/commands/init-team.md" "$TEAM_CMD_DEST"
-                log "Installed command: /init-team"
+                COMMANDS_INSTALLED=$((COMMANDS_INSTALLED + 1))
             fi
-        else
-            info "/init-team command already exists — skipped"
         fi
-        # /review-prs command
         REVIEW_CMD_DEST="$HOME/.claude/commands/review-prs.md"
         if [ ! -f "$REVIEW_CMD_DEST" ] || [ "$UPDATE" = true ]; then
             if [ -f "$SPEC_DIR/commands/review-prs.md" ]; then
                 run cp "$SPEC_DIR/commands/review-prs.md" "$REVIEW_CMD_DEST"
-                log "Installed command: /review-prs"
+                COMMANDS_INSTALLED=$((COMMANDS_INSTALLED + 1))
             fi
-        else
-            info "/review-prs command already exists — skipped"
         fi
         # settings.json — merge hooks, don't overwrite
@@ -366,7 +326,7 @@ case "$TOOL" in
         if [ ! -f "$SETTINGS" ]; then
             run cp "$SPEC_DIR/settings.json" "$SETTINGS"
-            log "Created $SETTINGS with hook registration"
+            CONFIG_FILES=$((CONFIG_FILES + 1))
         else
             # Merge both hooks into existing settings.json using Python
             NEEDS_MERGE=false
@@ -427,7 +387,6 @@ with open(out_path, "w") as f:
     f.write("\n")
 PYEOF
                         mv "$TMP_SETTINGS" "$SETTINGS"
-                        log "Merged hooks into existing $SETTINGS"
                     else
                         rm -f "$TMP_SETTINGS"
                         warn "Could not auto-merge hooks into $SETTINGS (malformed JSON or python3 unavailable)."
@@ -436,8 +395,6 @@ PYEOF
                 else
                     info "[dry-run] Would merge hooks into $SETTINGS"
                 fi
-            else
-                info "Hooks already registered in settings.json — skipped"
             fi
         fi
@@ -470,20 +427,19 @@ with open(out_path, "w") as f:
     f.write("\n")
 PYEOF
                         mv "$TMP_SETTINGS" "$SETTINGS"
-                        log "Registered wayfind MCP server in ~/.claude/settings.json"
+                        MCP_OK=true
                     else
                         rm -f "$TMP_SETTINGS"
-                        warn "Could not register MCP server — add manually to ~/.claude/settings.json:"
-                        warn "  \"mcpServers\": { \"wayfind\": { \"command\": \"$MCP_BIN\" } }"
+                        warn "Could not register MCP server — add manually to ~/.claude/settings.json"
                     fi
                 else
                     info "[dry-run] Would register wayfind MCP server ($MCP_BIN) in $SETTINGS"
                 fi
             else
-                info "MCP server already registered in settings.json — skipped"
+                MCP_OK=true
             fi
         else
-            warn "wayfind-mcp binary not found — skipping MCP registration. Re-run after npm install."
+            warn "wayfind-mcp not found — MCP registration skipped. Re-run setup after npm install."
         fi
         ;;
@@ -494,9 +450,7 @@ PYEOF
         GLOBAL_RULE="$HOME/.cursor/rules/ai-memory.mdc"
         if [ ! -f "$GLOBAL_RULE" ] || [ "${UPDATE:-false}" = true ]; then
             run cp "$SPEC_DIR/global-rule.mdc" "$GLOBAL_RULE"
-            log "Installed global Cursor rule: $GLOBAL_RULE"
-        else
-            info "Global Cursor rule already exists — skipped"
+            CONFIG_FILES=$((CONFIG_FILES + 1))
         fi
         # Per-repo rule (if --repo was passed)
@@ -506,8 +460,7 @@ PYEOF
                 run mkdir -p "$RULE_DIR"
                 if [ ! -f "$RULE_DIR/memory.mdc" ] || [ "${UPDATE:-false}" = true ]; then
                     run cp "$SPEC_DIR/repo-rule.mdc" "$RULE_DIR/memory.mdc"
-                    log "Installed repo rule: $RULE_DIR/memory.mdc"
-                    warn "Edit $RULE_DIR/memory.mdc to add repo name and initial status"
+                    CONFIG_FILES=$((CONFIG_FILES + 1))
                 else
                     info "Repo rule already exists — skipped"
                 fi
@@ -531,7 +484,7 @@ PYEOF
                 if [ "$DRY_RUN" = false ]; then
                     if [ ! -f "$CURSOR_MCP" ]; then
                         printf '{\n  "mcpServers": {\n    "wayfind": {\n      "command": "%s",\n      "args": []\n    }\n  }\n}\n' "$CURSOR_MCP_BIN" > "$CURSOR_MCP"
-                        log "Created ~/.cursor/mcp.json with wayfind MCP server"
+                        MCP_OK=true
                     else
                         TMP_MCP="$(mktemp)"
                         if python3 - "$CURSOR_MCP" "$CURSOR_MCP_BIN" "$TMP_MCP" <<'PYEOF' 2>/dev/null; then
@@ -550,21 +503,20 @@ with open(out_path, "w") as f:
     f.write("\n")
 PYEOF
                             mv "$TMP_MCP" "$CURSOR_MCP"
-                            log "Registered wayfind MCP server in ~/.cursor/mcp.json"
+                            MCP_OK=true
                         else
                             rm -f "$TMP_MCP"
-                            warn "Could not register MCP server — add manually to ~/.cursor/mcp.json:"
-                            warn "  \"mcpServers\": { \"wayfind\": { \"command\": \"$CURSOR_MCP_BIN\", \"args\": [] } }"
+                            warn "Could not register MCP server — add manually to ~/.cursor/mcp.json"
                         fi
                     fi
                 else
                     info "[dry-run] Would register wayfind MCP server ($CURSOR_MCP_BIN) in ~/.cursor/mcp.json"
                 fi
             else
-                info "MCP server already registered in ~/.cursor/mcp.json — skipped"
+                MCP_OK=true
             fi
         else
-            warn "wayfind-mcp binary not found — skipping Cursor MCP registration. Re-run after npm install."
+            warn "wayfind-mcp not found — MCP registration skipped. Re-run setup after npm install."
         fi
         ;;
@@ -592,7 +544,6 @@ if [ -n "$INSTALL_VERSION" ]; then
         TMP_VER="$(mktemp)"
         echo "$INSTALL_VERSION" > "$TMP_VER"
         mv "$TMP_VER" "$VERSION_DEST"
-        log "Version v${INSTALL_VERSION} written to $VERSION_DEST"
     else
         info "[dry-run] Would write v${INSTALL_VERSION} to $KIT_DEST_DIR/.wayfind-version"
     fi
@@ -656,40 +607,43 @@ Do not ask more than once per decision. Do not ask during routine implementation
     fi
 fi
-# ── Step 7: Personas (informational) ─────────────────────────────────────────
-header "Personas"
+# ── Summary ──────────────────────────────────────────────────────────────────
 echo ""
-echo "  Default personas: Product, Design, Engineering, Strategy"
-echo "  You can customize personas later with 'wayfind personas'"
-echo ""
-# ── Step 8: Summary ───────────────────────────────────────────────────────────
-header "Done"
+# Aggregate summary of what was installed
+SUMMARY_PARTS=""
+[ "$CONFIG_FILES" -gt 0 ] && SUMMARY_PARTS="${SUMMARY_PARTS}${CONFIG_FILES} config files"
+if [ "$HOOKS_INSTALLED" -gt 0 ]; then
+    [ -n "$SUMMARY_PARTS" ] && SUMMARY_PARTS="${SUMMARY_PARTS}, "
+    SUMMARY_PARTS="${SUMMARY_PARTS}${HOOKS_INSTALLED} hooks"
+fi
+if [ "$COMMANDS_INSTALLED" -gt 0 ]; then
+    [ -n "$SUMMARY_PARTS" ] && SUMMARY_PARTS="${SUMMARY_PARTS}, "
+    SUMMARY_PARTS="${SUMMARY_PARTS}${COMMANDS_INSTALLED} commands"
+fi
+if [ "$MCP_OK" = true ]; then
+    [ -n "$SUMMARY_PARTS" ] && SUMMARY_PARTS="${SUMMARY_PARTS}, "
+    SUMMARY_PARTS="${SUMMARY_PARTS}MCP server"
+fi
+if [ -n "$SUMMARY_PARTS" ]; then
+    log "Created ${SUMMARY_PARTS}"
+fi
+echo -e "${GREEN}✓${RESET} Wayfind installed for ${TOOL}."
 echo ""
-echo "Wayfind installed for $TOOL."
-echo ""
-echo "Next steps:"
-echo "  1. Edit $GLOBAL_STATE with your preferences and projects"
 if [ "$TOOL" = "claude-code" ]; then
-    echo "  2. Open a repo and run /init-memory to set it up"
-    echo "  3. Start a Claude Code session — it will load your state automatically"
-    echo "  4. Run /journal for a weekly digest of your AI session logs"
-    echo "  5. Set up your profile: wayfind whoami --setup"
-    echo "  6. Create or join a team: wayfind team create"
+    echo "  Next: open a repo and run /init-memory to set it up."
+    echo "        Then start a Claude Code session — Wayfind captures context automatically."
 elif [ "$TOOL" = "cursor" ]; then
-    echo "  2. Open a repo and run: bash setup.sh --tool cursor --repo <path>"
-    echo "  3. Start a Cursor session — the global rule loads your state automatically"
-    echo "  4. See specializations/cursor/README.md for full documentation"
+    echo "  Next: open a repo and run: bash setup.sh --tool cursor --repo <path>"
+    echo "        Then start a Cursor session — the global rule loads your state automatically."
 else
-    echo "  2. Add the session protocol to your tool's system prompt"
-    echo "     See: specializations/generic/README.md"
+    echo "  Next: add the session protocol to your tool's system prompt."
+    echo "        See: specializations/generic/README.md"
 fi
 echo ""
-echo "  Full documentation: README.md"
+echo "  Docs: https://github.com/usewayfind/wayfind"
 echo ""