obsidian-agent-fleet 0.3.2 → 0.4.2

package/README.md

@@ -1,224 +1,157 @@
 # Agent Fleet for Obsidian
 
-**Turn Obsidian into an AI-powered command center. Create autonomous agents, schedule tasks, chat in real-time, and connect to any MCP service — all from your vault.**
+**File-backed AI agents, task scheduling, and interactive chat — all inside Obsidian.**
 
-![Agent Fleet Dashboard](screenshot.png)
+Agent Fleet lets you create, configure, and run AI agents directly from your Obsidian vault. Every agent, skill, task, and run log is a markdown file with YAML frontmatter. If the plugin disappears, your knowledge stays.
 
----
-
-## What is Agent Fleet?
-
-Agent Fleet is an Obsidian plugin that lets you build, configure, and run AI agents directly from your vault. Agents are powered by **Claude Code CLI** — works with a Claude Max/Pro subscription or Anthropic API key. Every agent, skill, task, and run log is a markdown file. If the plugin disappears, your knowledge stays.
-
-### Core Capabilities
-
-🤖 **AI Agents** — Create specialized agents with system prompts, skills, permissions, and memory. Each agent is a folder of markdown files you fully own and control.
-
-💬 **Interactive Chat** — Dock a chat panel anywhere in Obsidian. Switch between agents. Attach documents and images. Send follow-up messages while the agent works.
+## Key Features
 
-📋 **Task Board** — Kanban view with scheduling, priority, real-time progress tracking, and abort. Tasks run on cron schedules or on-demand.
+- **Interactive Chat** — chat with agents in a side panel with streaming markdown responses
+- **Session Persistence** — conversations survive panel close and Obsidian restarts via Claude CLI `--resume`
+- **Task Scheduling** — cron-based recurring tasks, one-shot runs, and manual execution
+- **Skill System** — reusable skill libraries that agents can share
+- **Agent Memory** — persistent context across runs via `[REMEMBER]...[/REMEMBER]` tags
+- **Live Dashboard** — overview with charts, run history, kanban board, and approval workflow
+- **Lucide Icon Picker** — searchable icon selector for agent avatars (1,400+ icons)
+- **18 Built-in Skills** — PDF, PPTX, DOCX, XLSX, Claude API, MCP Builder, Frontend Design, and more
+- **Run Output** — rendered markdown with collapsible tool call summaries
 
-🔌 **MCP Integration** — Discover, authenticate, and inspect MCP servers. One-click OAuth 2.1 authentication. Assign MCP tools to specific agents.
+## Requirements
 
-🧠 **Agent Memory** — Agents persist context across sessions using `[REMEMBER]` tags stored as markdown.
-
-📊 **Dashboard** — Overview with run charts, success rates, activity timeline, fleet status, and streaming output from active agents.
-
----
+- **Obsidian** 1.6.0 or later (desktop only)
+- **[Claude Code CLI](https://docs.anthropic.com/en/docs/claude-code)** installed and authenticated
+  ```bash
+  npm install -g @anthropic-ai/claude-code
+  claude  # authenticate on first run
+  ```
+- **Claude Max subscription** or Anthropic API key (for Claude Code CLI)
 
-## Quick Start
+## Installation
 
-### Install
+### Via BRAT (recommended — auto-updates)
 
-**Via npm (recommended):**
-```bash
-npm install -g obsidian-agent-fleet
-```
-The installer automatically finds your Obsidian vaults and copies the plugin files.
+1. Install the [BRAT plugin](https://github.com/TfTHacker/obsidian42-brat) from Community Plugins
+2. Open BRAT settings → **Add Beta Plugin**
+3. Paste: `denberek/obsidian-agent-fleet`
+4. Enable **Agent Fleet** in Settings → Community Plugins
 
-**Via BRAT:**
-1. Install the [BRAT plugin](https://github.com/TfTHacker/obsidian42-brat)
-2. Add beta plugin: `denberek/obsidian-agent-fleet`
-3. Enable Agent Fleet in Settings → Community Plugins
+### Manual Install
 
-**Manual:**
-1. Download `main.js`, `manifest.json`, `styles.css` from the [latest release](https://github.com/denberek/obsidian-agent-fleet/releases)
-2. Create `<vault>/.obsidian/plugins/agent-fleet/`
+1. Download `main.js`, `manifest.json`, and `styles.css` from the [latest release](https://github.com/denberek/obsidian-agent-fleet/releases)
+2. Create folder: `<your-vault>/.obsidian/plugins/agent-fleet/`
 3. Copy the 3 files into that folder
-4. Restart Obsidian → Enable Agent Fleet
+4. Restart Obsidian → Settings → Community Plugins → Enable **Agent Fleet**
 
-### Requirements
+## First Launch
 
-- **Obsidian** 1.6.0+ (desktop only)
-- **[Claude Code CLI](https://docs.anthropic.com/en/docs/claude-code)** — the engine behind all agent execution:
-  ```bash
-  npm install -g @anthropic-ai/claude-code
-  claude  # authenticate on first run
-  ```
-- **Claude subscription** (Max or Pro) or **Anthropic API key** — Claude Code works with your existing subscription, no separate API costs. If you're already paying for Claude, you're ready to go.
-
-### First Launch
-
-On first launch, Agent Fleet creates a `_fleet/` folder in your vault:
+On first launch, Agent Fleet creates a `_fleet/` folder in your vault root with:
 
 ```
 _fleet/
 ├── agents/
-│   └── fleet-orchestrator/    ← default agent (manages the fleet)
+│   └── fleet-orchestrator/    ← default agent (knows how to manage the fleet)
 ├── skills/                    ← 18 built-in skills
 ├── tasks/
 ├── runs/
 └── memory/
 ```
 
-The **Fleet Orchestrator** agent is ready — click Chat to ask it to create new agents, tasks, or skills.
-
-### Update
-
-```bash
-npm update -g obsidian-agent-fleet
-```
-
-Or via BRAT: settings → check for updates.
+The **Fleet Orchestrator** agent is ready to use — click **Chat** to ask it to create new agents, tasks, or skills.
 
----
-
-## Features
+## How It Works
 
 ### Agents
 
-Agents are AI assistants with specific personalities, capabilities, and permissions. Each agent is a folder in `_fleet/agents/` containing markdown files:
-
-```
-agents/my-agent/
-├── agent.md       ← Identity: name, description, system prompt
-├── config.md      ← Runtime: model, timeout, permissions
-├── SKILLS.md      ← Agent-specific skills
-└── CONTEXT.md     ← Project context
-```
+Each agent is a folder in `_fleet/agents/<name>/` with these files:
 
-**What you can configure:**
-
-| Setting | Description |
-|---------|-------------|
-| **Name & Description** | Identity shown in the dashboard |
-| **Avatar** | Lucide icon picker (1,400+ icons) or emoji |
-| **System Prompt** | Core instructions that define the agent's behavior |
-| **Model** | Claude Opus 4.6, Sonnet 4.6, Haiku 4.5, Bedrock models, or custom |
-| **Adapter** | Claude Code (more adapters coming soon) |
-| **Working Directory** | Where the agent operates (defaults to vault root) |
-| **Timeout** | Max execution time in seconds |
-| **Permission Mode** | bypassPermissions, dontAsk, acceptEdits, or plan |
-| **Allow/Deny Lists** | Fine-grained tool control (e.g., allow `Bash(curl *)`, deny `Bash(rm -rf *)`) |
-| **Skills** | Shared skills from the skill library |
-| **MCP Servers** | Which MCP servers the agent can access |
-| **Memory** | Persistent context across sessions via `[REMEMBER]` tags |
-
-**Permission Modes:**
-
-| Mode | Behavior |
-|------|----------|
-| `bypassPermissions` | Auto-runs everything except deny list |
-| `dontAsk` | Only allow-listed commands run |
-| `acceptEdits` | File edits auto-approved, bash blocked unless allowed |
-| `plan` | Read-only — no writes, no commands |
+| File | Purpose |
+|------|---------|
+| `agent.md` | Identity, description, system prompt, skill assignments |
+| `config.md` | Model, timeout, permission mode, working directory |
+| `CONTEXT.md` | Project-specific context (optional) |
+| `SKILLS.md` | Agent-specific skills not shared with others (optional) |
+| `permissions.json` | Claude Code allow/deny rules (optional) |
 
+**Example `agent.md`:**
+```yaml
 ---
-
-### Interactive Chat
-
-The chat panel is a first-class Obsidian view — dock it in the sidebar, center, or any split.
-
-**Features:**
-- **Agent Switcher** — dropdown to switch between agents instantly. Each agent has its own conversation.
-- **Session Persistence** — conversations survive Obsidian restarts via Claude CLI `--resume`
-- **Bidirectional Streaming** — send follow-up messages while the agent is working. Steer it mid-task.
-- **Document Attachment** — click + to attach the active document. Agent gets the full content; you see a compact pill.
-- **Image Paste & Drop** — paste from clipboard or drag images into chat. Saved to vault, passed to Claude.
-- **Stop Button** — + button becomes ■ while agent works. Click to abort.
-- **Streaming Markdown** — responses render in real-time with syntax highlighting
-- **Code Block Copy** — hover any code block for a copy button
-- **Tool Activity** — see which tools the agent is using in real-time
-
-**Keyboard shortcuts:**
-- `Ctrl+Enter` / `Cmd+Enter` — send message
-- Ribbon icon (💬) or command palette to open chat
-
+name: site-monitor
+description: Checks website uptime and alerts on failures
+avatar: globe
+enabled: true
+tags: [monitoring]
+skills:
+  - agent-fleet-system
 ---
 
-### Task Board
-
-A kanban view for managing agent tasks with five columns:
+You are a website monitoring agent. Check the specified URL,
+report its HTTP status code, response time, and any errors.
+```
 
-| Column | Description |
-|--------|-------------|
-| **Backlog** | Tasks with no schedule, waiting to be run manually |
-| **Scheduled** | Tasks with a cron schedule, enabled and waiting |
-| **Running** | Currently executing — shows real-time progress bar tied to timeout |
-| **Done** | Completed today |
-| **Failed** | Failed, timed out, or cancelled today |
+### Skills
 
-**Task features:**
-- **Priority** — low / medium / high / critical (color-coded left border)
-- **Real-time Progress** — progress bar shows elapsed time vs timeout, updates every second
-- **Stop Button** — red ■ on running cards to abort (shows as "Cancelled", not "Failed")
-- **Cron Scheduling** — human-friendly picker (daily, weekdays, weekly, monthly, custom)
-- **Catch Up If Missed** — auto-run overdue tasks when Obsidian opens
-- **Run Now** — execute any task immediately regardless of schedule
-- **Drag & Drop** — move tasks between backlog and scheduled columns
+Reusable instruction sets in `_fleet/skills/<name>/`:
 
-**Creating tasks:**
+| File | Purpose |
+|------|---------|
+| `skill.md` | Core instructions and description |
+| `tools.md` | CLI/API tool documentation (optional) |
+| `references.md` | Background docs, conventions (optional) |
+| `examples.md` | Few-shot examples (optional) |
 
-Full-page form with:
-1. Title + Agent + Priority + Tags
-2. Instructions (what the agent should do)
-3. Optional schedule with frequency picker
-4. "Catch up if missed" toggle for scheduled tasks
+Agents reference skills by name in their `agent.md` frontmatter. Multiple agents can share the same skill.
 
----
+### Tasks
 
-### MCP Servers
+Scheduled or one-shot tasks in `_fleet/tasks/<name>.md`:
 
-Discover and manage all MCP (Model Context Protocol) servers configured in Claude Code.
+```yaml
+---
+task_id: check-website
+agent: site-monitor
+schedule: "0 * * * *"    # every hour
+type: recurring
+enabled: true
+---
 
-**Discovery:**
-- **stdio servers** — spawned and probed directly via JSON-RPC (~1-2s)
-- **HTTP/SSE servers** — probed with OAuth tokens for full tool schemas
-- **Plugin metadata** — descriptions from Claude's plugin directory
+Check https://example.com — report status code and response time.
+```
 
-**OAuth 2.1 Authentication:**
+**Task types:**
+- `recurring` — runs on a cron schedule
+- `once` — runs at a specific time (`run_at` field)
+- `immediate` — runs once on creation
 
-One-click browser-based auth for MCP servers:
-1. Click "Authenticate" on any server card
-2. Plugin discovers OAuth endpoints automatically
-3. Registers via Dynamic Client Registration
-4. Opens browser for approval (PKCE flow)
-5. Tokens stored in plugin settings, auto-refresh
+### Chat
 
-**Server Management:**
-- Enable/disable toggle per server (writes to Claude's settings)
-- Server cards show status, tool count, type, description
-- Detail slideover with full tool list, descriptions, input schemas, parameters
-- Assign MCP servers to specific agents in the agent editor
+Click **Chat** on any agent to open an interactive conversation panel. Features:
 
-**Progress Indicator:**
-Animated loading during discovery with phase-specific feedback (scanning → details → tools → done).
+- **Streaming responses** — text appears in real-time as the agent works
+- **Markdown rendering** — headers, lists, code blocks, tables render properly
+- **Tool activity indicator** — shows what the agent is doing ("Working… (Read)")
+- **Collapsible tool summary** — "🔧 12 tool calls" after each response
+- **Session persistence** — close and reopen, your conversation is still there
+- **`--resume` sessions** — Claude CLI maintains full tool context between turns
+- **New Chat** button to start fresh
 
----
+### Run History
 
-### Skills
+Every execution (scheduled or manual) is logged in `_fleet/runs/YYYY-MM-DD/` with:
+- Status (success, failure, timeout, cancelled, pending_approval)
+- Duration, token count, model used
+- Full prompt and output
+- Tools used with commands
 
-Reusable instruction sets that agents share. Each skill is a folder:
+### Agent Memory
 
+When `memory: true` in config, agents can persist context using:
 ```
-skills/my-skill/
-├── skill.md          ← Core instructions
-├── tools.md          ← CLI/API tool documentation
-├── references.md     ← Background docs
-└── examples.md       ← Few-shot examples
+[REMEMBER]Something important to remember[/REMEMBER]
 ```
 
-**18 Built-in Skills:**
+These entries are appended to `_fleet/memory/<agent-name>.md` and included in future prompts.
+
+## Built-in Skills
 
 | Skill | Description |
 |-------|-------------|
@@ -235,74 +168,21 @@ skills/my-skill/
 | `pptx` | Create, read, edit PowerPoint (.pptx) files |
 | `skill-creator` | Create, evaluate, and optimize skills |
 | `slack-gif-creator` | Animated GIFs optimized for Slack |
-| `taste-skill` | Senior UI/UX engineering for frontend design |
-| `frontend-slides` | HTML presentation creation |
-| And more... | |
-
----
-
-### Dashboard
+| `theme-factory` | Apply visual themes to artifacts |
+| `web-artifacts-builder` | Multi-component HTML artifacts with React/Tailwind |
+| `webapp-testing` | Test web apps with Playwright |
+| `xlsx` | Create, read, edit spreadsheet files |
 
-The main overview with:
+## Dashboard
 
-- **Stat Cards** — active agents, runs today, tokens used, scheduled tasks
-- **Run Activity Chart** — 14-day bar chart with green (success), yellow (cancelled), red (failure)
-- **Success Rate Donut** — overall success percentage
-- **Active Agent Cards** — fixed-height streaming output from running agents with agent→task title
-- **Activity Timeline** — recent runs with status, duration, tokens
-- **Fleet Status** — agent list with quick-run capability
+The dashboard provides:
 
-**Additional tabs:**
-- **Agents** — grid of agent cards with stats, toggle, edit, run
-- **Tasks Board** — kanban view (described above)
+- **Overview** — agent status cards with run charts
+- **Agents** — manage agents with enable/disable toggles
+- **Tasks Board** — kanban view of pending, completed, and failed runs
 - **Run History** — searchable table of all executions
-- **Skills Library** — browse, create, and edit skills
-- **Approvals** — pending tool use approvals
-- **MCP Servers** — server discovery and management
-
----
-
-### Agent Memory
-
-Agents persist context across sessions:
-
-1. Agent includes `[REMEMBER]important context[/REMEMBER]` in its output
-2. Extracted and appended to `_fleet/memory/<agent-name>.md`
-3. Injected into the agent's prompt on every future run
-4. The Fleet Orchestrator automatically includes memory instructions when creating new agents
-
----
-
-### Run History
-
-Every execution is logged in `_fleet/runs/YYYY-MM-DD/`:
-
-```yaml
----
-run_id: abc123
-agent: fleet-orchestrator
-task: daily-report
-status: success
-started: 2026-04-03T09:00:00
-completed: 2026-04-03T09:02:30
-duration_seconds: 150
-tokens_used: 4500
-model: claude-opus-4-6
----
-
-## Prompt
-...
-
-## Output
-...
-
-## Tools Used
-...
-```
-
-Click any run in the dashboard to see full details in a slideover panel.
-
----
+- **Skills Library** — browse and manage shared skills
+- **Approvals** — review and approve/reject pending tool uses
 
 ## Configuration
 
@@ -312,56 +192,81 @@ Click any run in the dashboard to see full details in a slideover panel.
 |---------|---------|-------------|
 | Fleet Folder | `_fleet` | Root folder for all fleet data |
 | Claude CLI Path | `claude` | Path to Claude Code CLI |
-| Default Model | `default` | Default model for new agents |
-| AWS Region | `us-east-1` | For AWS Bedrock model support |
-| Max Concurrent Runs | `2` | Parallel task execution limit |
-| Run Log Retention | `30` days | Auto-cleanup old logs |
-| Catch Up Missed Tasks | `true` | Run overdue tasks on startup |
+| Default Model | `default` | Default model for agents |
+| Max Concurrent Runs | `3` | Parallel execution limit |
+| Run Log Retention | `30` days | Auto-cleanup old run logs |
+| Catch Up Missed Tasks | `true` | Run missed tasks on startup |
 | Notification Level | `all` | `all`, `failures-only`, `none` |
 
-### File Structure
+### Agent Permission Modes
 
-All data lives in `_fleet/` as plain markdown:
+| Mode | Behavior |
+|------|----------|
+| `bypassPermissions` | Auto-runs everything except deny list |
+| `dontAsk` | Only allow-listed commands run |
+| `acceptEdits` | File edits auto-approved |
+| `plan` | Read-only, no execution |
+
+## Architecture
 
 ```
-_fleet/
-├── agents/           Agent folders (agent.md, config.md, etc.)
-├── skills/           Shared skill folders (skill.md, tools.md, etc.)
-├── tasks/            Task files with frontmatter
-├── runs/             Execution logs by date
-│   └── YYYY-MM-DD/
-├── memory/           Agent memory files
-└── chat-images/      Images pasted into chat
+src/
+├── main.ts                    Plugin entry point
+├── defaults.ts                Embedded default agents + skills
+├── fleetRepository.ts         File I/O and vault management
+├── types.ts                   TypeScript interfaces
+├── constants.ts               View types and defaults
+├── settingsTab.ts             Plugin settings UI
+├── services/
+│   ├── chatSession.ts         Interactive chat with --resume
+│   ├── executionManager.ts    Claude CLI process spawning
+│   ├── fleetRuntime.ts        Runtime state and orchestration
+│   └── taskScheduler.ts       Cron-based task scheduling
+├── views/
+│   ├── dashboardView.ts       Main dashboard (3700+ lines)
+│   ├── agentsView.ts          Sidebar agent list
+│   ├── sidebarView.ts         Navigation sidebar
+│   └── inboxView.ts           Inbox view
+├── modals/
+│   ├── iconPickerModal.ts     Lucide icon selector
+│   ├── taskModal.ts           Task creation
+│   ├── createAgentModal.ts    Agent creation wizard
+│   └── confirmDeleteModal.ts  Deletion confirmation
+├── components/
+│   ├── chartRenderer.ts       Bar and donut charts
+│   ├── dragDrop.ts            Drag and drop utilities
+│   └── scheduleEditor.ts      Cron schedule editor
+└── utils/
+    ├── icons.ts               Icon helper
+    └── markdown.ts            Frontmatter parser
 ```
 
-Everything is searchable, version-controllable, and fully yours.
+## Development
 
----
-
-## FAQ
-
-**Q: Do I need an API key?**
-Not necessarily. Agent Fleet works with your **Claude Max or Pro subscription** via Claude Code CLI. No separate API key or billing. If you prefer, you can also use an Anthropic API key directly.
+```bash
+# Clone
+git clone https://github.com/denberek/obsidian-agent-fleet.git
+cd obsidian-agent-fleet
 
-**Q: Does it work without internet?**
-No — agents need the Claude API to run. But all your data (agents, tasks, skills, memory) is local markdown.
+# Install dependencies
+npm install
 
-**Q: Can I use different models per agent?**
-Yes. Each agent has its own model setting. Supports Anthropic direct (Opus, Sonnet, Haiku) and AWS Bedrock models.
+# Development build (watches for changes)
+npm run dev
 
-**Q: What happens if I delete the plugin?**
-Your `_fleet/` folder stays. All agents, tasks, skills, run logs, and memory are plain markdown files in your vault.
+# Production build
+npm run build
 
-**Q: Can multiple agents run at the same time?**
-Yes, up to `maxConcurrentRuns` (default 2). Additional tasks queue until a slot opens.
+# Type check
+npx tsc --noEmit
 
-**Q: Does the chat remember previous conversations?**
-Yes. Each agent has persistent chat sessions that survive Obsidian restarts via Claude CLI `--resume`.
+# Run tests
+npm test
 
----
+# Symlink to vault for development
+ln -s $(pwd) ~/path-to-vault/.obsidian/plugins/agent-fleet
+```
 
-## Links
+## License
 
-- [Releases](https://github.com/denberek/obsidian-agent-fleet/releases)
-- [npm package](https://www.npmjs.com/package/obsidian-agent-fleet)
-- [Report Issues](https://github.com/denberek/obsidian-agent-fleet/issues)
+MIT

package/bin/cli.js

@@ -37,7 +37,6 @@ function getVaults() {
 
 function resolveClaudePath() {
   const { execSync } = require("child_process");
-  // Try to resolve claude full path via login shell (picks up nvm/fnm/etc)
   const shells = ["/bin/zsh", "/bin/bash", "/bin/sh"];
   for (const shell of shells) {
     if (!fs.existsSync(shell)) continue;
@@ -57,14 +56,12 @@ function writePluginSettings(vaultPath, claudePath) {
   const dataPath = path.join(vaultPath, ".obsidian", "plugins", PLUGIN_ID, "data.json");
 
   let settings = {};
-  // Preserve existing settings if they exist
   if (fs.existsSync(dataPath)) {
     try {
       settings = JSON.parse(fs.readFileSync(dataPath, "utf8"));
     } catch { /* start fresh */ }
   }
 
-  // Only set claudeCliPath if we found it and user hasn't manually set one
   if (claudePath && (!settings.claudeCliPath || settings.claudeCliPath === "claude")) {
     settings.claudeCliPath = claudePath;
   }
@@ -75,10 +72,8 @@ function writePluginSettings(vaultPath, claudePath) {
 function installToVault(vaultPath) {
   const pluginDir = path.join(vaultPath, ".obsidian", "plugins", PLUGIN_ID);
 
-  // Ensure directories exist
   fs.mkdirSync(pluginDir, { recursive: true });
 
-  // Copy plugin files
   const files = ["main.js", "manifest.json", "styles.css"];
   for (const file of files) {
     const src = path.join(PLUGIN_DIR, file);
@@ -100,17 +95,16 @@ function main() {
     const vaults = getVaults();
 
     if (vaults.length === 0) {
-      if (isAuto) return; // Silent fail for postinstall
+      if (isAuto) return;
       console.error("❌ No Obsidian vaults found.");
       console.error("   Make sure Obsidian is installed and has at least one vault.");
       console.error("");
       console.error("   Manual install:");
-      console.error("   Copy the files from node_modules/agent-fleet/plugin/");
+      console.error("   Copy the files from node_modules/obsidian-agent-fleet/plugin/");
       console.error("   to <your-vault>/.obsidian/plugins/agent-fleet/");
       process.exit(1);
     }
 
-    // Resolve Claude CLI full path
     const claudePath = resolveClaudePath();
     if (!isAuto) {
       if (claudePath) {
@@ -120,7 +114,6 @@ function main() {
       }
     }
 
-    // Install to all vaults
     let installed = 0;
     for (const vault of vaults) {
       try {

package/package.json

@@ -1,31 +1,36 @@
 {
   "name": "obsidian-agent-fleet",
-  "version": "0.3.2",
-  "description": "Agent Fleet for Obsidian \u2014 AI agents, task scheduling, and interactive chat",
-  "author": "Denis Berekchiyan",
-  "license": "UNLICENSED",
+  "version": "0.4.2",
+  "description": "Obsidian plugin for file-backed AI agents, task scheduling, channels (Slack), heartbeat, and interactive chat.",
+  "main": "plugin/main.js",
   "bin": {
-    "obsidian-agent-fleet": "./bin/cli.js"
+    "agent-fleet": "bin/cli.js"
   },
   "files": [
-    "bin/",
-    "plugin/",
+    "bin/cli.js",
+    "plugin/main.js",
+    "plugin/manifest.json",
+    "plugin/styles.css",
     "README.md"
   ],
-  "keywords": [
-    "obsidian",
-    "ai",
-    "agent",
-    "claude",
-    "task",
-    "automation"
-  ],
-  "repository": {
-    "type": "git",
-    "url": "https://github.com/denberek/obsidian-agent-fleet"
-  },
-  "homepage": "https://github.com/denberek/obsidian-agent-fleet",
   "scripts": {
-    "postinstall": "node bin/cli.js install --auto 2>/dev/null || true"
+    "build": "node esbuild.config.mjs production",
+    "dev": "node esbuild.config.mjs",
+    "test": "vitest run",
+    "typecheck": "tsc --noEmit"
+  },
+  "devDependencies": {
+    "@types/node": "^24.5.2",
+    "@types/ws": "^8.18.1",
+    "builtin-modules": "^4.0.0",
+    "esbuild": "^0.25.9",
+    "obsidian": "^1.8.10",
+    "tslib": "^2.8.1",
+    "typescript": "^5.9.2",
+    "vitest": "^3.2.4"
+  },
+  "dependencies": {
+    "croner": "^8.1.2",
+    "ws": "^8.20.0"
   }
-}
+}