oh-my-opencode-slim 0.9.13 → 0.9.15

package/README.md

@@ -1,8 +1,8 @@
 <div align="center">
-  <img src="img/team.png" alt="Pantheon agents" style="border-radius: 10px;" width="620">
+  <img src="img/team.jpeg" alt="Pantheon agents" style="border-radius: 10px;">
   <p><i>Seven divine beings emerged from the dawn of code, each an immortal master of their craft await your command to forge order from chaos and build what was once thought impossible.</i></p>
   <p><b>Open Multi Agent Suite</b> · Mix any models · Auto delegate tasks</p>
-  <p><a href="https://moltfounders.com/jobs/09d1c6e7-9e0e-4683-8d78-e2376aaa2333"><img src="https://moltfounders.com/badges/4.png" alt="MoltFounders" height="30"></a></p>
+
   <p><sub>by <b>Boring Dystopia Development</b></sub></p>
   <p>
     <a href="https://boringdystopia.ai/"><img src="https://img.shields.io/badge/boringdystopia.ai-111111?style=for-the-badge&logo=vercel&logoColor=white" alt="boringdystopia.ai"></a>&nbsp;
@@ -13,7 +13,13 @@
 
 ---
 
-## 📦 Installation
+## What's This Plugin
+
+oh-my-opencode-slim is an agent orchestration plugin for OpenCode. It includes a built-in team of specialized agents that can scout a codebase, look up fresh documentation, review architecture, handle UI work, and execute well-scoped implementation tasks under one orchestrator.
+
+The main idea is simple: instead of forcing one model to do everything, the plugin routes each part of the job to the agent best suited for it, balancing **quality, speed and cost**.
+
+To explore the agents themselves, see **[Meet the Pantheon](#meet-the-pantheon)**. For the full feature set, see **[Features & Workflows](#features-and-workflows)** below.
 
 ### Quick Start
 
@@ -21,49 +27,53 @@
 bunx oh-my-opencode-slim@latest install
 ```
 
-The installer generates an OpenAI configuration by default (using `gpt-5.4` and `gpt-5.4-mini`). No provider questions asked.
+### Getting Started
 
-For non-interactive mode:
+The installer generates an OpenAI preset by default, using `openai/gpt-5.4` for the higher-judgment agents and `openai/gpt-5.4-mini` for the faster scoped agents.
 
-```bash
-bunx oh-my-opencode-slim@latest install --no-tui --tmux=yes --skills=yes
-```
+Then:
 
-To force overwrite of an existing configuration:
-```bash
-bunx oh-my-opencode-slim@latest install --reset
-```
+1. **Log in to the providers you want to use if you haven't already**:
 
-### For Alternative Providers
+   ```bash
+   opencode auth login
+   ```
+2. **Refresh and list the models OpenCode can see**:
 
-The default configuration uses OpenAI. To use Kimi, GitHub Copilot, or ZAI Coding Plan, see **[Provider Configurations](docs/provider-configurations.md)** for step-by-step instructions and config examples.
+   ```bash
+   opencode models --refresh
+   ```
+3. **Open your plugin config** at `~/.config/opencode/oh-my-opencode-slim.json`
 
-> [!TIP]
-> Want to see the latest models OpenCode knows about? Run `opencode models --refresh` to refresh the cache and list currently available models.
+4. **Update the models you want for each agent**
 
-### JSON Schema
+> [!TIP]
+> Want to understand how automatic delegation works in practice? Review the **[Orchestrator prompt](https://github.com/alvinunreal/oh-my-opencode-slim/blob/master/src/agents/orchestrator.ts#L28)** — it contains the delegation rules, specialist routing logic, and the thresholds for when the main agent should hand work off to subagents.
 
-An official JSON Schema is included in the package for editor validation and autocomplete. Add a `$schema` reference to your config file:
+The default generated configuration looks like this:
 
 ```jsonc
 {
   "$schema": "https://unpkg.com/oh-my-opencode-slim@latest/oh-my-opencode-slim.schema.json",
-  // your config...
+  "preset": "openai",
+  "presets": {
+    "openai": {
+      "orchestrator": { "model": "openai/gpt-5.4", "variant": "high", "skills": ["*"], "mcps": ["*", "!context7"] },
+      "oracle": { "model": "openai/gpt-5.4", "variant": "high", "skills": ["simplify"], "mcps": [] },
+      "librarian": { "model": "openai/gpt-5.4-mini", "variant": "low", "skills": [], "mcps": ["websearch", "context7", "grep_app"] },
+      "explorer": { "model": "openai/gpt-5.4-mini", "variant": "low", "skills": ["cartography"], "mcps": [] },
+      "designer": { "model": "openai/gpt-5.4-mini", "variant": "medium", "skills": ["agent-browser"], "mcps": [] },
+      "fixer": { "model": "openai/gpt-5.4-mini", "variant": "low", "skills": [], "mcps": [] }
+    }
+  }
 }
 ```
 
-This enables autocomplete and inline validation in VS Code, Neovim, and other editors that support JSON Schema.
+### For Alternative Providers
 
-### For LLM Agents
+To use Kimi, GitHub Copilot, ZAI Coding Plan, or a mixed-provider setup, see **[Provider Configurations](docs/provider-configurations.md)** for step-by-step config examples. If you want a ready-made starting point, check the **[Author's Preset](docs/authors-preset.md)** and **[$30 Preset](docs/thirty-dollars-preset.md)** - the `$30` preset is the best cheap setup.
 
-Paste this into any coding agent:
-
-```
-Install and configure by following the instructions here:
-https://raw.githubusercontent.com/alvinunreal/oh-my-opencode-slim/refs/heads/master/README.md
-```
-
-**Detailed installation guide:** [docs/installation.md](docs/installation.md)
+You can also mix and match any models per agent. For model suggestions, see the **Recommended Models** listed under each agent below.
 
 ### ✅ Verify Your Setup
 
@@ -88,6 +98,8 @@ If any agent fails to respond, check your provider authentication and config fil
 
 ---
 
+<a id="meet-the-pantheon"></a>
+
 ## 🏛️ Meet the Pantheon
 
 ### 01. Orchestrator: The Embodiment Of Order
@@ -122,6 +134,11 @@ If any agent fails to respond, check your provider authentication and config fil
       <b>Recommended Models:</b> <code>openai/gpt-5.4</code> <code>anthropic/claude-opus-4.6</code>
     </td>
   </tr>
+  <tr>
+    <td colspan="2">
+      <b>Model Guidance:</b> Choose your default, strongest all-around coding model. Orchestrator is both the main coding agent and the delegator, so it needs strong implementation ability, good judgment, and reliable instruction-following.
+    </td>
+  </tr>
 </table>
 
 ---
@@ -158,6 +175,11 @@ If any agent fails to respond, check your provider authentication and config fil
       <b>Recommended Models:</b> <code>cerebras/zai-glm-4.7</code> <code>fireworks-ai/accounts/fireworks/routers/kimi-k2p5-turbo</code> <code>openai/gpt-5.4-mini</code>
     </td>
   </tr>
+  <tr>
+    <td colspan="2">
+      <b>Model Guidance:</b> Choose a fast, low-cost model. Explorer handles broad scouting work, so speed and efficiency usually matter more than using your strongest reasoning model.
+    </td>
+  </tr>
 </table>
 
 ---
@@ -194,12 +216,20 @@ If any agent fails to respond, check your provider authentication and config fil
       <b>Recommended Models:</b> <code>openai/gpt-5.4 (high)</code> <code>google/gemini-3.1-pro-preview (high)</code>
     </td>
   </tr>
+  <tr>
+    <td colspan="2">
+      <b>Model Guidance:</b> Choose your strongest high-reasoning model for architecture, hard debugging, trade-offs, and code review.
+    </td>
+  </tr>
 </table>
 
 ---
 
 ### Council: The Chorus of Minds
 
+> [!NOTE]
+> **Why doesn't Orchestrator auto-call Council more often?** This is intentional. Council runs multiple models at once, so automatic delegation is kept strict because it is usually the highest-cost path in the system. In practice, Council is meant to be used manually when you want it, for example: <code>@council compare these two architectures</code>.
+
 <table>
   <tr>
     <td width="30%" align="center" valign="top">
@@ -235,6 +265,11 @@ If any agent fails to respond, check your provider authentication and config fil
       <b>Recommended Setup:</b> <code>Strong master</code> + <code>diverse councillors</code> across providers
     </td>
   </tr>
+  <tr>
+    <td colspan="2">
+      <b>Model Guidance:</b> Use a strong synthesis model as the master and diverse models as councillors. The value of Council comes from comparing different model perspectives, not just picking the single strongest model everywhere.
+    </td>
+  </tr>
 </table>
 
 ---
@@ -271,6 +306,11 @@ If any agent fails to respond, check your provider authentication and config fil
       <b>Recommended Models:</b> <code>cerebras/zai-glm-4.7</code> <code>fireworks-ai/accounts/fireworks/routers/kimi-k2p5-turbo</code> <code>openai/gpt-5.4-mini</code>
     </td>
   </tr>
+  <tr>
+    <td colspan="2">
+      <b>Model Guidance:</b> Choose a fast, low-cost model. Librarian handles research and documentation lookups, so speed and efficiency usually matter more than using your strongest reasoning model.
+    </td>
+  </tr>
 </table>
 
 ---
@@ -307,6 +347,11 @@ If any agent fails to respond, check your provider authentication and config fil
       <b>Recommended Models:</b> <code>google/gemini-3.1-pro-preview</code> <code>kimi-for-coding/k2p5</code> 
     </td>
   </tr>
+  <tr>
+    <td colspan="2">
+      <b>Model Guidance:</b> Choose a model that is strong at UI/UX judgment, frontend implementation, and visual polish.
+    </td>
+  </tr>
 </table>
 
 ---
@@ -343,12 +388,17 @@ If any agent fails to respond, check your provider authentication and config fil
       <b>Recommended Models:</b> <code>cerebras/zai-glm-4.7</code> <code>fireworks-ai/accounts/fireworks/routers/kimi-k2p5-turbo</code> <code>openai/gpt-5.4-mini</code>
     </td>
   </tr>
+  <tr>
+    <td colspan="2">
+      <b>Model Guidance:</b> Choose a fast, reliable coding model for routine, scoped implementation work. Fixer usually receives a concrete plan or bounded instructions from Orchestrator, making it a good place for efficient execution tasks such as tests, test updates, and straightforward code changes.
+    </td>
+  </tr>
 </table>
 
 ### 07. Observer: The Silent Witness
 
 > [!NOTE]
-> **Why a separate agent?** Not all models support vision. Your strongest coding model (e.g. for design decisions) may not be able to read images, while a vision-capable model may not be the best for reasoning. Observer solves this by having its **own model** — configure a vision-capable model for it while keeping Designer on your strongest reasoning model. Disabled by default; enable via `disabled_agents: []` in config.
+> **Why a separate agent?** If your Orchestrator model is not multimodal, enable Observer to handle images, screenshots, PDFs, and other visual files. Observer is disabled by default and gives the Orchestrator a dedicated multimodal reader without forcing you to change your main reasoning model. Set `disabled_agents: []` and an `observer` model in your configuration.
 
 <table>
   <tr>
@@ -376,45 +426,53 @@ If any agent fails to respond, check your provider authentication and config fil
       <b>Default Model:</b> <code>openai/gpt-5.4-mini</code> — <i>configure a vision-capable model to enable</i>
     </td>
   </tr>
+  <tr>
+    <td colspan="2">
+      <b>Model Guidance:</b> Choose a vision-capable model if you want the agent to read screenshots, images, PDFs, and other visual files.
+    </td>
+  </tr>
 </table>
 
 ---
 
 ## 📚 Documentation
 
-### 🚀 Getting Started
+Use this section as a map: start with installation, then jump to features, configuration, or example presets depending on what you need.
 
-| Doc | Contents |
-|-----|----------|
-| **[Installation Guide](docs/installation.md)** | CLI flags, `--reset`, auth, troubleshooting |
-| **[Provider Configurations](docs/provider-configurations.md)** | OpenAI, Kimi, Copilot, ZAI, Fireworks AI — mixing providers, fallback chains |
+### 🚀 Start Here
 
-### ✨ Features
+| Doc | What it covers |
+|-----|----------------|
+| **[Installation Guide](docs/installation.md)** | Install the plugin, use CLI flags, reset config, and troubleshoot setup |
+| **[Provider Configurations](docs/provider-configurations.md)** | Configure OpenAI, Kimi, GitHub Copilot, ZAI, Fireworks AI, or mixed-provider presets |
 
-| Feature | Doc | What it does |
-|---------|-----|--------------|
-| **Council** | [council.md](docs/council.md) | Run N models in parallel, synthesize one answer (`@council`) |
-| **Interview** | [interview.md](docs/interview.md) | Browser-based Q&A flow for turning rough ideas into a live markdown spec |
-| **Multiplexer Integration** | [multiplexer-integration.md](docs/multiplexer-integration.md) | Watch agents work in real-time with auto-spawned panes (Tmux/Zellij) |
-| **Cartography Skill** | [cartography.md](docs/cartography.md) | Auto-generate hierarchical codemaps for any codebase |
+<a id="features-and-workflows"></a>
 
-### ⚙️ Config & Reference
+### ✨ Features & Workflows
+
+| Doc | What it covers |
+|-----|----------------|
+| **[Council](docs/council.md)** | Run multiple models in parallel and synthesize a single answer with `@council` |
+| **[Interview](docs/interview.md)** | Turn rough ideas into a structured markdown spec through a browser-based Q&A flow |
+| **[Multiplexer Integration](docs/multiplexer-integration.md)** | Watch agents work live in Tmux or Zellij panes |
+| **[Todo Continuation](docs/todo-continuation.md)** | Auto-continue orchestrator sessions with cooldowns and safety checks |
+| **[Cartography](docs/cartography.md)** | Generate hierarchical codemaps to understand large codebases faster |
 
-| Doc | Contents |
-|-----|----------|
-| **[Skills](docs/skills.md)** | `simplify`, `agent-browser`, `cartography` — assignment syntax |
-| **[MCPs](docs/mcps.md)** | `websearch`, `context7`, `grep_app` — permissions per agent |
-| **[Tools](docs/tools.md)** | Background tasks, LSP, code search, formatters |
-| **[Configuration](docs/configuration.md)** | Config files, prompt overriding, JSONC, full option reference |
+### ⚙️ Config & Reference
 
-Slim only intercepts `apply_patch` before native execution. It rewrites recoverable stale patches, canonizes safe tolerant matches against the real file when unicode/trim drift is the only mismatch, keeps the authored `new_lines` bytes intact, preserves existing file EOL/final-newline state for updates, validates malformed patches strictly before helper execution, uses a conservative bounded LCS fallback, supports sequential `Update File` hunks on the same path through accumulated helper state, and blocks `apply_patch` before the native tool runs if any patch path falls outside the allowed root/worktree. This rescue does not extend to `edit` or `write`.
+| Doc | What it covers |
+|-----|----------------|
+| **[Configuration](docs/configuration.md)** | Config file locations, JSONC support, prompt overrides, and full option reference |
+| **[Skills](docs/skills.md)** | Built-in and recommended skills such as `simplify`, `agent-browser`, and `cartography` |
+| **[MCPs](docs/mcps.md)** | `websearch`, `context7`, `grep_app`, and how MCP permissions work per agent |
+| **[Tools](docs/tools.md)** | Built-in tool capabilities like background tasks, `webfetch`, LSP tools, code search, and formatters |
 
-### 💡 Presets
+### 💡 Example Presets
 
-| Doc | Contents |
-|-----|----------|
-| **[Author's Preset](docs/authors-preset.md)** | The exact config the author runs daily — OpenAI Pro + GitHub Copilot |
-| **[$30 Preset](docs/thirty-dollars-preset.md)** | A mixed setup using Codex Plus ($20) + GitHub Copilot Pro ($10) for about $30/month total |
+| Doc | What it covers |
+|-----|----------------|
+| **[Author's Preset](docs/authors-preset.md)** | The author's daily mixed-provider setup |
+| **[$30 Preset](docs/thirty-dollars-preset.md)** | A budget mixed-provider setup for around $30/month |
 
 ---
 
@@ -425,7 +483,7 @@ Slim only intercepts `apply_patch` before native execution. It rewrites recovera
   <p><sub>Every merged contribution leaves a mark on the realm.</sub></p>
 
   <!-- ALL-CONTRIBUTORS-BADGE:START - Do not remove or modify this section -->
-[![All Contributors](https://img.shields.io/badge/all_contributors-38-orange.svg?style=flat-square)](#contributors-)
+[![All Contributors](https://img.shields.io/badge/all_contributors-40-orange.svg?style=flat-square)](#contributors-)
 <!-- ALL-CONTRIBUTORS-BADGE:END -->
 </div>
 
@@ -487,6 +545,8 @@ Slim only intercepts `apply_patch` before native execution. It rewrites recovera
     <tr>
       <td align="center" valign="top" width="16.66%"><a href="https://github.com/dkovacevic15"><img src="https://avatars.githubusercontent.com/u/24757821?v=4?s=100" width="100px;" alt="Dusan Kovacevic"/><br /><sub><b>Dusan Kovacevic</b></sub></a><br /><a href="https://github.com/alvinunreal/oh-my-opencode-slim/commits?author=dkovacevic15" title="Code">💻</a></td>
       <td align="center" valign="top" width="16.66%"><a href="https://github.com/jwcrystal"><img src="https://avatars.githubusercontent.com/u/121911854?v=4?s=100" width="100px;" alt="jwcrystal"/><br /><sub><b>jwcrystal</b></sub></a><br /><a href="https://github.com/alvinunreal/oh-my-opencode-slim/commits?author=jwcrystal" title="Code">💻</a></td>
+      <td align="center" valign="top" width="16.66%"><a href="https://zenstudio.cv/"><img src="https://avatars.githubusercontent.com/u/10528635?v=4?s=100" width="100px;" alt="Nguyen Canh Toan"/><br /><sub><b>Nguyen Canh Toan</b></sub></a><br /><a href="https://github.com/alvinunreal/oh-my-opencode-slim/commits?author=ZenStudioLab" title="Code">💻</a></td>
+      <td align="center" valign="top" width="16.66%"><a href="https://github.com/tom-dyar"><img src="https://avatars.githubusercontent.com/u/8899513?v=4?s=100" width="100px;" alt="Thomas Dyar"/><br /><sub><b>Thomas Dyar</b></sub></a><br /><a href="https://github.com/alvinunreal/oh-my-opencode-slim/commits?author=tom-dyar" title="Code">💻</a></td>
     </tr>
   </tbody>
 </table>

package/dist/agents/orchestrator.d.ts

@@ -1,6 +1,7 @@
-import type { AgentConfig } from '@opencode-ai/sdk/v2';
+import type { AgentConfig } from "@opencode-ai/sdk/v2";
 export interface AgentDefinition {
     name: string;
+    displayName?: string;
     description?: string;
     config: AgentConfig;
     /** Priority-ordered model entries for runtime fallback resolution. */

package/dist/background/background-manager.d.ts

@@ -65,6 +65,11 @@ export declare class BackgroundTaskManager {
      * to add new background agent types without updating SUBAGENT_DELEGATION_RULES.
      */
     private getSubagentRules;
+    /**
+     * Resolve the agent associated with a session.
+     * Untracked sessions are treated as orchestrator sessions by default.
+     */
+    private getSessionAgent;
     /**
      * Check if a parent session is allowed to delegate to a specific agent type.
      * @param parentSessionId - The session ID of the parent
@@ -154,8 +159,11 @@ export declare class BackgroundTaskManager {
     /**
      * Retrieve the current state of a background task.
      *
+     * Checks in-memory first. If not found (e.g. after plugin reinitialization
+     * caused by context compaction), falls back to the persisted state on disk.
+     *
      * @param taskId - The task ID to retrieve
-     * @returns The task object, or null if not found
+     * @returns The task object, or null if not found in memory or on disk
      */
     getResult(taskId: string): BackgroundTask | null;
     /**

package/dist/background/multiplexer-session-manager.d.ts

@@ -10,6 +10,7 @@ interface SessionEvent {
             id?: string;
             parentID?: string;
             title?: string;
+            directory?: string;
         };
         sessionID?: string;
         status?: {
@@ -26,6 +27,7 @@ interface SessionEvent {
 export declare class MultiplexerSessionManager {
     private client;
     private serverUrl;
+    private directory;
     private multiplexer;
     private sessions;
     private pollInterval?;

package/dist/cli/index.js

@@ -13755,7 +13755,8 @@ var AgentOverrideConfigSchema = exports_external.object({
   variant: exports_external.string().optional().catch(undefined),
   skills: exports_external.array(exports_external.string()).optional(),
   mcps: exports_external.array(exports_external.string()).optional(),
-  options: exports_external.record(exports_external.string(), exports_external.unknown()).optional()
+  options: exports_external.record(exports_external.string(), exports_external.unknown()).optional(),
+  displayName: exports_external.string().min(1).optional()
 });
 var MultiplexerTypeSchema = exports_external.enum(["auto", "tmux", "zellij", "none"]);
 var MultiplexerLayoutSchema = exports_external.enum([
@@ -13809,6 +13810,7 @@ var PluginConfigSchema = exports_external.object({
   setDefaultAgent: exports_external.boolean().optional(),
   scoringEngineVersion: exports_external.enum(["v1", "v2-shadow", "v2"]).optional(),
   balanceProviderUsage: exports_external.boolean().optional(),
+  showStartupToast: exports_external.boolean().optional().describe("Show the startup activation toast when OpenCode starts. Defaults to true."),
   manualPlan: ManualPlanSchema.optional(),
   presets: exports_external.record(exports_external.string(), PresetSchema).optional(),
   agents: exports_external.record(exports_external.string(), AgentOverrideConfigSchema).optional(),
@@ -13825,7 +13827,7 @@ var PluginConfigSchema = exports_external.object({
 });
 // src/config/agent-mcps.ts
 var DEFAULT_AGENT_MCPS = {
-  orchestrator: ["*"],
+  orchestrator: ["*", "!context7"],
   designer: [],
   oracle: [],
   librarian: ["websearch", "context7", "grep_app"],
@@ -13837,9 +13839,6 @@ var DEFAULT_AGENT_MCPS = {
   "council-master": []
 };
 
-// src/cli/skills.ts
-import { spawnSync } from "node:child_process";
-
 // src/cli/custom-skills.ts
 import {
   copyFileSync,
@@ -13851,6 +13850,12 @@ import {
 import { dirname as dirname2, join as join2 } from "node:path";
 import { fileURLToPath } from "node:url";
 var CUSTOM_SKILLS = [
+  {
+    name: "simplify",
+    description: "Code simplification and readability-focused refactoring",
+    allowedAgents: ["oracle"],
+    sourcePath: "src/skills/simplify"
+  },
   {
     name: "cartography",
     description: "Repository understanding and hierarchical codemap generation",
@@ -13899,14 +13904,8 @@ function installCustomSkill(skill) {
 }
 
 // src/cli/skills.ts
+import { spawnSync } from "node:child_process";
 var RECOMMENDED_SKILLS = [
-  {
-    name: "simplify",
-    repo: "https://github.com/brianlovin/claude-config",
-    skillName: "simplify",
-    allowedAgents: ["oracle"],
-    description: "YAGNI code simplification expert"
-  },
   {
     name: "agent-browser",
     repo: "https://github.com/vercel-labs/agent-browser",
@@ -13955,6 +13954,7 @@ function installSkill(skill) {
 }
 
 // src/cli/providers.ts
+var SCHEMA_URL = "https://unpkg.com/oh-my-opencode-slim@latest/oh-my-opencode-slim.schema.json";
 var MODEL_MAPPINGS = {
   openai: {
     orchestrator: { model: "openai/gpt-5.4" },
@@ -13994,12 +13994,16 @@ var MODEL_MAPPINGS = {
 };
 function generateLiteConfig(installConfig) {
   const config2 = {
+    $schema: SCHEMA_URL,
     preset: "openai",
     presets: {}
   };
   const createAgentConfig = (agentName, modelInfo) => {
     const isOrchestrator = agentName === "orchestrator";
-    const skills = isOrchestrator ? ["*"] : RECOMMENDED_SKILLS.filter((s) => s.allowedAgents.includes("*") || s.allowedAgents.includes(agentName)).map((s) => s.skillName);
+    const skills = isOrchestrator ? ["*"] : [
+      ...RECOMMENDED_SKILLS.filter((s) => s.allowedAgents.includes("*") || s.allowedAgents.includes(agentName)).map((s) => s.skillName),
+      ...CUSTOM_SKILLS.filter((s) => s.allowedAgents.includes("*") || s.allowedAgents.includes(agentName)).map((s) => s.name)
+    ];
     if (agentName === "designer" && !skills.includes("agent-browser")) {
       skills.push("agent-browser");
     }
@@ -14457,13 +14461,13 @@ var BOLD = "\x1B[1m";
 var DIM = "\x1B[2m";
 var RESET = "\x1B[0m";
 var SYMBOLS = {
-  check: `${GREEN}✓${RESET}`,
-  cross: `${RED}✗${RESET}`,
-  arrow: `${BLUE}→${RESET}`,
-  bullet: `${DIM}•${RESET}`,
-  info: `${BLUE}ℹ${RESET}`,
-  warn: `${YELLOW}⚠${RESET}`,
-  star: `${YELLOW}★${RESET}`
+  check: `${GREEN}[ok]${RESET}`,
+  cross: `${RED}[x]${RESET}`,
+  arrow: `${BLUE}->${RESET}`,
+  bullet: `${DIM}-${RESET}`,
+  info: `${BLUE}[i]${RESET}`,
+  warn: `${YELLOW}[!]${RESET}`,
+  star: `${YELLOW}*${RESET}`
 };
 function printHeader(isUpdate) {
   console.log();
@@ -14510,19 +14514,6 @@ function handleStepResult(result, successMsg) {
   printSuccess(`${successMsg} ${SYMBOLS.arrow} ${DIM}${result.configPath}${RESET}`);
   return true;
 }
-function formatConfigSummary() {
-  const lines = [];
-  lines.push(`${BOLD}Configuration Summary${RESET}`);
-  lines.push("");
-  lines.push(`  ${BOLD}Preset:${RESET} ${BLUE}openai${RESET}`);
-  lines.push(`  ${SYMBOLS.check} OpenAI (default)`);
-  const seeDocs = "see docs/provider-configurations.md";
-  lines.push(`  ${DIM}○ Kimi — ${seeDocs}${RESET}`);
-  lines.push(`  ${DIM}○ GitHub Copilot — ${seeDocs}${RESET}`);
-  lines.push(`  ${DIM}○ ZAI Coding Plan — ${seeDocs}${RESET}`);
-  return lines.join(`
-`);
-}
 async function runInstall(config2) {
   const detected = detectCurrentConfig();
   const isUpdate = detected.isInstalled;
@@ -14565,12 +14556,12 @@ async function runInstall(config2) {
 ${JSON.stringify(liteConfig, null, 2)}
 `);
   } else {
-    const configPath = getExistingLiteConfigPath();
-    const configExists = existsSync4(configPath);
+    const configPath2 = getExistingLiteConfigPath();
+    const configExists = existsSync4(configPath2);
     if (configExists && !config2.reset) {
-      printInfo(`Configuration already exists at ${configPath}. ` + "Use --reset to overwrite.");
+      printInfo(`Configuration already exists at ${configPath2}. ` + "Use --reset to overwrite.");
     } else {
-      const liteResult = writeLiteConfig(config2, configExists ? configPath : undefined);
+      const liteResult = writeLiteConfig(config2, configExists ? configPath2 : undefined);
       if (!handleStepResult(liteResult, configExists ? "Config reset" : "Config written"))
         return 1;
     }
@@ -14618,21 +14609,31 @@ ${JSON.stringify(liteConfig, null, 2)}
       printSuccess(`${customSkillsInstalled}/${totalCustom} custom skills processed`);
     }
   }
-  console.log();
-  console.log(formatConfigSummary());
-  console.log();
   const statusMsg = isUpdate ? "Configuration updated!" : "Installation complete!";
   console.log(`${SYMBOLS.star} ${BOLD}${GREEN}${statusMsg}${RESET}`);
   console.log();
   console.log(`${BOLD}Next steps:${RESET}`);
   console.log();
-  console.log(`  1. Start OpenCode:`);
+  const configPath = getExistingLiteConfigPath();
+  console.log("  1. Log in to the provider(s) you want to use:");
+  console.log(`     ${BLUE}$ opencode auth login${RESET}`);
+  console.log();
+  console.log("  2. Refresh the models OpenCode can see:");
+  console.log(`     ${BLUE}$ opencode models --refresh${RESET}`);
+  console.log();
+  console.log("  3. Review your generated config:");
+  console.log(`     ${BLUE}${configPath}${RESET}`);
+  console.log();
+  console.log("  4. Start OpenCode:");
   console.log(`     ${BLUE}$ opencode${RESET}`);
   console.log();
+  console.log("  5. Verify the agents are responding:");
+  console.log(`     ${BLUE}> ping all agents${RESET}`);
+  console.log();
   const modelsInfo = "Default configuration uses OpenAI models (gpt-5.4 / gpt-5.4-mini).";
-  console.log(`${BOLD}${modelsInfo}${RESET}`);
+  console.log(`${modelsInfo}`);
   const altProviders = "For alternative providers (Kimi, GitHub Copilot, ZAI Coding Plan)";
-  console.log(`${BOLD}${altProviders}, see:${RESET}`);
+  console.log(`${altProviders}, see:`);
   const docsUrl = "https://github.com/alvinunreal/oh-my-opencode-slim/" + "blob/master/docs/provider-configurations.md";
   console.log(`  ${BLUE}${docsUrl}${RESET}`);
   console.log();
@@ -14640,7 +14641,7 @@ ${JSON.stringify(liteConfig, null, 2)}
 }
 async function install(args) {
   const config2 = {
-    hasTmux: args.tmux === "yes",
+    hasTmux: false,
     installSkills: args.skills === "yes",
     installCustomSkills: args.skills === "yes",
     dryRun: args.dryRun,
@@ -14652,13 +14653,12 @@ async function install(args) {
 // src/cli/index.ts
 function parseArgs(args) {
   const result = {
-    tui: true
+    tui: true,
+    skills: "yes"
   };
   for (const arg of args) {
     if (arg === "--no-tui") {
       result.tui = false;
-    } else if (arg.startsWith("--tmux=")) {
-      result.tmux = arg.split("=")[1];
     } else if (arg.startsWith("--skills=")) {
       result.skills = arg.split("=")[1];
     } else if (arg === "--dry-run") {
@@ -14679,8 +14679,7 @@ oh-my-opencode-slim installer
 Usage: bunx oh-my-opencode-slim install [OPTIONS]
 
 Options:
-  --tmux=yes|no          Enable tmux integration (yes/no)
-  --skills=yes|no        Install recommended skills (yes/no)
+  --skills=yes|no        Install recommended and bundled skills (default: yes)
   --no-tui               Non-interactive mode
   --dry-run              Simulate install without writing files
   --reset                Force overwrite of existing configuration
@@ -14691,7 +14690,7 @@ For alternative providers, see docs/provider-configurations.md.
 
 Examples:
   bunx oh-my-opencode-slim install
-  bunx oh-my-opencode-slim install --no-tui --tmux=no --skills=yes
+  bunx oh-my-opencode-slim install --no-tui --skills=yes
   bunx oh-my-opencode-slim install --reset
 `);
 }

package/dist/cli/types.d.ts

@@ -1,7 +1,6 @@
 export type BooleanArg = 'yes' | 'no';
 export interface InstallArgs {
     tui: boolean;
-    tmux?: BooleanArg;
     skills?: BooleanArg;
     dryRun?: boolean;
     reset?: boolean;

package/dist/config/schema.d.ts

@@ -60,6 +60,7 @@ export declare const AgentOverrideConfigSchema: z.ZodObject<{
     skills: z.ZodOptional<z.ZodArray<z.ZodString>>;
     mcps: z.ZodOptional<z.ZodArray<z.ZodString>>;
     options: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodUnknown>>;
+    displayName: z.ZodOptional<z.ZodString>;
 }, z.core.$strip>;
 export declare const MultiplexerTypeSchema: z.ZodEnum<{
     auto: "auto";
@@ -129,6 +130,7 @@ export declare const PresetSchema: z.ZodRecord<z.ZodString, z.ZodObject<{
     skills: z.ZodOptional<z.ZodArray<z.ZodString>>;
     mcps: z.ZodOptional<z.ZodArray<z.ZodString>>;
     options: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodUnknown>>;
+    displayName: z.ZodOptional<z.ZodString>;
 }, z.core.$strip>>;
 export type Preset = z.infer<typeof PresetSchema>;
 export declare const WebsearchConfigSchema: z.ZodObject<{
@@ -187,6 +189,7 @@ export declare const PluginConfigSchema: z.ZodObject<{
         v2: "v2";
     }>>;
     balanceProviderUsage: z.ZodOptional<z.ZodBoolean>;
+    showStartupToast: z.ZodOptional<z.ZodBoolean>;
     manualPlan: z.ZodOptional<z.ZodObject<{
         orchestrator: z.ZodObject<{
             primary: z.ZodString;
@@ -235,6 +238,7 @@ export declare const PluginConfigSchema: z.ZodObject<{
         skills: z.ZodOptional<z.ZodArray<z.ZodString>>;
         mcps: z.ZodOptional<z.ZodArray<z.ZodString>>;
         options: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodUnknown>>;
+        displayName: z.ZodOptional<z.ZodString>;
     }, z.core.$strip>>>>;
     agents: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodObject<{
         model: z.ZodOptional<z.ZodUnion<readonly [z.ZodString, z.ZodArray<z.ZodUnion<readonly [z.ZodString, z.ZodObject<{
@@ -246,6 +250,7 @@ export declare const PluginConfigSchema: z.ZodObject<{
         skills: z.ZodOptional<z.ZodArray<z.ZodString>>;
         mcps: z.ZodOptional<z.ZodArray<z.ZodString>>;
         options: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodUnknown>>;
+        displayName: z.ZodOptional<z.ZodString>;
     }, z.core.$strip>>>;
     disabled_agents: z.ZodOptional<z.ZodArray<z.ZodString>>;
     disabled_mcps: z.ZodOptional<z.ZodArray<z.ZodString>>;