← Auto-building agentsCONTENT HISTORY

Update to Auto-building agents

Snapshot Nov 13, 2026 · 12:12 UTC · version 1.0.5

WHAT CHANGED

Product listing or positioning changed

Long description — Now says: goal and turn it into reusable AgentScript. Your assistant writes the script directly, and Super executes it in your connected Chrome extension. Reuse code...

Observed in the public listing; claims come from the publisher.

Save Auto-building agents and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Long description

Before

Nov 3, 2026 · 19:04 UTC

goal. Super auto-builds it into AgentScript, a scripting language for reusable agent workflows. Build the workflow once, inspect it, and rerun its saved logic instead of asking a model to reinvent every step. Scripted control flow makes ...

After

Nov 13, 2026 · 12:12 UTC

goal and turn it into reusable AgentScript. Your assistant writes the script directly, and Super executes it in your connected Chrome extension. Reuse code for navigation, calculations, formatting, and other predictable steps. Invoke mod...

Declared skills

Before

Nov 3, 2026 · 19:04 UTC

[{"description":"Build, run, continue, and inspect agents using Super and the user's connected Super Mac app or Chrome extension.","interface":{"brand_color":null,"default_prompt":null,"display_name":"build-agents","icon_large_url":null,...

After

Nov 13, 2026 · 12:12 UTC

[{"description":"Build, run, continue, and inspect agents using Super and the user's connected Super Mac app or Chrome extension.","interface":{"brand_color":null,"default_prompt":null,"display_name":"build-agents","icon_large_url":null,...

Composer icon url

Before

Nov 3, 2026 · 19:04 UTC

https://files.openai.com/content?id=file_00000000737c81f69765db0ce0125c72

After

Nov 13, 2026 · 12:12 UTC

https://files.openai.com/content?id=file_00000000110082308bdf44132373e7ae

Default prompt

Before

Nov 3, 2026 · 19:04 UTC

Build a research agent using my Super Chrome extension.

After

Nov 13, 2026 · 12:12 UTC

Find competitors on TikTok getting many views and generate slideshows with a similar style for my business.

Compare saved observations

Download comparison JSON
Full technical diff · 8 changed fields

changed /release/id

BEFORE
"pluginrel_45d1c6de8f788191a71beb75b35fece0"
AFTER
"pluginrel_924cddb85da881919e337a51e36c5e66"

changed /release/interface/composer_icon_url

BEFORE
"https://files.openai.com/content?id=file_00000000737c81f69765db0ce0125c72"
AFTER
"https://files.openai.com/content?id=file_00000000110082308bdf44132373e7ae"

changed /release/interface/default_prompt

BEFORE
"Build a research agent using my Super Chrome extension."
AFTER
"Find competitors on TikTok getting many views and generate slideshows with a similar style for my business."

changed /release/interface/default_prompts

BEFORE
[
  "Build a research agent using my Super Chrome extension.",
  "Build an agent using my connected Super Mac app.",
  "Continue my existing Super agent and check its progress."
]
AFTER
[
  "Find competitors on TikTok getting many views and generate slideshows with a similar style for my business.",
  "Schedule a live onboarding session.",
  "Grow my SEO by finding customers in my ICP on social media and generating helpful interactive tools to publish on my site."
]

changed /release/interface/logo_url

BEFORE
"https://files.openai.com/content?id=file_00000000cebc81f69059b53617135932"
AFTER
"https://files.openai.com/content?id=file_00000000ab108230aeb29f52c091e59e"

changed /release/interface/long_description

BEFORE
"Describe a goal. Super auto-builds it into AgentScript, a scripting language for reusable agent workflows. Build the workflow once, inspect it, and rerun its saved logic instead of asking a model to reinvent every step.\n\nScripted control flow makes repeated execution more predictable and reduces opportunities for model errors to accumulate across long tasks. For illustration, an independent 1% error probability per decision produces a 99.3% chance of at least one error over 500 decisions. This is a hypothetical example, not a measured hallucination rate or a guarantee that every error causes failure.\n\nUse models where intelligence is needed: generating text, images or video, interpreting a page, and making judgments. Let code handle the reusable workflow around those calls. Replacing 100 comparable model calls with one means 100x fewer calls; actual savings depend on the workflow, tokens and providers. Script execution avoids per-step inference charges, but computing, Super access and remaining model calls can still cost money.\n\nBuild and run workflows with your connected Chrome extension or Mac app, inspect results, and continue projects across chats. Scripts and changing websites can still fail, so completion is verified from observed results. Requires a Super account and a connected client; Chrome execution requires Growth access or an authorized manual grant."
AFTER
"Describe a goal and turn it into reusable AgentScript. Your assistant writes the script directly, and Super executes it in your connected Chrome extension. Reuse code for navigation, calculations, formatting, and other predictable steps. Invoke model-based functions only when the task needs interpretation or generation.\n\nBuild workflows for competitor research, business operations, and useful interactive tools. Inspect progress, diagnose failures, revise the script, and continue until the requested result is verified or a specific blocker needs your input. Connect a supported client to run device actions.\n\nCreate persistent projects, inspect connected devices and their capabilities, and continue existing workflows. Your agent preserves task constraints and distinguishes queued work from observed completion. Help and onboarding options are available on request.\n\nChrome workflows run through the connected Super Chrome extension. Support and live onboarding information are available on request."

changed /release/skills

BEFORE
[
  {
    "description": "Build, run, continue, and inspect agents using Super and the user's connected Super Mac app or Chrome extension.",
    "interface": {
      "brand_color": null,
      "default_prompt": null,
      "display_name": "build-agents",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "code",
      "short_description": "Build, run, continue, and inspect agents using Super and the user's connected Super Mac app or Chrome extension."
    },
    "name": "build-agents",
    "plugin_release_skill_id": "pluginrsk_6ae92dd840788191b9ed9983b4803b40"
  }
]
AFTER
[
  {
    "description": "Build, run, continue, and inspect agents using Super and the user's connected Super Mac app or Chrome extension.",
    "interface": {
      "brand_color": null,
      "default_prompt": null,
      "display_name": "build-agents",
      "icon_large_url": null,
      "icon_small_url": null,
      "iconography": "code",
      "short_description": "Build, run, continue, and inspect agents using Super and the user's connected Super Mac app or Chrome extension."
    },
    "name": "build-agents",
    "plugin_release_skill_id": "pluginrsk_6af6c067c7a081919927148f4204f429"
  }
]

changed /release/version

BEFORE
"1.0.2"
AFTER
"1.0.5"
Full snapshot data
{
  "canonical_app_id": "asdk_app_6ac2633c40008191a028cd2643815cce",
  "connector_id": "asdk_app_6ac2633c40008191a028cd2643815cce",
  "created_at": "2026-10-05T14:00:38.982219Z",
  "discoverability": "LISTED",
  "id": "plugin_asdk_app_6ac2633c40008191a028cd2643815cce",
  "is_template": false,
  "is_template_instance": false,
  "is_v2_template": false,
  "name": "super",
  "release": {
    "app_ids": [
      "asdk_app_6ac2633c40008191a028cd2643815cce"
    ],
    "app_manifest": {
      "apps": {
        "super": {
          "id": "asdk_app_6ac2633c40008191a028cd2643815cce",
          "required": true
        }
      }
    },
    "app_templates": [],
    "description": "Autobuild deterministic agents",
    "display_name": "Auto-building agents",
    "id": "pluginrel_924cddb85da881919e337a51e36c5e66",
    "interface": {
      "brand_color": "#101010",
      "capabilities": [
        "Build agents",
        "Browser automation",
        "Mac automation"
      ],
      "category": "Productivity",
      "composer_icon_dark_url": null,
      "composer_icon_url": "https://files.openai.com/content?id=file_00000000110082308bdf44132373e7ae",
      "default_prompt": "Find competitors on TikTok getting many views and generate slideshows with a similar style for my business.",
      "default_prompts": [
        "Find competitors on TikTok getting many views and generate slideshows with a similar style for my business.",
        "Schedule a live onboarding session.",
        "Grow my SEO by finding customers in my ICP on social media and generating helpful interactive tools to publish on my site."
      ],
      "developer_name": "Super Powers AI",
      "logo_url": "https://files.openai.com/content?id=file_00000000ab108230aeb29f52c091e59e",
      "logo_url_dark": null,
      "long_description": "Describe a goal and turn it into reusable AgentScript. Your assistant writes the script directly, and Super executes it in your connected Chrome extension. Reuse code for navigation, calculations, formatting, and other predictable steps. Invoke model-based functions only when the task needs interpretation or generation.\n\nBuild workflows for competitor research, business operations, and useful interactive tools. Inspect progress, diagnose failures, revise the script, and continue until the requested result is verified or a specific blocker needs your input. Connect a supported client to run device actions.\n\nCreate persistent projects, inspect connected devices and their capabilities, and continue existing workflows. Your agent preserves task constraints and distinguishes queued work from observed completion. Help and onboarding options are available on request.\n\nChrome workflows run through the connected Super Chrome extension. Support and live onboarding information are available on request.",
      "plugin_category_id": "productivity",
      "privacy_policy_url": "https://app.getsupers.com/privacy",
      "screenshot_urls": [],
      "short_description": "Autobuild deterministic agents",
      "terms_of_service_url": "https://app.getsupers.com/terms",
      "website_url": "https://getsupers.com/"
    },
    "keywords": [
      "agents",
      "automation",
      "mac",
      "chrome"
    ],
    "mcp_servers": [
      {
        "key": "super",
        "metadata": {
          "headers": {},
          "type": "streamable-http",
          "url": "https://app.getsupers.com/mcp"
        }
      }
    ],
    "onboarding_skill_name": "build-agents",
    "requires_local_executor": false,
    "skills": [
      {
        "description": "Build, run, continue, and inspect agents using Super and the user's connected Super Mac app or Chrome extension.",
        "interface": {
          "brand_color": null,
          "default_prompt": null,
          "display_name": "build-agents",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "code",
          "short_description": "Build, run, continue, and inspect agents using Super and the user's connected Super Mac app or Chrome extension."
        },
        "name": "build-agents",
        "plugin_release_skill_id": "pluginrsk_6af6c067c7a081919927148f4204f429"
      }
    ],
    "version": "1.0.5"
  },
  "scope": "GLOBAL",
  "share_url": "https://chatgpt.com/plugins/plugin_asdk_app_6ac2633c40008191a028cd2643815cce?open_in_app",
  "status": "ENABLED"
}

SHA-256 of public snapshot: 70fd51f755d71d25b3eaa264db7e4a9975a77eed7afa6e48027fd70f46984d3e