Super Powers AI v1.0.7
Autobuild deterministic agents
From the developer
The plugin returns account-linked external Stripe checkout links for Super Chrome subscriptions. Users complete checkout themselves; the plugin does not submit payment. The Chrome Extension plan currently costs $20/month and each successful subscription payment grants $10 in model credits. Model-based agent functions can consume credits; deterministic script steps do not. Authorized shopping research or checkout preparation stops before payment confirmation.
Find competitors on TikTok getting many views and generate slideshows with a similar style for my business.
Developer declarations; not independently tested. Listing last checked Nov 14, 2026. Package observed Nov 14, 2026.
From the marketplace listing
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. Scripted 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. Use 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. Build 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. Your assistant writes AgentScript directly, and Super executes Chrome workflows through your connected Super Chrome extension. Use reusable code for navigation, calculations, formatting, and other predictable steps. Build 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. Create persistent projects and inspect connected devices and their capabilities. Your agent preserves task constraints and distinguishes queued work from observed completion. Support and live onboarding information are available on request. Deterministic scripts can reduce model inference costs for repeated agent runs by up to 100% when those runs require no model calls. Computing, Super access, and other service costs may still apply.
Language: English · Automatically detected from descriptions.
Exact text from the indicated source. A mention alone does not establish support for your task.
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. Scripted 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. Use 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. Build 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. Your assistant writes AgentScript directly, and Super executes Chrome workflows through your connected Super Chrome extension. Use reusable code for navigation, calculations, formatting, and other predictable steps. Build 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. Create persistent projects and inspect connected devices and their capabilities. Your agent preserves task constraints and distinguishes queued work from observed completion. Support and live onboarding information are available on request. Deterministic scripts can reduce model inference costs for repeated agent runs by up to 100% when those runs require no model calls. Computing, Super access, and other service costs may still apply.
· 3 observations
Default prompts updated; open the comparison for details. Long description changed from “goal and turn it into reusable AgentScript. Your assistant writes the script directly, and Super executes it in your connected Chrome extension. Reuse code...” to “goal. Super auto-builds it into AgentScript, a scripting...
View comparison →Package or technical metadata updated
View technical comparison →· 4 observations
Skill instructions changed from “For Chrome onboarding, call super_account_status before asking the user to subscribe, install, reconnect, or add credits. Follow its current...” to “Write the complete AgentScript JavaScript body directly in this ChatGPT conversation, then call super_run_browser_script. ChatGPT...
View comparison →Default prompt changed from “Build a research agent using my Super Chrome extension.” to “Find competitors on TikTok getting many views and generate slideshows with a similar style for my business.”. Default prompts updated; open the comparison for details. Long description changed from “goal. Super auto-builds it...
View comparison →Package or technical metadata updated
View technical comparison →· 4 observations
Skill instructions changed from “agent building, first” to “onboarding, call super_account_status before asking the user to subscribe, install, reconnect, or add credits. Follow its current chrome_onboarding result....”.
View comparison →Full description changed from “Build agents on Mac and Chrome” to “Autobuild deterministic agents”. Long description changed from “Build and run agents from your goals using Super and your connected Mac app or Chrome extension. Create persistent projects, delegate tasks to the Super...” to “Describe a goal. Super...
View comparison →Package or technical metadata updated
View technical comparison →· 1 observation
Package or technical metadata updated
View technical comparison →Find competitors to follow as you develop your plugin.
Hand long-running work to Vincen AI agents running on a cloud computer: websites, presentations, research, images, videos and connected-a...
Shared terms: agent, step, describe, task
Create and maintain ArchiMate architecture models, relationships and views with your agent.
Shared terms: agent, execute, goal, interactive
Give AI agents shared project memory and coordinate work with people across your Swarm Spaces.
Shared terms: agent, completion, device, execute
Local-first video creation, editing workflows, subtitles, narration, and document automation for ChatGPT and Codex.
Shared terms: agent, capabilitie, reusable, reuse
Build and host persistent AI agents on camelRun. Create agents, run tasks, review their work, schedule checks, and deploy reusable config...
Shared terms: agent, continue, persistent, reusable
--- name: build-agents description: Build, run, continue, and inspect agents using Super and the user's connected Super Mac app or Chrome extension. --- Turn the user's objective into a persistent Super agent workflow. Use the connected Super MCP tools and their current input schemas. Discover capabilities at runtime instead of hard-coding command names or automation sequences. Write the complete AgentScript JavaScript body directly in this ChatGPT conversation, then call super_run_browser_script. ChatGPT authors the code using this conversation; do not delegate script generation to super_build_browser_agent, super_chat, the extension-selected model, or a separate API call. No OpenAI API key is needed. ChatGPT usage limits still apply. Observed failure: Super's old build step used the extension-selected local model and failed with a hostname lookup error despite a connected extension. The direct path queues the code you supply without calling a model. Never retry the old builder or blame a connected extension for that authoring-provider failure. Observed onboarding failure: users verified successfully but received no subscription link in chat. Immediately after login or connection for a Chrome task, FIRST call super_account_status, even when Chrome is already connected. If subscription_required is true, show next_user_message / subscription_message with the returned account-linked subscription_url as a clickable Markdown link in the FIRST user-visible reply. Use the configured plan name and price. Do not wait for agent generation, extension setup, or a user request for payment instructions. Do not redirect users to Settings to find the link. Show it once, then preserve the task. Wait for the user to subscribe, then refresh access. Respect manual grants; verification_unavailable is not proof an upgrade is missing. ChatGPT access does not replace Growth access. Each successful paid Growth subscription invoice grants the configured credits once per invoice. Inspect the returned balance instead of assuming fulfillment. Favor deterministic code wherever practical: reusable functions, loops, arithmetic, sorting, data formatting, already-known URL navigation, current unique observed control labels, typing, and page reads. Do not add model calls for steps code can reliably perform. Use a model-based function only for an actual semantic task such as interpreting unstructured evidence, an ambiguous visual control, or generating requested content. Batch related extraction into one call and reuse the result. Do not add a model approval, classification, or verification call to every step. Preserve direct observation of the result without a redundant model check. Only explicit model functions invoke inference: magicScraper, magicClicker/click, and modelFunction. They use the function_model returned in this contract, independent of the extension selection. Omit function_model in super_run_browser_script to use the configured default, or supply a model only when the user asks. Purely deterministic scripts need no model credits. Model-based functions spend Super credits; surface an actual insufficient-credit error and add_credits_url when applicable, without blocking a model-free script. Use top-level async JavaScript statements ending with return observedResult. Never wrap the body in an uncalled function or Markdown fences. Start with openUrl to create a dedicated tab; later actions stay on it. Standard JavaScript is available. No DOM, document, window, chrome, imports, require, Playwright, Puppeteer, fetch, or provider APIs are supported inside the worker. Do not use jev/classify/xWebsiteStudio in this path: use modelFunction only when a model judgment is necessary so the configured function model remains authoritative. Read pageText to observe a page. Navigation can be asynchronous: retry a loading observation on the SAME tab, not by creating duplicates. clickLabel requires an exact unique label in current evidence; use magicClicke
Preview of the first 4,000 characters. Read full instructions →
Referenced files: 1 — file references are metadata, not package contents.
Replace starter prompts with TikTok competitor slideshows, live onboarding scheduling and ICP-led SEO tools. Add direct assistant-authored AgentScript execution over MCP; favor deterministic code and reserve model calls for explicit model functions using the configured default. Persist through execution, diagnosis and script repair until the requested result works or user input is required. Add onboarding-calendar and support-email discovery. Fulfill subscription model credits on each successful paid invoice with duplicate protection. Show the configured subscription link in the first authenticated Chrome-task response. Route unpaid Chrome dashboard logins directly to the entry subscription checkout; retain later upgrades and bypass checkout for entitled accounts. Track link delivery separately from clicks and automatic redirects. Remove external entitlement calls from code verification; fresh-account email login reached Stripe in 12.0 seconds in the clean timing test. Include paid-access requirements in the listing.
Declared in the saved package. Remote tools may change independently.
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
Package observed Nov 14, 2026.
plugin_asdk_app_6ac2633c40008191a028cd2643815cce
Download plugin data (JSON)Plugin details: served from cache. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.
