Agent skill

Flow Next Drive

by gmickel in gmickel/flow-next

Drive any UI surface like a real user - a web app, a Chromium-backed desktop app (Electron / WebView2, reached over CDP), or a genuinely native app (macOS AppKit/SwiftUI, or a non-CDP webview)…

MITAuto-check passedProductivity & Automation

Install Flow Next Drive

skills CLI
$ npx skills add gmickel/flow-next --skill flow-next-drive -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install gmickel/flow-next flow-next-drive --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/gmickel/flow-next.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/flow-next/skills/flow-next-drive .claude/skills/flow-next-drive && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
flow-next-drive
GitHub stars
709
Token cost
~3.6k tokens
SKILL.md length
1,850 words
Files
14 (incl. references)
Skills in repo
43
Repo updated
First seen
Licence
MIT

At a glance

Drive any UI surface like a real user - a web app, a Chromium-backed desktop app (Electron / WebView2, reached over CDP), or a genuinely native app (macOS AppKit/SwiftUI, or a non-CDP webview)…

  • Works in 4 steps: Detect the surface, then branch → The universal flow (all surfaces) → Web ladder (surfaces A and B) → …
  • Verify deployed UI
  • SKILL.md covers Step 1 — Detect the surface,…, Step 2 — The universal flow…, Step 3 — Web ladder (surfaces… and Step 4 — Native rung (surface…, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Flow Next Drive is an agent skill from gmickel/flow-next. Drive any UI surface like a real user - a web app, a Chromium-backed desktop app (Electron / WebView2, reached over CDP), or a genuinely native app (macOS AppKit/SwiftUI, or a non-CDP webview) reached via the Cua Driver / Computer Use. Detects the surface, picks the best available driver, degrades gracefully. Use to navigate sites, verify deployed UI, test web or desktop apps, capture baseline screenshots, drive a sign-in flow, scrape data, fill forms, run an e2e check, or inspect current page state. Triggers on…

Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including reference files (for example `references/advanced.md`, `references/agent-browser.md` and `references/auth.md`).

It sits in Productivity & Automation, covering Desktop control, Authentication and Web scraping. It works with macOS, SwiftUI and Electron. The repository describes itself as: Faster than your agent alone. And better. A workflow plugin that takes a bug, idea or ticket to a verified pull request: specs, cross-model review by risk, live QA, receipts in… The licence is MIT.

When your agent uses it

  • Verify deployed UI
  • Capture baseline screenshots
  • Drive a sign-in flow
  • Run an e2e check

Example prompts

  • “check the page”
  • “verify UI”
  • “test the site”
  • “/flow-next-drive”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Detect the surface, then branch
  2. The universal flow (all surfaces)
  3. Web ladder (surfaces A and B)
  4. Native rung (surface C): Cua Driver, then Computer Use

What it can do on your machine

Read from SKILL.md and the folder at commit 09e291e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Flow Next Drive loads about 3.6k tokens when it runs, and up to ~31k if it reads all its reference files. Until then it costs about 214 tokens; SKILL.md has 1,850 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~214
When it runs · the whole SKILL.md, loaded when a task matches
~3.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~31k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from gmickel/flow-next at commit 09e291e, republished under its MIT licence (© gmickel). 1,850 words, ~3,626 tokens.

Download SKILL.mdSave it as .claude/skills/flow-next-drive/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.
name
flow-next-drive
description
Drive any UI surface like a real user - a web app, a Chromium-backed desktop app (Electron / WebView2, reached over CDP), or a genuinely native app (macOS AppKit/SwiftUI, or a non-CDP webview) reached via the Cua Driver / Computer Use. Detects the surface, picks the best available driver, degrades gracefully. Use to navigate sites, verify deployed UI, test web or desktop apps, capture baseline screenshots, drive a sign-in flow, scrape data, fill forms, run an e2e check, or inspect current page state. Triggers on "check the page", "verify UI", "test the site", "test this app", "drive the app", "automate this desktop app", "read docs at", "look up API", "visit URL", "browse", "screenshot", "scrape", "e2e test", "login flow", "capture baseline", "see how it looks", "inspect current", "before redesign", "Electron app", "native app".

flow-next-drive — surface-aware UI automation

Drive any UI surface the way a real user would. Whatever driver the environment has, the work is the same shape: observe / navigate → snapshot → act on fresh refs → capture evidence → release. This skill is a router: it detects the surface, picks the highest available driver on a ladder, degrades gracefully when a richer driver is absent, and hands off to a per-rung reference for the command detail.

It orchestrates drivers — it does not reimplement them. The default rung (Vercel's agent-browser CLI) is the only driver assumed present; every other rung is detected and optional. A pass must succeed with whatever the environment actually has — most cloud VMs, Linux, and CI have no Computer Use, so it is never a hard dependency and never on a headless/no-display path.

Driver ladder + universal-flow structure adapted from Ray Fernando's running-bug-review-board skill (Apache-2.0).

Step 1 — Detect the surface, then branch

Classify the target into one of three buckets and take the matching path. The universal flow (Step 2) is shared; only the actuation and the per-surface reference differ.

#SurfaceWhat it isPath
AWeb appA URL in a browser (localhost dev server, staging, production)Web ladder (Step 3)
BChromium-backed desktop appElectron / Windows WebView2 — Chromium under the hood, exposes a CDP debug portWeb ladder (Step 3), attaching over CDP to the app's remote-debugging port
CTrue-native / non-CDP surfacemacOS AppKit/SwiftUI, Catalyst, or a webview exposing no CDP (macOS WKWebView, which Tauri uses on macOS)Native rung (Step 4) — Cua Driver → Computer Use (attended); Cua Sandbox (headless/CI)

How to decide:

  • A bare URL, or a dev/staging/prod web app → A.
  • A desktop app you can launch with --remote-debugging-port=<n> (or one already exposing one) → B. Electron and Windows WebView2 are Chromium; the web ladder drives them by CDP-attach. Do not route these to Computer Use.
  • A desktop app with no CDP port — genuinely native (AppKit/SwiftUI), or a macOS WKWebView / Tauri-on-macOS app — → C. Per-platform caveat: Windows WebView2 is CDP-drivable (→ B); macOS WKWebView generally is not (→ C) — verify per platform.

When unsure whether a desktop app exposes CDP, probe for B first (try to launch/attach with a debug port). If no port is reachable, fall to C.

When .flow/features/ exists and the caller did not pass unmapped, Read .flow/features/README.md and the feature file the caller names, else the one matching feature file, first; never the whole map. They pre-resolve the route, preconditions, and gotchas. Select by **Surface:** plus sub-feature IDs (feature-entry-contract.md, "Live-app stages"). Live detection above remains the fallback when the map is absent or does not cover this target. A mapped route that no longer matches the live app gets a drift note per the contract's "Writers and drift notes" section, then live detection continues; never edit the map mid-run.

Done when
  • The target is classified A, B, or C before any driving starts, and the classification is stated. A pass that started acting before naming the surface has broken this.
  • A desktop app was probed for a CDP port before being routed to C.
  • When .flow/features/ existed, the index and the named or one matching feature file were read before driving (none after a caller's unmapped); live detection was the fallback otherwise, and a stale mapped route was filed as a drift note.

Step 2 — The universal flow (all surfaces)

observe / list what's open
navigate to the target (URL, or focus the app window)
snapshot              → fresh element refs (after a DOM change; for ONE known target prefer semantic find)
act                   → click / fill / type / press / scroll toward the next step
verify                → expected text/state appeared AND console clean + no failed API/network requests
capture               → screenshot + console/errors at the moment of interest (and on failure)
release               → close the tab / end the session when fully done

verify is not DOM-only — every verify checks the console is clean and no API/network request failed, alongside the expected text or state. A pass declared on a green-looking DOM while a request returned 500 or the console threw an uncaught exception has broken this: that is exactly the silent breakage a real user hits, and the /flow-next:qa qa_verdict rests on this evidence. The tooling is already on the default rung (agent-browser console, agent-browser network requests --filter api; the DevTools-MCP rung has richer inspection). A failed request or console error under a green DOM is a finding, not noise.

Snapshot cost: a full interactive snapshot -i before every act is the dominant token cost of a long flow. Re-snapshot after a DOM change, but for a single known target prefer a semantic locator (find role|text|label … <action> — no snapshot needed), and use snapshot -c / -d <depth> when you only need to verify one region.

Refs (@e1, @e2, …) go stale after any navigation, click, or form submit. Element refs are refreshed by re-snapshotting after any navigation, click, or submit. A "ref not found" or pointer-events: none result reported as a bug before a re-snapshot has broken this — it is a stale snapshot until a fresh one says otherwise.

Done when
  • Every act ran against refs from a snapshot taken after the last DOM change (or against a semantic locator that needs none).
  • Every verify carries three checks — expected text/state, clean console, no failed API/network request. Native rungs (cua, computer use) have no console or network channel: verify the expected state plus any app log, and say those checks were unavailable.
  • Evidence was captured at the moment of interest and on failure — screenshot plus console/network output — so a downstream /flow-next:qa verdict rests on artifacts rather than narration.
  • The session or tab is released when the pass is done. A left-open session or daemon has broken this.

Step 3 — Web ladder (surfaces A and B)

Probe availability top-down and use the highest rung that passes; fail soft to the next; the terminal rung is manual. Never hard-depend on any rung above the default.

RungDriverUse whenReference
1 (default)agent-browser CLIAlways assumed present. CDP-based, headless-safe, no extra install. Drives web apps; drives Electron / WebView2 over CDP (--cdp <port> / --auto-connect).references/agent-browser.md
2chrome-devtools-mcpYou want built-in auto-wait (fewer stale-ref failures), DevTools-grade network/console inspection, Lighthouse, or to attach to your real signed-in Chrome (--browser-url / --autoConnect) so bot defenses don't challenge an automated profile.references/chrome-devtools-mcp.md
3Playwright (CLI or MCP)The repo already has Playwright configured, or you need a headless CI-style run / large cross-browser regression suite.references/playwright.md
4cursor-ide-browser MCPOn a Cursor host: no install, no command -v. Probe the server by id cursor-ide-browser (a catalog omission is not absence). If that probe fails in an attended session, ask once for @Browser (no space) or the Browser pane showing connected, then re-probe once — skip the ask when unattended. Real snapshot YAML + browser_cdp. Cannot satisfy verify (console + network) unaided — a /flow-next:qa pass here must set QA_OUTCOME=BLOCKED with blocked_reason naming the missing channels (do not invent console_path / network path values). When higher rungs are missing, prefer this over instructing an install.references/cursor-ide-browser.md
5 (terminal)Manual + screenshot relayNo browser driver available — drive yourself, paste console errors and screenshots into chat (attended only; unattended reports no driver and QA records BLOCKED).—

Surface B note: an Electron / WebView2 app is driven through this same web ladder, over its CDP debug port. Routing a Chromium-backed desktop app to the native rung has broken this. Attach to the app's remote-debugging port (agent-browser --cdp <port> / --auto-connect; chrome-devtools-mcp --browser-url=http://127.0.0.1:<port>). Launch the app with a dedicated debug port and a dedicated user-data-dir; treat the open debug port as a security exposure (any local app can drive that session).

agent-browser command detail lives in the rung reference, not here. The default-rung reference references/agent-browser.md is the entry point — setup/version check, the universal flow in agent-browser commands, the Chromium-desktop (Electron / WebView2) CDP driver, the --headed daemon-reuse gotcha, and an index into the per-topic references it folds: commands.md, advanced.md (CDP attach), auth.md, snapshot-refs.md, session-management.md, proxy.md, debugging.md.

Show full SKILL.md (621 more words)Show less

Step 4 — Native rung (surface C): Cua Driver, then Computer Use

Only for surface C (a genuinely native app or a non-CDP webview): read references/cua.md § Native rung (surface C) first; it holds the driver probe order and routes to Computer Use.

Driver detection & graceful degradation (all surfaces)

  1. Probe, don't assume. Detect each non-default rung before planning around it (command -v, MCP list, uname -s for the macOS-only paths). Treat anything above the default rung — incl. Cua Driver and Computer Use — as probably absent. On a Cursor host, probe cursor-ide-browser by exact server id at least once before concluding it is absent — catalog omission alone is not a negative, and there is no install step. If that probe fails in an attended session, ask once via AskUserQuestion: type @Browser in chat (no space), or open the Browser pane until it shows connected, and confirm Settings → Tools & MCP → Browser Automation is Browser Tab. On portable hosts without that tool, use a numbered prompt with a final Other — type your own answer option. After they confirm, re-probe once. Skip the ask when unattended / autonomous / $CI / FLOW_AUTONOMOUS=1 and degrade. A mid-run MCP server does not exist after this pass already drove the pane is the lease-drop flake, not a first-use miss — do not ask @Browser for that; see references/cursor-ide-browser.md.
  2. Pick the highest rung that passes; fail soft to the next. The terminal rung is always manual / documented-limitation — the pass still completes.
  3. No native driver is required or on a headless/CI path. Neither the local Cua Driver nor Computer Use runs without a real display; most VMs/Linux/CI lack both. (Headless/CI native driving is the opt-in Cua Sandbox surface — see references/cua.md.)
  4. Graceful degradation on the native rung (C): (Determine attended vs headless first — $CI ⇒ headless, else the empirical cua-driver call get_screen_size display probe; NOT $DISPLAY on macOS. See references/cua.md § "Determining headless / CI".)
    • Attended (real display): prefer Cua Driver (background, provider-agnostic) when present → else Computer Use (screen-takeover) → else documented-limitation (document, don't fail).
    • Headless / CI (no display): the Cua Sandbox is the only native option (provision a hermetic VM, drive, tear down each run); local backend is the default, cua.ai cloud is explicit opt-in (bills + egress). No backend and no opted-in cloud → documented-limitation. See references/cua.md.
    • A Chromium-backed app (B) still drives via the web-ladder CDP attach (Step 3), or by driving its local dev-server URL in a browser. Note that shell-level integration (system tray, native menus, OS dialogs) can't be reached this way — surface that limitation.
    • A genuinely native app (C) with no native driver at all → document the limitation rather than fail.
    • On macOS, the Cua Driver's Accessibility-vs-Screen-Recording permission split means driving can work while screenshots don't — surface "AX-only evidence, no screenshot" rather than emit an empty one (references/cua.md).
  5. agent-browser stays the only assumed-present driver. No MCP server, Cua Driver, or Computer Use is ever a hard install dependency; flowctl never imports any of them.
Done when
  • Every rung above agent-browser that the plan relies on was probed first (command -v, MCP list, uname -s; for cursor-ide-browser, an id-probe — and on an attended Cursor miss, one @Browser ask plus one re-probe). A pass that planned around an unprobed rung has broken this.
  • An absent driver degraded to the next rung or to a documented limitation, and the pass still reached a stated outcome rather than ending there.

Boundaries

  • iOS / iPadOS app driving is out of scope — the request is declined and deferred to the community iOS simulator skills. A pass that spun up a simulator has broken this.
  • This skill provides driver/actuation + the surface conditional. The full native-desktop QA workflow (scenario authoring, bug filing, verdict) is a downstream /flow-next:qa concern.
  • Don't reinvent what a driver already does (Playwright, Computer Use) — orchestrate, don't replace.

© gmickel, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 13 other files (references) in plugins/flow-next/skills/flow-next-drive of gmickel/flow-next.

  • SKILL.md
  • references/advanced.md
  • references/agent-browser.md
  • references/auth.md
  • references/chrome-devtools-mcp.md
  • references/commands.md
  • references/computer-use.md
  • references/cua.md
  • references/cursor-ide-browser.md
  • references/debugging.md
  • references/playwright.md
  • references/proxy.md
  • references/session-management.md
  • references/snapshot-refs.md

Open the folder on GitHubat commit 09e291e

Compare with similar skills

Flow Next Drive next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Flow Next Drive compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Flow Next Drive this skillgmickel/flow-next709—~3.6kAutomated safety check: PassMIT
Electron App Automationvercel-labs/agent-browser44k5 repos~1.7kAutomated safety check: PassApache-2.0
Interceptor iOSHacker-Valley-Media/Interceptor519—~1.9kAutomated safety check: PassCustom licence
Interceptor BrowserHacker-Valley-Media/Interceptor519—~4.8kAutomated safety check: PassCustom licence
Unicliolo-dot-io/Uni-CLI274—~3.8kAutomated safety check: NotesApache-2.0
Verify BuildShiinaLabs/wifi-lens119—~827Automated safety check: PassApache-2.0

Similar skills

  • Electron App Automation

    vercel-labs/agent-browser

    Official

    Automates Electron desktop apps such as VS Code, Slack or Discord by connecting agent-browser to their Chrome DevTools Protocol port.

    44k GitHub starsUsed in 5 repos~1.7k tokens
    Productivity & AutomationAuto-check passed
  • Interceptor iOS

    Hacker-Valley-Media/Interceptor

    Drive any installed app on an owned, unlocked, Developer-Mode iPhone via interceptor ios : ref-tagged element trees, deterministic coordinate taps (click), reliable text entry (type/keys), scroll…

    519 GitHub stars~1.9k tokensUpdated 7 days ago
    Productivity & AutomationAuto-check passed
  • Interceptor Browser

    Hacker-Valley-Media/Interceptor

    Drive a signed-in Chrome / Brave / Safari session via the interceptor CLI: open/read pages, click, type, inspect DOM/text/network, automate rich browser editors and scene graphs, capture…

    519 GitHub stars~4.8k tokensUpdated 7 days ago
    Productivity & AutomationAuto-check passed
  • Unicli

    olo-dot-io/Uni-CLI

    Comprehensive guide to Uni-CLI — the open Agent-Computer Interface runtime for real software.

    274 GitHub stars~3.8k tokensUpdated 5 days ago
    Productivity & AutomationAuto-check: notes
  • Verify Build

    ShiinaLabs/wifi-lens

    A skill your agent uses when a change touches the WiFi Lens product itself (Swift app source, unit tests) before claiming that work is complete, before committing such a change, or when asked to…

    119 GitHub stars~827 tokensUpdated yesterday
    MobileAuto-check passed
  • Swiftui Expert Skill

    omarshahine/HomeClaw

    A skill your agent uses when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state management, view composition, performance, Liquid Glass adoption, or Instruments .trace…

    175 GitHub starsUsed in 4 repos~2.8k tokens
    MobileAuto-check passed

More from gmickel/flow-next

All 43 skills in this repo
  • Flow Next Resolve PR

    gmickel/flow-next

    Resolve PR review feedback. An agent skill from gmickel/flow-next.

    709 GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Flow Next Resolve PR

    gmickel/flow-next

    Resolve PR review feedback — fetch unresolved threads, triage, dispatch per-thread resolver agents, validate, commit, reply + resolve via GraphQL.

    709 GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Flow Next

    gmickel/flow-next

    Manage .flow/ tasks and specs. An agent skill from gmickel/flow-next.

    709 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check passed
  • Flow Next Audit

    gmickel/flow-next

    Audit .flow/memory/ entries against the current codebase and decide Keep / Update / Consolidate / Replace / Delete / Harden per entry.

    709 GitHub stars~3.1k tokensUpdated 2 days ago
    Auto-check: notes
  • Flow Next Capture

    gmickel/flow-next

    Save the current conversation as a source-tagged flow-next spec, then offer review or editing.

    709 GitHub stars~1.9k tokensUpdated 2 days ago
    Auto-check: notes
  • Flow Next Chart

    gmickel/flow-next

    Decision-map discovery for one oversized unclear idea before capture.

    709 GitHub stars~2.7k tokensUpdated 2 days ago
    Auto-check: notes

Questions about Flow Next Drive

What does Flow Next Drive do?

Drive any UI surface like a real user - a web app, a Chromium-backed desktop app (Electron / WebView2, reached over CDP), or a genuinely native app (macOS AppKit/SwiftUI, or a non-CDP webview)…. Flow Next Drive is an agent skill from gmickel/flow-next. Drive any UI surface like a real user - a web app, a Chromium-backed desktop app (Electron / WebView2, reached over CDP), or a genuinely native app (macOS AppKit/SwiftUI, or a non-CDP webview) reached via the Cua Driver / Computer Use.

When should I use Flow Next Drive?

Flow Next Drive fits situations like: verify deployed UI; capture baseline screenshots; drive a sign-in flow; run an e2e check.

How do I install Flow Next Drive in Claude Code?

Run `npx skills add gmickel/flow-next --skill flow-next-drive -a claude-code`. Or copy the skill folder (plugins/flow-next/skills/flow-next-drive in gmickel/flow-next) into .claude/skills/flow-next-drive in your project. Claude Code loads it when a task matches its description.

How do I install Flow Next Drive in Codex?

Run `npx skills add gmickel/flow-next --skill flow-next-drive -a codex`. Or copy the skill folder (plugins/flow-next/skills/flow-next-drive in gmickel/flow-next) into .agents/skills/flow-next-drive in your project. Codex loads it when a task matches its description.

Can I use Flow Next Drive in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add gmickel/flow-next --skill flow-next-drive -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/flow-next-drive, .gemini/skills/flow-next-drive, .github/skills/flow-next-drive and .opencode/skills/flow-next-drive in your project.

What does Flow Next Drive need to run?

SKILL.md names no scripts, command-line tools or credentials: Flow Next Drive is instructions for the agent only.

Does Flow Next Drive access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Flow Next Drive safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Flow Next Drive use?

Flow Next Drive is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Flow Next Drive use?

About 3.6k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 28k tokens, read only when the agent opens those files.

What are the alternatives to Flow Next Drive?

Skills that share tags, products or a category with Flow Next Drive: Electron App Automation (vercel-labs/agent-browser, 44k stars), Interceptor iOS (Hacker-Valley-Media/Interceptor, 519 stars), Interceptor Browser (Hacker-Valley-Media/Interceptor, 519 stars) and Unicli (olo-dot-io/Uni-CLI, 274 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Flow Next Drive?

gmickel (a GitHub user) maintains it in gmickel/flow-next, which has 709 GitHub stars. The repository holds 43 skills in this directory. The repository was last updated on October 7, 2026.

Source: gmickel/flow-next on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.