Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gmickel/flow-next --skill flow-next-drivegit clone --depth 1 https://github.com/gmickel/flow-nextWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gmickel/flow-next/flow-next-drive)<a href="https://agentmods.dev/skills/gmickel/flow-next/flow-next-drive"><img src="https://agentmods.dev/badge/skills/gmickel/flow-next/flow-next-drive/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gmickel/flow-next/flow-next-drive"><img src="https://agentmods.dev/badge/skills/gmickel/flow-next/flow-next-drive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00220 | $0.03808 |
| Opus 5.5 | $0.00088 | $0.01523 |
| Sonnet 5.5 | $0.00044 | $0.00762 |
| Haiku 4.5 | $0.00022 | $0.00381 |
Grade A, and why
flow-next-drive scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 21d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex note — Browser Use vs this skill: Codex desktop (v0.124+) bundles a Browser Use plugin (invoke
$browser-use <task>) controlling its in-app browser. Scope is narrow:localhost,127.0.0.1,::1,file://, current in-app tab. No cookies, no auth, no extensions, no production sites, no Electron apps, no mobile sims. For those narrow cases, delegate: use$browser-usedirectly, or just describe the task in prose (Codex routes natural-language plugin calls). Use this skill (the prose triggers listed above —check the page,verify UI,test this app, etc.) for everything outside that scope — production sites, authenticated flows, cookies/saved sessions, Electron / native apps, iOS Simulator, proxies, headed browsers, video recording, visual diff. In Codex CLI (no desktop app, no in-app browser), always use this skill — Browser Use is not available there.
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-boardskill (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.
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 177 B
- references/advanced.md 5.4 KB
- references/agent-browser.md 8.5 KB
- references/auth.md 4.9 KB
- references/chrome-devtools-mcp.md 4.6 KB
- references/commands.md 11 KB
- references/computer-use.md 10 KB
- references/cua.md 36 KB
- references/cursor-ide-browser.md 9.5 KB
- references/debugging.md 3.7 KB
- references/playwright.md 3.5 KB
- references/proxy.md 3.0 KB
- references/session-management.md 3.8 KB
- references/snapshot-refs.md 4.2 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 21d ago Changed · -10 lines 40fd0bc30872
- 23d ago Changed c870ad8d55b5
- 27d ago Changed 2f52c4f51feb
- 28d ago Changed cf3b58b171d2
- 1mo ago First seen · 124 lines · 220 tokens per session scan A 5b47c83cde4f
flow-next-drive is a skill published in the GitHub repository gmickel/flow-next (711 stars, last pushed today), licensed MIT. It adds 220 tokens to every session and 3,808 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pr
Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.
backlog
Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…
clarify
This skill should be used when user appears confused, frustrated, or shows misalignment between expectations and reality. Triggers on phrases like "I don't understand", "this doesn't make sense", "confused", "wait, shouldn't it...", "why is this happening", "I thought X did Y", contradictory statements, or frustration…
project-execution
Executes implementation plans with progress tracking, checkpoint validation, and quality gates. Use after planning is complete and tasks are ready to implement.
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.
root-cause-investigator
Systematic root cause analysis for errors, bugs, and unexpected behaviors using 5-Why methodology. Use when user reports errors, build failures, test failures, performance issues, integration problems, or any "it's not working" scenarios.