Agent Browser CLI
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
Switches to the next connected Claude or Codex account that has proven capacity when a session or weekly usage limit is hit, using the headroom CLI.
$ npx skills add domanski-ai/headroom --skill rotator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install domanski-ai/headroom rotator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/domanski-ai/headroom.git skills-src && mkdir -p .claude/skills && cp -r skills-src/integrations/claude-code/skills/rotator .claude/skills/rotator && rm -rf skills-srcUse ~/.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/
Install the "rotator" agent skill from https://github.com/domanski-ai/headroom/tree/master/integrations/claude-code/skills/rotator into .claude/skills/rotator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rotator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/domanski-ai/headroom/tree/master/integrations/claude-code/skills/rotatorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add domanski-ai/headroom --skill rotator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install domanski-ai/headroom rotator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/domanski-ai/headroom.git skills-src && mkdir -p .agents/skills && cp -r skills-src/integrations/claude-code/skills/rotator .agents/skills/rotator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "rotator" agent skill from https://github.com/domanski-ai/headroom/tree/master/integrations/claude-code/skills/rotator into .agents/skills/rotator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rotator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add domanski-ai/headroom --skill rotator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install domanski-ai/headroom rotator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/domanski-ai/headroom.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/integrations/claude-code/skills/rotator .cursor/skills/rotator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "rotator" agent skill from https://github.com/domanski-ai/headroom/tree/master/integrations/claude-code/skills/rotator into .cursor/skills/rotator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rotator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/domanski-ai/headroom.git --path integrations/claude-code/skills/rotator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add domanski-ai/headroom --skill rotator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install domanski-ai/headroom rotator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/domanski-ai/headroom.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/integrations/claude-code/skills/rotator .gemini/skills/rotator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "rotator" agent skill from https://github.com/domanski-ai/headroom/tree/master/integrations/claude-code/skills/rotator into .gemini/skills/rotator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rotator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install domanski-ai/headroom rotatorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add domanski-ai/headroom --skill rotator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/domanski-ai/headroom.git skills-src && mkdir -p .github/skills && cp -r skills-src/integrations/claude-code/skills/rotator .github/skills/rotator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "rotator" agent skill from https://github.com/domanski-ai/headroom/tree/master/integrations/claude-code/skills/rotator into .github/skills/rotator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rotator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add domanski-ai/headroom --skill rotator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install domanski-ai/headroom rotator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/domanski-ai/headroom.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/integrations/claude-code/skills/rotator .opencode/skills/rotator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "rotator" agent skill from https://github.com/domanski-ai/headroom/tree/master/integrations/claude-code/skills/rotator into .opencode/skills/rotator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rotator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
rotatorSwitches to the next connected Claude or Codex account that has proven capacity when a session or weekly usage limit is hit, using the headroom CLI.
When a command or session fails with a session, weekly or usage-limit error, or you ask which account has capacity, the agent runs headroom rotate for the chosen model family (claude by default). The tool cools the exhausted account down until its window resets, picks the next login with proven headroom in your configured preference order and prints the export line for it. The agent relays the one-line result as it is.
If every account is limited, the command exits with code 2 and the agent reports the earliest reset time instead of failing silently or switching to a weaker model. A status view is available through headroom status. Account changes go through headroom connect and setup, never by editing the config file by hand. The new account applies to new sessions that inherit CLAUDE_CONFIG_DIR or CODEX_HOME, so the current session needs a restart to move.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 4cdc772. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Account Rotator for Usage Limits loads about 483 tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 221 words of instructions outside code blocks.
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.
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.
The full file from domanski-ai/headroom at commit 4cdc772, republished under its MIT licence (© domanski-ai). 221 words, ~483 tokens.
.claude/skills/rotator/SKILL.md (or your agent's skills folder).Rotate BETWEEN connected logins for the same provider when one hits a usage
limit. Powered by the headroom CLI (https://github.com/domanski-ai/headroom).
/rotator (optionally /rotator <model>, default claude).headroom rotate <model> (default model family: claude).
It cools the current account down until its window resets, picks the next
login with PROVEN headroom, and prints the export line for the new account.rotated <old> -> <new> (<family>); <old> cools until <reset>.headroom status <model> and show the table.~/.headroom/config.json by hand from this skill; account
changes go through headroom connect / headroom setup.CLAUDE_CONFIG_DIR (or CODEX_HOME). The current interactive session keeps
its own login; tell the user to restart the session if they want it moved.© domanski-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in integrations/claude-code/skills/rotator of domanski-ai/headroom.
Open the folder on GitHubat commit 4cdc772
Account Rotator for Usage Limits 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Account Rotator for Usage Limits this skilldomanski-ai/headroom | 107 | — | ~483 | Automated safety check: Pass | MIT | |
| Agent Browser CLIvercel-labs/agent-browser | 44k | 24 repos | ~864 | Automated safety check: Pass | Apache-2.0 | |
| Dev Browser AutomationMemTensor/MemOS | 12k | 3 repos | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Electron App Automationvercel-labs/agent-browser | 44k | 5 repos | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Next Dev Loopvercel/next.js | 143k | 9 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Skyvern Browser AutomationSkyvern-AI/skyvern | 23k | 1 repos | ~2.9k | Automated safety check: Pass | AGPL-3.0 |
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
MemTensor/MemOS
Automates a real browser through short TypeScript scripts that keep page state between runs, for navigating, filling forms, taking screenshots and extracting data.
vercel-labs/agent-browser
Automates Electron desktop apps such as VS Code, Slack or Discord by connecting agent-browser to their Chrome DevTools Protocol port.
vercel/next.js
Verify Next.js runtime behavior after editing app code. An agent skill from vercel/next.js.
Skyvern-AI/skyvern
Picks the right Skyvern CLI command for a web task, from quick yes/no checks to reusable multi-page workflows, instead of falling back to plain page fetching.
telegramdesktop/tdesktop
Audit Telegram Desktop dependencies on freshly fetched origin/dev for releases and security fixes, including upstream lag and backport candidates in patched forks.
Categories
Switches to the next connected Claude or Codex account that has proven capacity when a session or weekly usage limit is hit, using the headroom CLI. When a command or session fails with a session, weekly or usage-limit error, or you ask which account has capacity, the agent runs headroom rotate for the chosen model family (claude by default). The tool cools the exhausted account down until its window resets, picks the next login with proven headroom in your configured preference order and prints the export line for it.
Account Rotator for Usage Limits fits situations like: hitting a session or weekly usage limit on one connected account; checking which of your accounts still has capacity; seeing when an exhausted account becomes usable again.
Run `npx skills add domanski-ai/headroom --skill rotator -a claude-code`. Or copy the skill folder (integrations/claude-code/skills/rotator in domanski-ai/headroom) into .claude/skills/rotator in your project. Claude Code loads it when a task matches its description.
Run `npx skills add domanski-ai/headroom --skill rotator -a codex`. Or copy the skill folder (integrations/claude-code/skills/rotator in domanski-ai/headroom) into .agents/skills/rotator in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add domanski-ai/headroom --skill rotator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rotator, .gemini/skills/rotator, .github/skills/rotator and .opencode/skills/rotator in your project.
SKILL.md names no scripts, command-line tools or credentials: Account Rotator for Usage Limits is instructions for the agent only. Our summary lists: The headroom CLI with connected accounts configured.
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.
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.
Account Rotator for Usage Limits is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 483 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Account Rotator for Usage Limits: Agent Browser CLI (vercel-labs/agent-browser, 44k stars), Dev Browser Automation (MemTensor/MemOS, 12k stars), Electron App Automation (vercel-labs/agent-browser, 44k stars) and Next Dev Loop (vercel/next.js, 143k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
domanski-ai (a GitHub user) maintains it in domanski-ai/headroom, which has 107 GitHub stars. The repository was last updated on August 25, 2026.
Source: domanski-ai/headroom on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.