Agent skill
Connecting the MCP server tells an agent which tools exist. The skill teaches it how to use them well: that numbers expire after every action, that a cookie banner can swallow a click, that a missing number usually means "scroll". It is a Markdown playbook the agent loads only when a task involves a browser.
It's optional. BrowserControl works without it, but with it agents hit fewer stale IDs and retry the wrong element less often.
Install it
The Codex, Claude Code, and OpenCode 2 plugins include the skill. To install it by hand in Claude Code:
mkdir -p .claude/skills/browsercontrol
curl -fsSL https://raw.githubusercontent.com/adityasasidhar/browsercontrol/main/skills/browsercontrol/SKILL.md \
-o .claude/skills/browsercontrol/SKILL.mdmkdir -p ~/.claude/skills/browsercontrol
curl -fsSL https://raw.githubusercontent.com/adityasasidhar/browsercontrol/main/skills/browsercontrol/SKILL.md \
-o ~/.claude/skills/browsercontrol/SKILL.mdRestart Claude Code and confirm with /skills. You can also call it directly with /browsercontrol.
Other agents: the file is plain Markdown with a short YAML header. Paste its body into whatever your client uses for standing instructions, such as a rules file or a system prompt.
Why it costs almost nothing
Skills load in stages:
| Stage | What loads | When |
|---|---|---|
| 1 | The name and one-line description | Every session, about one line |
| 2 | The body of SKILL.md | Only when a task needs a browser, or you type /browsercontrol |
On a task with no browser in it, the agent carries a single sentence.
What's in it
- The loop, and why every action makes the previous screenshot useless.
- Three rules that prevent most failures: an ID lives for one screenshot, no number means hidden rather than absent, and the text map is ground truth.
- How to choose a tool:
findversus scrolling,actversus single calls, extraction versus reading the page,wait_forversus fixed waits. - Behavior to rely on:
type_textreplaces rather than appends,check_checkboxsets rather than toggles, settings like mocks stick until undone, full-page screenshots aren't annotated. - Recipes for forms, debugging, responsive checks, multi-tab research, and recording.
- Recovery: a symptom-to-fix table.
Read it on GitHub.
Docs for agents
This site is published in forms an agent can read directly:
| URL | What it is |
|---|---|
/llms.txt | An index of every page with a one-line summary, following llmstxt.org. |
/llms-full.txt | All of the documentation in one file. |
Any page + .md | That page as plain Markdown, for example /guide/quickstart.md. |
/tools.json | Every tool with its signature, parameters, and return type, generated from the server. |
Each page also has a Copy page button under its title, with options to view the Markdown or open the page in an AI assistant.
