browser-harness
Skill4 starsChanged 6 months agoMITView on GitHub
Direct browser control via CDP. For task-specific edits, use agent-workspace/agent_helpers.py. For setup, install, or connection problems, read https://github.com/browser-use/browser-harness/blob/main/install.md. Domain skills are off by default. Set BH_DOMAIN_SKILLS=1 to enable them; see the bottom section. If BH_DOMAIN_SKILLS=1 and the task is site-specific, read every file in the matching $BH_AGENT_WORKSPACE/domain-skills/<site>/ directory before inventing an approach. If the daemon cannot connect, run diagnostics: If Chrome remote debugging is not enabled, the harness opens: Ask the user to tick "Allow remote debugging for this browser…
10 other projects use a version of this, 5 of them edited.
Adopted by
Most recently taken up by
- davidondrej/cloudroom-coretheir own version, first seen Nov 1, 2026
- davidondrej/cloudroomtheir own version, first seen Nov 1, 2026
- davidondrej/skillsedited, first seen Oct 29, 2026
- edgardoperrelli-maker/claude-skillsedited, first seen Oct 25, 2026
- MarioJames/skill-foundrytheir own version, first seen Oct 11, 2026
- browser-use/browser-harnessedited, first seen Oct 8, 2026
Used with
Projects with it also use adr-verbatim, file-tree and 7 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
davidondrejSkilladr-verbatim
Record concise ADRs that preserve the user''s decisions without conversational noise. Use for "adr-verbatim", "new ADR", "document that as an ADR", "record this decision", or supplied ADR wording.
Also in 3 projects that use this
davidondrejSkillfile-tree
Manually-invoked skill that prints a nice file tree of the current topic in a code block. Use when the user says "file-tree" or "file tree".
Also in 3 projects that use this
matyasstochSkilldistribute-skill-to-all-agents
Distribute a newly-created agent skill across all 4 canonical skill folders on a local machine so Claude Code, Codex/OpenAI Agents, Pi Agent, and Hermes all see it. Use whenever the user says "give this skill to all agents", "distribute this skill", "sync skills across agents", or after creating a new skill that should be globally available. Covers the .claude/skills symlink and the ~/.pi/agent/skills (NOT ~/.pi/skills) trap.
Also in 3 projects that use this
attentiondotnetSkillsetup-help
Walk the user through setting up anything step by step. Use when the user asks for help setting up, configuring, installing, or getting something working — "help me set up X", "walk me through this", "setup-help". Differentiator: gives one current step at a time, then always lists every remaining setup step after each response.
Also in 4 projects that use this
matyasstochSkilleffective-agent-skills
How to write effective agent skills — what to do, what not to do, anatomy, progressive disclosure, design patterns, anti-patterns, testing, security. Read this whenever a skill (Claude Skill, Agent Skill, SKILL.md) is being created, edited, reviewed, or debugged. Use when the user says "create a skill", "new skill", "update this skill", "improve a skill", "why isn't my skill triggering", or anything else involving authoring or editing SKILL.md files.
Also in 3 projects that use this
maragudkSkilldecisions
Guide for recording significant architectural and design decisions in docs/decisions.md. Use this skill when clearly significant architectural decisions are made (database choices, frameworks, core design patterns) or when explicitly asked to document a decision. Be conservative - only suggest for major decisions, not minor implementation details.
Also in 3 projects that use this
- +2 more from davidondrej
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 5
- browser-use/browser-harness★ 19k24% same
- davidondrej/skills★ 4.3k10% same
- matyasstoch/david-skills★ 5911% same
- attentiondotnet/davidondrej-skills★ 1110% same
- edgardoperrelli-maker/claude-skills★ 043% same
Wrote their own version · 5
- davidondrej/cloudroom★ 1.5ksame name
- davidondrej/cloudroom-core★ 1.5ksame name
- itgoyo/hermes-skills★ 53same name
- MarioJames/skill-foundry★ 1same name
- Synthenova/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository79 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- 21st-magicSkill
- alpacaSkill
- ask-mattSkill
- autoresearchSkill
- auto-stage-commitSkill
- codebase-designSkill
- codeburnSkill
- codex-reviewSkill
- compact-memorySkill
- connect-recommendSkill
- connect-required-verification-informationSkill
- decision-mappingSkill
- delegate-taskSkill
- design-an-interfaceSkill
- design-mdSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- edit-articleSkill
- extract-designSkill
- ffmpegSkill
- find-skillsSkill
- firecrawlSkill
- generateSkill
- git-guardrails-claude-codeSkill
- grillingSkill
- grill-me-codexSkill
- grill-meSkill
- grill-with-docs-codexSkill
- grill-with-docsSkill
- gwSkill
- handoffSkill
- implementSkill
- improve-codebase-architectureSkill
- kie-aiSkill
- lightragSkill
- llmfitSkill
- loop-meSkill
- migrate-to-shoehornSkill
- notebooklmSkill
- obsidian-vaultSkill
- openspaceSkill
- playwrightSkill
- prototypeSkill
- qaSkill
- request-refactor-planSkill
- resolving-merge-conflictsSkill
- reviewSkill
- roastSkill
- scaffold-exercisesSkill
- session-handoffSkill
- setup-matt-pocock-skillsSkill
- setup-pre-commitSkill
- site-teardownSkill
- skill-discoverySkill
- skilluiSkill
- spline-3dSkill
- stripe-appsSkill
- stripe-best-practicesSkill
- stripe-directorySkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 0 are common, 4 are distinctive, and 10 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
If the daemon cannot connect, run diagnostics:
- Distinctive: line 35
If Chrome remote debugging is not enabled, the harness opens:
- Very specific: line 41
Ask the user to tick "Allow remote debugging for this browser instance" and click Allow if Chrome shows a permission popup.
- Distinctive: line 45
Use Browser Use cloud for headless servers, parallel sub-agents, or isolated work.
- Very specific: line 70
When the task is done and a cloud browser is still running, ask directly: "Should I close this browser now?" If yes, run …
- Very specific: line 72
Do not start a remote daemon and then keep using the default daemon.
- Very specific: line 80
After navigation, call wait_for_load().
- Very specific: line 81
If the current tab is stale or internal, call ensure_real_tab().
- Very specific: line 82
Use js(...) for DOM inspection or extraction when coordinates are the wrong tool.
- Distinctive: line 88
If you get stuck on a browser mechanic, check https://github.com/browser-use/browser-harness/tree/main/interaction-skills.
- Very specific: line 111
Keep the connection model simple: use the default daemon, BU_NAME, BU_CDP_URL, BU_CDP_WS, or start_remote_daemon(...).
- Very specific: line 121
Ask before leaving cloud browsers running.
- Very specific: line 125
Only applies when BH_DOMAIN_SKILLS=1.
- Very specific: line 127
When enabled, search $BH_AGENT_WORKSPACE/domain-skills/<host>/ before inventing an approach.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
browser-harness
Direct browser control via CDP. For task-specific edits, use agent-workspace/agent_helpers.py. For setup, install, or connection problems, read https://github.com/browser-use/browser-harness/blob/main/install.md.
Domain skills are off by default. Set BH_DOMAIN_SKILLS=1 to enable them; see the bottom section.
If BH_DOMAIN_SKILLS=1 and the task is site-specific, read every file in the matching $BH_AGENT_WORKSPACE/domain-skills/<site>/ directory before inventing an approach.
Usage
browser-harness <<'PY'
print(page_info())
PY- Invoke as
browser-harness. Use heredocs for multi-line commands. - Helpers are pre-imported.
run.pycallsensure_daemon()beforeexec. - First navigation is
new_tab(url), notgoto_url(url). - The normal local flow attaches to the running Chrome/Chromium CDP endpoint. No browser ids or local profile selection.
Local Chrome
If the daemon cannot connect, run diagnostics:
browser-harness --doctorIf Chrome remote debugging is not enabled, the harness opens:
chrome://inspect/#remote-debuggingAsk the user to tick "Allow remote debugging for this browser instance" and click Allow if Chrome shows a permission popup. Then retry the same browser-harness command.
Remote Browsers
Use Browser Use cloud for headless servers, parallel sub-agents, or isolated work. Authenticate once:
browser-harness auth loginOr import a key safely:
browser-harness auth login --api-key-stdinPick a short made-up name; r7k2 below is just a placeholder:
browser-harness <<'PY'
start_remote_daemon("r7k2")
PY
BU_NAME=r7k2 browser-harness <<'PY'
new_tab("https://example.com")
print(page_info())
PYWhen the task is done and a cloud browser is still running, ask directly: "Should I close this browser now?" If yes, run stop_remote_daemon(name). Remote daemons bill until they stop or time out.
Do not start a remote daemon and then keep using the default daemon. Use the same name for BU_NAME.
Cloud profile cookie sync reference: https://github.com/browser-use/browser-harness/blob/main/interaction-skills/profile-sync.md.
Page Workflow
- Screenshots first: use
capture_screenshot()to understand visible state. - Clicking: screenshot -> read pixel ->
click_at_xy(x, y)-> screenshot again. - After navigation, call
wait_for_load(). - If the current tab is stale or internal, call
ensure_real_tab(). - Use
js(...)for DOM inspection or extraction when coordinates are the wrong tool. - Login walls: stop and ask. Exception: use available SSO automatically when Chrome is already signed in; still stop for passwords, MFA, consent, or ambiguous account choice.
- Raw CDP is available with
cdp("Domain.method", ...).
Interaction Skills
If you get stuck on a browser mechanic, check https://github.com/browser-use/browser-harness/tree/main/interaction-skills.
- connection.md
- cookies.md
- cross-origin-iframes.md
- dialogs.md
- downloads.md
- drag-and-drop.md
- dropdowns.md
- iframes.md
- network-requests.md
- print-as-pdf.md
- profile-sync.md
- screenshots.md
- scrolling.md
- shadow-dom.md
- tabs.md
- uploads.md
- viewport.md
Design Constraints
- Coordinate clicks default. CDP mouse events pass through iframes/shadow/cross-origin at the compositor level.
- Keep the connection model simple: use the default daemon,
BU_NAME,BU_CDP_URL,BU_CDP_WS, orstart_remote_daemon(...). - Core helpers stay short. Put task-specific helper additions in
$BH_AGENT_WORKSPACE/agent_helpers.py.
Gotchas
chrome://inspect/#remote-debuggingmust be enabled for local Chrome control.- Chrome may show an "Allow remote debugging?" popup; wait for the user to click Allow.
- Omnibox popups are not real work tabs.
- CDP target order is not Chrome's visible tab-strip order.
BU_CDP_URLis an HTTP DevTools endpoint; the daemon resolves it to WebSocket.- Ask before leaving cloud browsers running; stop them with
stop_remote_daemon(name)orPATCH /browsers/{id} {"action":"stop"}.
Domain Skills
Only applies when BH_DOMAIN_SKILLS=1. Otherwise ignore domain skills.
When enabled, search $BH_AGENT_WORKSPACE/domain-skills/<host>/ before inventing an approach. goto_url(...) returns up to 10 skill filenames for the navigated host.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

