browse
Browser automation via the agent-browser CLI, for login flows, screenshots, page interaction and DOM extraction.
Skill by kronael
Chalk Labs
Need help deploying browse?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kronael-browse
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/browse
Tools it pre-approves 1
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(agent-browser:*)
What's inside
- Skill name
browse- Description
- Browser automation via the agent-browser CLI, for login flows, screenshots, page interaction and DOM extraction. NOT for plain HTTP fetches. ALWAYS run it through Bash — NEVER as an Agent subagent type.
- License
- Unlicense
- Allowed tools
- Bash(agent-browser:*)
- Instructions
- 81 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (2)
- SKILL.md
- debug.md
SKILL.md (first lines)
# Browser Automation with agent-browser ## Core workflow 1. `agent-browser open <url>` 2. `agent-browser snapshot -i` (interactive elements with refs like `@e1`) 3. Interact using refs 4. Re-snapshot after navigation or significant DOM changes ## Commands ```bash # Navigation agent-browser open <url> | back | forward | reload | close # Snapshot agent-browser snapshot [-i interactive] [-c compact] [-d depth] [-s selector] # Interact (use @refs from snapshot) agent-browser click|dblclick|hover @e1 agent-browser fill @e2 "text" # Clear and type agent-browser type @e2 "text" # Type without clearing agent-browser press Enter agent-browser check|uncheck @e1 agent-browser select @e1 "value" agent-browser scroll down 500 agent-browser upload @e1 file.pdf # Get info agent-browser get text|html|value @e1 agent-browser get attr @e1 href agent-browser get title|url agent-browser get count ".item" # Screenshot/PDF agent-browser screenshot [path.png] [--full] agent-browser pdf output.pdf # Wait agent-browser wait @e1 | 2000 | --text "Success" | --url "pattern" | --load networkidle # Semantic locators (alternative to refs) agent-browser find role button click --name "Submit" agent-browser find text "Sign In" click agent-browser find label "Email" fill "user@test.com" # Auth state agent-browser state save|load auth.json # Storage agent-browser cookies [set name value | clear] agent-browser storage local [set k v] agent-browser eval "document.title" ``` ## Rules - ALWAYS `agent-browser wait --load networkidle` (or wait --text/--url) BEFORE snapshot on dynamic pages; NEVER snapshot directly after `open` on SPAs — refs will be stale - ALWAYS prefer `find role --name`, `find text`, `find label` over numbered `@eN` refs; `@eN` refs are valid only within one snapshot — NEVER reuse across navigations - ALWAYS `agent-browser screenshot err.png --full` before reporting an unexpected failure ## Coordinate clicks (canvas, maps, custom renderers) ALWAYS use `mouse` for coordinate-based clicks. JS `MouseEvent` has `isTrusted=false` and is blocked by security-conscious apps; `mouse` sends real CDP input events with `isTrusted=true`. ```bash agent-browser mouse move 930 120 agent-browser mouse down agent-browser mouse up ``` ## Debugging: console, page errors, network, perf, memory `agent-browser` snapshots and clicks but does NOT stream console logs, network, or performance/heap. For those drive Playwright directly from a script — ALWAYS read `debug.md` in this directory first: the one-time browser install, the capture script, the refetch / freeze / leak recipes and the stale-build trap.
From kronael/tools, Unlicense.
More from kronael/tools
- 0.622score
distill
kronael
/distill — Use when compressing a long document, transcript, or codebase into its essence.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
eval
kronael
Evaluation router — judge a product, codebase, UI or engineer from one fixed lens or every lens.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
kronael-sync
kronael
Sync Kronael into ~/.claude from Codex (bundle + CLI tools rig/udfix/spec-lint/dockbox), first setup included; bridge global/project CLAUDE.md, skills, and…
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
ans
kronael
/ans — answer-only mode toggle, NEVER edit files or run shell; /ans end exits.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
astgrep
kronael
Structural code search and rewrite with ast-grep (tree-sitter AST patterns).
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
astra
kronael
Ask the codex CLI on gpt-6-astra (or gpt-6.1-sol, the Sol variant) for a second opinion, usually routed through oracle.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
bugs
kronael
The `BUGS.md` open-issues queue — record-don't-fix policy, entry format, pruning.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
codemap
kronael
Map a codebase and drill into it — ranked overview, callers, blast radius, module, import and call graphs.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
continue
kronael
/continue — goal mode.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
create
kronael
Router for creative artifact generation — CVs, web pages, explainers, videos, generative art, diagrams.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
diagrams
kronael
ASCII architecture and workflow diagrams using Unicode box-drawing chars.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
dispatch
kronael
/dispatch — launch a background subagent at default model; § Tiers is the one table of every model tier, Claude and Codex.
SkillAFreshness: A★ 6Claude Code +9
Signals
- Stars
- 6
- Forks
- 3
- Open issues
- 0
- Last commit (this folder)
- Oct 22, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Unlicense
- Repository
- github.com/kronael/tools
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kronael
- 0.622score
distill
kronael
/distill — Use when compressing a long document, transcript, or codebase into its essence.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
kronael-sync
kronael
Sync Kronael into ~/.claude from Codex (bundle + CLI tools rig/udfix/spec-lint/dockbox), first setup included; bridge global/project CLAUDE.md, skills, and…
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
ans
kronael
/ans — answer-only mode toggle, NEVER edit files or run shell; /ans end exits.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
astgrep
kronael
Structural code search and rewrite with ast-grep (tree-sitter AST patterns).
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
astra
kronael
Ask the codex CLI on gpt-6-astra (or gpt-6.1-sol, the Sol variant) for a second opinion, usually routed through oracle.
SkillAFreshness: A★ 6Claude Code +9 - 0.619score
eval
kronael
Evaluation router — judge a product, codebase, UI or engineer from one fixed lens or every lens.
SkillAFreshness: A★ 6Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get browse running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
browse skill. Agent Mart. https://agentmart.dev/skills/kronael-browse (last updated 2026-10-24)