agent-chrome
Read web pages, or act on the user's signed-in accounts, in the user's agent Chrome.
Skill by 265866
Chalk Labs
Need help deploying agent-chrome?
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/265866-agent-chrome
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: design, backend, cloud, security
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. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-chrome
What's inside
- Skill name
agent-chrome- Description
- Read web pages, or act on the user's signed-in accounts, in the user's agent Chrome. Use whenever WebFetch, curl, or another plain fetch fails or returns an unusable page, such as HTTP 403 or 429, a timeout, "unable to fetch", a Cloudflare or bot check, or a JavaScript-only page. Use it before falling back to secondary sources or reporting a page as unreadable. Use it for pages behind the user's sign-in, such as account usage, billing, settings, consoles, OAuth consent, and eBay or Facebook Marketplace comps. Prefer an official CLI or API that already authenticates, and use control-ui for local UI.
- License
- unknown
- Instructions
- 97 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- agent-chrome.ts · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from 265866/claude-config
- 0.565score
god-recipe
265866
Build a "god recipe" for a dish: find the web's highest-rated, best-tested recipes, compare them side by side, and synthesize one best version, with strict…
SkillAFreshness: AClaude Code +9 - 0.565score
listing-photos
265866
Prepares item photos for a Facebook Marketplace listing: straightens tilt and keystone, brightens shadows, converts to sRGB, strips metadata, blurs plates and…
SkillAFreshness: AClaude Code +9 - 0.565score
architect
265866
Ground consequential design choices, sketch caller usage, types and module boundaries, and verify implementation against the chosen design.
SkillAFreshness: AClaude Code +9 - 0.564score
go-best-practices
265866
Go best practices.
SkillAFreshness: AClaude Code +9 - 0.561score
interrogate
265866
Use for "interrogate", "adversarial review", "multi-reviewer review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillAFreshness: AClaude Code +9 - 0.559score
full-send
265866
Use when Colton gives "full send" or "full stop" as the instruction for a task, not as emphasis or a request to halt.
SkillAFreshness: AClaude Code +9 - 0.559score
edit-prose
265866
Edit prose for clear wording, concrete claims, and the intended tone.
SkillAFreshness: AClaude Code +9 - 0.559score
homelab
265866
Look up or update which host runs a self-hosted service, on which port, and where it is defined, across the user's tailnet (moss, redwood, mycelium…
SkillAFreshness: AClaude Code +9 - 0.559score
arena
265866
Compare independently produced artifacts against a rubric, then synthesize and verify one coherent result.
SkillAFreshness: AClaude Code +9 - 0.559score
control-ui
265866
Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI.
SkillAFreshness: AClaude Code +9 - 0.556score
clean-code
265866
Simplify a scoped diff, remove unnecessary comments and defensive code, and resolve type workarounds while preserving behavior and repository style.
SkillAFreshness: AClaude Code +9 - 0.554score
full-stop
265866
Use when Colton gives "full stop" as the instruction for a task, not as emphasis or a request to halt.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 14, 2026 (16 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/265866/claude-config
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from 265866
- 0.565score
architect
265866
Ground consequential design choices, sketch caller usage, types and module boundaries, and verify implementation against the chosen design.
SkillAFreshness: AClaude Code +9 - 0.565score
listing-photos
265866
Prepares item photos for a Facebook Marketplace listing: straightens tilt and keystone, brightens shadows, converts to sRGB, strips metadata, blurs plates and…
SkillAFreshness: AClaude Code +9 - 0.565score
god-recipe
265866
Build a "god recipe" for a dish: find the web's highest-rated, best-tested recipes, compare them side by side, and synthesize one best version, with strict…
SkillAFreshness: AClaude Code +9 - 0.564score
go-best-practices
265866
Go best practices.
SkillAFreshness: AClaude Code +9 - 0.561score
interrogate
265866
Use for "interrogate", "adversarial review", "multi-reviewer review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillAFreshness: AClaude Code +9 - 0.559score
arena
265866
Compare independently produced artifacts against a rubric, then synthesize and verify one coherent result.
SkillAFreshness: AClaude 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 agent-chrome 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
agent-chrome skill. Agent Mart. https://agentmart.dev/skills/265866-agent-chrome (last updated 2026-10-24)