Adonis0123/adonis-skills / skills/chrome-dev-mcp
chrome-dev-mcp
VerifiedUse this skill when the user invokes /chrome-dev-mcp or asks for Chrome DevTools MCP, CDP, list_pages/select_page, UXC packaging for Chrome DevTools, DOM snapshots, Console, Network, Performance, Lighthouse, heap analysis, browser-internal debugging, connection recovery, or correct-Chrome validation across Claude Code, Codex, Grok Build/Grok002, Cursor CLI, Hermes, or WorkBuddy. Use it when the evidence is Chrome-specific (Lighthouse, a full trace, heap data) or the caller has no page session yet; a page already open in ego-browser keeps its own Console and request diagnosis. Also use it as the verification step right after the user or this session changes a web UI or asks to accept or check a page: collect a screenshot, Console, and Network evidence before calling it done. Do not use it for ordinary navigation, form filling, scraping, or desktop UI unless browser-internal signals or UI-change acceptance are required. A passing readiness or list_pages check proves the connection only, never the change.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.4 KB |
| evals/evals.json | config | 14.7 KB |
| evals/trigger-eval.json | config | 3.3 KB |
| references/host-verification.md | markdown | 5.9 KB |
| references/maintenance.md | markdown | 4.5 KB |
| references/profile-identity.md | markdown | 1.6 KB |
| references/uxc-facade.md | markdown | 7.5 KB |
| scripts/configure-local.zshexecutable | script | 1.8 KB |
| scripts/ensure-connection.zshexecutable | script | 2.6 KB |
| scripts/host-acceptance.zshexecutable | script | 6.9 KB |
| scripts/install-uxc.zshexecutable | script | 4.0 KB |
| scripts/lib/load-config.zshexecutable | script | 438 B |
| scripts/lib/readiness-envelope.zsh | script | 1.5 KB |
| scripts/lib/uxc-link-contract.zsh | script | 1.5 KB |
| scripts/lib/uxc-owned-binary.zsh | script | 2.8 KB |
| scripts/lib/uxc-release.zshexecutable | script | 642 B |
| scripts/setup-uxc-link.zshexecutable | script | 3.1 KB |
| scripts/test/host-acceptance.test.mjs | script | 5.3 KB |
| scripts/test/readiness-envelope.test.mjs | script | 2.7 KB |
| scripts/test/ui-acceptance.test.mjs | script | 5.2 KB |
| scripts/uxc-readiness.zshexecutable | script | 2.7 KB |
scripts/test/host-acceptance.test.mjs
View on GitHubimport { test } from "node:test";
import assert from "node:assert/strict";
import { spawnSync } from "node:child_process";
import { chmodSync, mkdtempSync, rmSync, writeFileSync } from "node:fs";
import { tmpdir } from "node:os";
import { dirname, join } from "node:path";
import { fileURLToPath } from "node:url";
const script = join(
dirname(fileURLToPath(import.meta.url)),
"..",
"host-acceptance.zsh",
);
const secretUrl = "http://secret.example/private";
// Fake host CLIs: each prints what a real headless session would capture.
const fakes = {
"chrome-dev-mcp-cli": `print -r -- '{"ok":true,"data":{"content":[{"type":"text","text":"1: Private (${secretUrl}) [selected]"}]}}'`,
claude: `print -r -- '{"type":"assistant","message":{"content":[{"type":"tool_use","input":{"command":"zsh scripts/uxc-readiness.zsh"}}]}}'
print -r -- '{"type":"result","result":"CHROME_DEV_MCP_READY"}'`,
codex: `while (( $# > 0 )); do [[ "$1" == -o ]] && { print -r -- CHROME_DEV_MCP_READY >| "$2"; }; shift; done
print -r -- 'exec chrome-dev-mcp-cli list_pages'`,
grok: `print -r -- '{"type":"thought","data":"prompt says reply CHROME_DEV_MCP_FAIL on failure"}'
print -r -- 'CHROME_DEV_MCP_READY'`,
"cursor-agent": `print -r -- '{"type":"tool_call","command":"zsh scripts/uxc-readiness.zsh"}'
print -r -- '{"type":"result","result":"CHROME_DEV_MCP_READY ${secretUrl}"}'`,
};
function run(args) {
const dir = mkdtempSync(join(tmpdir(), "cdm-acceptance-"));
try {
for (const [name, body] of Object.entries(fakes)) {
const file = join(dir, name);
writeFileSync(file, `#!/bin/zsh\n${body}\n`);
chmodSync(file, 0o755);
}
const result = spawnSync(
"/bin/zsh",
[script, "--out", join(dir, "out"), ...args],
{
encoding: "utf8",
env: { HOME: dir, TMPDIR: dir, PATH: `${dir}:/usr/bin:/bin` },
},
);
const lines = Object.fromEntries(
result.stdout
.split("\n")
.filter((line) => line.startsWith("HOST="))
.map((line) => {
const fields = Object.fromEntries(
line.split(" ").map((pair) => pair.split("=")),
);
return [fields.HOST, fields];
}),
);
return { ...result, hosts: lines };
} finally {
rmSync(dir, { recursive: true, force: true });
}
}
test("hosts with a tool trace and clean sentinel are VERIFIED", () => {
const { hosts } = run(["--host", "claude", "--host", "codex"]);
assert.equal(hosts.claude.RESULT, "VERIFIED");
assert.equal(hosts.codex.RESULT, "VERIFIED");
});
test("a sentinel without a real tool call stays UNVERIFIED", () => {
const { hosts, status } = run(["--host", "grok"]);
assert.equal(hosts.grok.SENTINEL, "READY");
assert.equal(hosts.grok.TOOL_TRACE, "NO");
assert.equal(hosts.grok.RESULT, "UNVERIFIED");
assert.equal(status, 1);
});
test("a page URL in the final answer fails as a leak without printing it", () => {
const { hosts, stdout } = run(["--host", "cursor"]);
assert.equal(hosts.cursor.LEAK, "YES");
assert.equal(hosts.cursor.RESULT, "FAIL");
assert.ok(!stdout.includes(secretUrl));
});
test("--bypass passes the host's approve-everything flag", () => {
const saved = fakes.claude;
fakes.claude = `[[ " $* " == *" --permission-mode bypassPermissions "* ]] || exit 3
${saved}`;
try {
const { hosts } = run(["--host", "claude", "--bypass"]);
assert.equal(hosts.claude.RESULT, "VERIFIED");
assert.equal(hosts.claude.EXIT, "0");
} finally {
fakes.claude = saved;
}
});
test("cursor adds --auto-review only on opt-in and --force only with --bypass", () => {
const saved = fakes["cursor-agent"];
const ready = `print -r -- '{"type":"tool_call","command":"zsh scripts/uxc-readiness.zsh"}'
print -r -- '{"type":"result","result":"CHROME_DEV_MCP_READY"}'`;
const noWide = `[[ " $* " != *" --force "* && " $* " != *" --yolo "* ]] || exit 4`;
try {
fakes["cursor-agent"] = `[[ " $* " != *" --auto-review "* ]] || exit 3
${noWide}
${ready}`;
const normal = run(["--host", "cursor"]);
assert.equal(normal.hosts.cursor.EXIT, "0");
fakes["cursor-agent"] = `[[ " $* " == *" --auto-review "* ]] || exit 3
${noWide}
${ready}`;
const optIn = run(["--host", "cursor", "--cursor-auto-review"]);
assert.equal(optIn.hosts.cursor.EXIT, "0");
assert.equal(optIn.hosts.cursor.RESULT, "VERIFIED");
fakes["cursor-agent"] = `[[ " $* " == *" --force "* ]] || exit 3
${ready}`;
const bypass = run(["--host", "cursor", "--bypass"]);
assert.equal(bypass.hosts.cursor.EXIT, "0");
assert.equal(bypass.hosts.cursor.RESULT, "VERIFIED");
} finally {
fakes["cursor-agent"] = saved;
}
});
test("grok answer ignores sentinels quoted in thoughts", () => {
const saved = fakes.grok;
fakes.grok = `print -r -- '{"type":"thought","data":"reply CHROME_DEV_MCP_FAIL on failure"}'
print -r -- '{"type":"tool_call_update","command":"zsh scripts/uxc-readiness.zsh"}'
print -r -- '{"type":"text","data":"CHROME_DEV_MCP_READY"}'`;
try {
const { hosts } = run(["--host", "grok"]);
assert.equal(hosts.grok.SENTINEL, "READY");
assert.equal(hosts.grok.RESULT, "VERIFIED");
} finally {
fakes.grok = saved;
}
});
test("an unknown host fails closed", () => {
const { status, stderr } = run(["--host", "hermes"]);
assert.equal(status, 69);
assert.match(stderr, /ERROR_CLASS=unknown_host/);
});
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |