Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/manhvann/codexkitnpx agentmods add skills/manhvann/codexkit/chrome-devtoolsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/manhvann/codexkit/chrome-devtools)<a href="https://agentmods.dev/skills/manhvann/codexkit/chrome-devtools"><img src="https://agentmods.dev/badge/skills/manhvann/codexkit/chrome-devtools/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/manhvann/codexkit/chrome-devtools"><img src="https://agentmods.dev/badge/skills/manhvann/codexkit/chrome-devtools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 254 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Memory Poisoning · line 109 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium MCP Rug Pull · line 165 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 166 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.05622 |
| Opus 5.5 | $0.00015 | $0.02249 |
| Sonnet 5.5 | $0.00008 | $0.01124 |
| Haiku 4.5 | $0.00004 | $0.00562 |
Grade B, and why
ck:chrome-devtools scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > $SKILL_DIR/.codex/chrome-devtools/tmp/login-test.js << 'EOF' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# Netscape format (from curl/wget): Copies of this mod
1 near-identical copy found in the catalogue:
- vc:chrome-devtools — 91% identical, 67 lines differ
How it starts
The opening of the file, as written. The whole thing — 626 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome DevTools Agent Skill
Browser automation via Puppeteer scripts with persistent sessions. All scripts output JSON.
Skill Location
Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope.
# Detect skill location (no cd needed - scripts use __dirname for paths)
SKILL_DIR=""
if [ -d ".agents/skills/chrome-devtools/scripts" ]; then
SKILL_DIR=".agents/skills/chrome-devtools/scripts"
elif [ -d "$HOME/.codex/skills/chrome-devtools/scripts" ]; then
SKILL_DIR="$HOME/.codex/skills/chrome-devtools/scripts"
fi
# Run scripts with full path: node "$SKILL_DIR/script.js" --args
Choosing Your Approach
| Scenario | Approach |
|---|---|
| Source-available sites | Read source code first, write selectors directly |
| Unknown layouts | Use aria-snapshot.js for semantic discovery |
| Visual inspection | Take screenshots to verify rendering |
| Debug issues | Collect console logs, analyze with session storage |
| Accessibility audit | Use ARIA snapshot for semantic structure analysis |
Automation Browsing Running Mode
Browser visibility is resolved automatically by resolveHeadless() in lib/browser.js:
| Environment | Default | Why |
|---|---|---|
| macOS / Windows | Headed (visible) | Better debugging, OAuth login support |
| Linux / WSL | Headless | Servers typically have no display |
CI (CI, GITHUB_ACTIONS, GITLAB_CI, JENKINS_URL env vars) |
Headless | No display available |
Override with --headless true or --headless false on any script.
- Run multiple scripts/sessions in parallel to simulate real user interactions.
- Run multiple scripts/sessions in parallel to simulate different device types (mobile, tablet, desktop).
ARIA Snapshot (Element Discovery)
When page structure is unknown, use aria-snapshot.js to get a YAML-formatted accessibility tree with semantic roles, accessible names, states, and stable element references.
What ships with it
28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/cdp-domains.md 17 KB
- references/performance-guide.md 21 KB
- references/puppeteer-reference.md 19 KB
- scripts/__tests__/error-handling.test.js 3.6 KB runs code
- scripts/__tests__/selector.test.js 6.4 KB runs code
- scripts/.gitignore 53 B
- scripts/aria-snapshot.js 10 KB runs code
- scripts/click.js 2.4 KB runs code
- scripts/connect-chrome.js 4.1 KB runs code
- scripts/console.js 1.9 KB runs code
- scripts/evaluate.js 1.4 KB runs code
- scripts/fill.js 2.0 KB runs code
- scripts/import-cookies.js 5.7 KB runs code
- scripts/inject-auth.js 7.3 KB runs code
- scripts/install-deps.sh 4.3 KB runs code
- scripts/install.sh 2.1 KB runs code
- scripts/lib/browser.js 9.9 KB runs code
- scripts/lib/selector.js 5.3 KB runs code
- scripts/navigate.js 4.6 KB runs code
- scripts/network.js 2.9 KB runs code
- scripts/package.json 345 B
- scripts/performance.js 4.0 KB runs code
- scripts/README.md 7.9 KB
- scripts/screenshot.js 6.2 KB runs code
- scripts/select-ref.js 3.8 KB runs code
- scripts/snapshot.js 3.6 KB runs code
- scripts/ws-debug.js 1.5 KB runs code
- scripts/ws-full-debug.js 3.3 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 626 lines · 38 tokens per session scan B b7b62d89abca
ck:chrome-devtools is a skill published in the GitHub repository manhvann/codexkit (89 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 5,622 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…