Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/manhvann/codexkit/chrome-devtoolsnpx skills add manhvann/codexkit --skill chrome-devtoolsgit clone --depth 1 https://github.com/manhvann/codexkitWhat 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 | $0.00038 | $0.05622 |
| Opus 5 | $0.00019 | $0.02811 |
| Sonnet 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 2d 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 > $SKILL_DIR/.codex/chrome-devtools/tmp/login-test.js << 'EOF' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# Netscape format (from curl/wget): How it starts
The opening of the file, as written. The whole thing — 626 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome DevTools Agent Skill
Browser automation via Puppeteer scripts with persistent sessions. All scripts output JSON.
Skill Location
Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope.
# Detect skill location (no cd needed - scripts use __dirname for paths)
SKILL_DIR=""
if [ -d ".agents/skills/chrome-devtools/scripts" ]; then
SKILL_DIR=".agents/skills/chrome-devtools/scripts"
elif [ -d "$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.
- 2d 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 (88 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 5,622 once invoked, about $0.0002 per session on Opus 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
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
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…
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.
mintlify-preview
Run the public Mintlify product docs site locally for live preview. Use when previewing or iterating on docs under docs/ (.mdx/.md pages, docs.json nav), or when the user says "start the docs", "run mintlify", "preview the docs site".