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/ulises-jeremias/agent-toolkit/chrome-devtoolsnpx skills add ulises-jeremias/agent-toolkit --skill chrome-devtoolsgit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWrote 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/ulises-jeremias/agent-toolkit/chrome-devtools)<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/chrome-devtools"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/chrome-devtools.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00050 | $0.02106 |
| Opus 5 | $0.00025 | $0.01053 |
| Sonnet 5 | $0.00010 | $0.00421 |
| Haiku 4.5 | $0.00005 | $0.00211 |
Grade A, and why
chrome-devtools scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`list_network_requests` + `get_network_request` (HAR-like), `list_console_messages` with source-mapped stacks. Prefer over `curl` when JS rendering or auth is involved. How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome DevTools
Control and inspect a live Chrome browser via the official ChromeDevTools/chrome-devtools-mcp (chrome-devtools-mcp, Apache-2.0) MCP server. Gives your coding agent the full power of Chrome DevTools for runtime debugging, network inspection, performance analysis, and rendering diagnostics — while playwright-cli remains the primary tool for deterministic interaction and E2E validation.
Complementarity:
playwright-cli→ deterministiclocator/snapshot/assertworkflows, multi-tab, traces, screenshots.chrome-devtools→ network + console + performance traces + rendering diagnostics + Puppeteer-based reliable automation via DevTools. Do not re-implement Playwright flows via DevTools JSON-RPC; pick the right provider per capability (see decision table).
When to use which provider
| Need | Use playwright-cli |
Use chrome-devtools |
Either |
|---|---|---|---|
| Click / fill / navigate deterministically | ✅ locators, snapshot → stable eN refs, fixtures |
— | |
| Take screenshot of rendered state (verification required before declaring UI good) | ✅ screenshot + trace |
✅ take_screenshot + rendering inspection |
✅ |
| Assert E2E condition / generate test | ✅ assertions, e2e-runner specs |
— | |
| Inspect DOM / accessibility tree / computed styles | snapshot (a11y-aware) limited |
✅ DOM, a11y tree, style inspection | |
| Network requests / console messages / runtime debugging | limited | ✅ list_network_requests, console, source-mapped stack traces |
|
| Performance trace / CrUX field data / insights | — | ✅ performance_* tools + CrUX |
|
| Reliable automation that auto-waits | — | ✅ Puppeteer-based click/type/navigate via DevTools |
|
| Extract JS-rendered data quickly | ✅ snapshot + CLI loop |
Rule for design workflows: design-improvement and design-assessment use playwright-cli for implement → run → capture (primary capture + interaction); pull in chrome-devtools when browser.network / browser.console / browser.performance / browser.runtime-debug is required. Either MCP alone suffices for degraded mode; together they cover implement → render → capture → inspect → compare → iterate.
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.
- 4d ago First seen · 147 lines · 50 tokens per session scan A 81a9dbb9ba16
chrome-devtools is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 2,106 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (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
vindicate
Use when the user wants to write, add, fix, stabilize (flaky), refactor, run, or audit Playwright browser tests, draft requirements/stories from a recording (no tests), find test-coverage gaps, scaffold a Playwright project, or set up Playwright CI. Vindicate's guided workflow for grounded, conformant Playwright test…
playwright-execute
Run Playwright tests or suites and upload the resulting report to Katalon True Platform. Use when you need to execute Playwright scripts, package scripts, spec files, projects, or suites, configure or verify @katalon/playwright-reporter, upload Playwright reports with Katalon CLI/reporter commands, and verify uploaded…
docs
Scale up scraping and drive interactive pages. Use batchscrape for many URLs, getbatchresults to page through async output, scrapewithactions to interact before scraping, and generatellmstxt to produce a site's AI policy file.
crawlforge-web-scraping
Scrapes web pages and returns clean Markdown, HTML, plain text, links, or metadata using CrawlForge's scrape, fetchurl, extractcontent, extracttext, extractlinks, extractmetadata, mapsite, and crawldeep tools. Use when the user wants to scrape a URL, fetch a page, get the markdown or text of a website, extract links…
crawlforge-batch-automation
Automates large scraping jobs and browser interactions with CrawlForge's batchscrape, getbatchresults, scrapewithactions, and generatellmstxt tools. Use when the user wants to scrape many URLs at once, batch-scrape a list of pages, collect dozens of product, news, or competitor pages, run browser actions (click, type…
browser-qa
Use when you need lightweight browser QA for a web page, local HTML file, or app: inspect console errors, broken assets, keyboard/focus behavior, viewport readability, and publish evidence-backed findings JSON through a local HTML report viewer.