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 skills add fmind/dot --skill chrome-devtoolsgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/chrome-devtools)<a href="https://agentmods.dev/skills/fmind/dot/chrome-devtools"><img src="https://agentmods.dev/badge/skills/fmind/dot/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/fmind/dot/chrome-devtools"><img src="https://agentmods.dev/badge/skills/fmind/dot/chrome-devtools.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00019 | $0.01047 |
| Opus 5.5 | $0.00008 | $0.00419 |
| Sonnet 5.5 | $0.00004 | $0.00209 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
chrome-devtools scanned grade A with 0 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 today.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome DevTools
Use Chrome DevTools MCP or its CLI for live browser diagnostics. playwright owns repeatable end-to-end journeys; web-frontend owns platform implementation guidance.
Setup
Require Node.js LTS, npm/npx, and supported Chrome. Reuse an available DevTools connection; otherwise follow mcp-setup for the active harness. The launch command below uses a reviewed package pin; recheck installed help before updating it.
npx --yes [email protected] --isolated --headless --no-usage-statistics --no-performance-crux
The MCP client starts that process over stdio. Use a dedicated browser profile. Keep remote debugging on loopback; browser content, network bodies, cookies, screenshots, and traces may expose private data. The two opt-out flags disable MCP usage statistics and CrUX URL lookups respectively.
Task guides
- cli: Drive DevTools from the shell with the chrome-devtools CLI daemon instead of an MCP connection.
Workflow
- Identify the target: list pages and select the intended page ID, URL, viewport, and browser mode. Take a fresh accessibility snapshot before using element UIDs; navigation and rerenders can invalidate them.
- Reproduce the symptom: list bounded console errors and failed-request metadata, then inspect only the relevant request IDs and bodies. Reuse a still-current snapshot; refresh it after navigation or a relevant rerender. Save large traces as artifacts instead of returning their raw contents. Redact credentials and private request data.
- Measure performance: record a bounded trace of the same action before and after a change; preserve CPU/network throttling, cache conditions, viewport, and tool versions. Stop traces you started and save artifacts in the authorized workspace.
- Check accessibility: inspect roles, names, focus order, keyboard operation, and visible contrast. Run
lighthouse_auditfor the one-shot accessibility, SEO, and best-practice report; it reloads the page unlessmodeissnapshot, and it excludes performance, which needs a trace. Combine automated checks with manual interaction; an accessibility tree or Lighthouse score alone does not establish WCAG conformance. - Investigate memory and cookies: compare repeated lifecycle actions and heap snapshots;
take_heapsnapshotis on by default, whilecompare_heapsnapshotsand the other analysis tools need--memoryDebuggingon the MCP server; inspectHttpOnly,Secure,SameSite, and partitioning in the request's actual context. A single heap size or cookie attribute is not a diagnosis. - Close task-owned pages: after verifying the fix.
What ships with it
1 file 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.
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.
- today Changed 4cd4c2cde62e
- yesterday Changed 478af6ac7df4
- 18d ago Changed · -2 lines 7b3ea12f3951
- 20d ago Changed cd04842c2f2c
- 21d ago Changed · +6 lines · -1 tokens per session b40c90d4293f
- 23d ago Changed e77b64d36299
- 29d ago Changed 530a3af5fdd1
- 1mo ago Changed · +1 lines · -18 tokens per session c716583bc506
- 1mo ago Changed · +1 lines aef1e8ee67cd
- 1mo ago First seen · 51 lines · 38 tokens per session scan A 3556b5b3d93d
chrome-devtools is a skill published in the GitHub repository fmind/dot (12 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 1,047 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
systematic-debugging
Diagnose unknown-cause bugs, test/build or auth failures, flakes, and runtime performance regressions. Investigate, reduce, localize, falsify hypotheses, and explain root cause before implementation.
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot config init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
gather-context
Build comprehensive understanding of a problem by gathering context from GitHub issues, codebase exploration, git history, and linked references. Use when starting work on an issue or investigating a problem.
taste
Martin's judgement on task-shaped decisions — how to debug, how far to build, what to simplify, what to delete, how to test, what to spend, how to roll out, and how to ask him a question. Load before asking him anything with AskUserQuestion, at any fork where two reasonable approaches diverge, when deciding how much…
diagnose-ci
Investigate failing REMOTE CI runs on GitHub Actions: find the failed run, pull the failed-step logs with gh, identify the root cause (compile error, test failure, lint, missing secret, timeout), and recommend a fix. Read-only: it does not commit, push, or edit. Use when CI is red, a GitHub Actions run failed, or the…