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 skyfox675/agents-skills --skill browser-diagnosisgit clone --depth 1 https://github.com/skyfox675/agents-skillsWrote 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/skyfox675/agents-skills/browser-diagnosis)<a href="https://agentmods.dev/skills/skyfox675/agents-skills/browser-diagnosis"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/browser-diagnosis/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/skyfox675/agents-skills/browser-diagnosis"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/browser-diagnosis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
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 →
- medium MCP Rug Pull · line 35 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 36 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 36 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 | $0.00188 | $0.01825 |
| Opus 5 | $0.00094 | $0.00912 |
| Sonnet 5 | $0.00038 | $0.00365 |
| Haiku 4.5 | $0.00019 | $0.00183 |
Grade A, and why
browser-diagnosis 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 11d 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.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Diagnosis (any browser MCP)
Front-end symptoms often can't be root-caused from code alone — the answer is in the real network traffic, the actual API responses, the console, and the DOM as the signed-in user sees it. This skill captures that evidence with whatever browser MCP the environment has, so the workflow isn't tied to one tool. Not everyone can run the Chrome (claude-in-chrome) MCP; Playwright and Cypress MCPs are common alternatives, and Chrome DevTools MCP is another.
Pick the browser MCP (in order), then degrade
claude-in-chrome— best when you need the operator's real signed-in Chrome session (their cookies, their data). Works in its own new tab group.- Playwright MCP — a clean automated browser; great when you can log in with test creds or the page is public.
- Cypress MCP — same idea via a Cypress/Playwright-core runner with ARIA snapshots and network intercept.
- Chrome DevTools MCP — strong for network/console/performance inspection.
Use the first one that's connected. If none is available: don't fake it — give the operator the exact repro steps to run and ask them to paste the failing request/response and console output, or file with code-only evidence and mark the browser-derived claims unverified. Say which.
Capability map (do the same step on any MCP)
| Step | claude-in-chrome | Playwright MCP | Cypress MCP | Chrome DevTools MCP |
|---|---|---|---|---|
| Isolate a context | tabs_context_mcp then a new tab group |
a fresh browser context/tab | its own browser instance | new_page |
| Navigate | navigate |
browser_navigate |
cypress_navigate |
navigate_page |
| Read network | read_network_requests |
browser_network_requests |
cypress_evaluate (fetch/XHR shim) or cy.intercept in a spec |
list_network_requests |
| Read console | read_console_messages |
browser_console_messages |
cypress_evaluate (capture console) |
list_console_messages |
| Run JS / shim fetch | javascript_tool |
browser_evaluate |
cypress_evaluate |
evaluate_script |
| DOM snapshot | read_page / find |
browser_snapshot |
cypress_snapshot (ARIA) |
take_snapshot |
| Click / type | computer |
browser_click / browser_type |
cypress_click / cypress_type |
click / fill |
| Screenshot | gif_creator / computer |
browser_take_screenshot |
cypress_screenshot |
take_screenshot |
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.
- 11d ago First seen · 73 lines · 188 tokens per session scan A 03c8756db2df
browser-diagnosis is a skill published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 188 tokens to every session and 1,825 once invoked, about $0.0009 per session on Opus 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 2026-08-31.
Other skills, from other repositories
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
chrome-performance-optimizer
Autonomous multi-agent performance optimization loop for Chromium and V8. Supports profile-seeded mode (analyzing Speedometer 3 / JetStream profiles via pprof or Sagacity MCP) and pattern-driven discovery mode (fan-out exploration of Blink and V8 macro-patterns grounded in historical wins and past rejected CLs).…
nullaway
Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.