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 commands/serkan-ozal/browser-devtools-claude/browser-referencegit clone --depth 1 https://github.com/serkan-ozal/browser-devtools-claudeWhat 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 | $0.00000 | $0.00415 |
| Opus 5 | $0.00000 | $0.00208 |
| Sonnet 5 | $0.00000 | $0.00083 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
browser-reference 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 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.
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.
What it actually says
Browser Platform Commands
Use with PLATFORM=browser. Web automation via Playwright.
| Command | Tool(s) |
|---|---|
| /browse | navigation_go-to |
| /screenshot | content_take-screenshot |
| /click, /fill, /hover | interaction_click, interaction_fill, interaction_hover |
| /select, /drag, /scroll | interaction_select, interaction_drag, interaction_scroll |
| /keypress | interaction_press-key |
| /html, /text, /pdf | content_get-as-html, content_get-as-text, content_save-as-pdf |
| /accessibility | a11y_take-aria-snapshot, a11y_take-ax-tree-snapshot |
| /console, /network, /webvitals | o11y_get-console-messages, o11y_get-http-requests, o11y_get-web-vitals |
| /trace | o11y_set-trace-id, o11y_get-trace-id, o11y_new-trace-id |
| /intercept, /mock | stub_intercept-http-request, stub_mock-http-response |
| /reload, /back, /forward | navigation_reload, navigation_go-back-or-forward |
| /resize | interaction_resize-viewport, interaction_resize-window |
| /figma | figma_compare-page-with-design |
| /react | react_get-component-for-element, react_get-element-for-component |
| /wait | sync_wait-for-network-idle |
| /otel | o11y_get-trace-id, o11y_get-console-messages |
| /run-js | See run-js-browser — use execute (in page: page.evaluate(); server VM: no page). |
| (batch) | execute — no slash command; use from agent/skill or CLI run execute or daemon POST /call. See commands/browser/execute.md for VM API (callTool, page). |
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 · 25 lines · 0 tokens per session scan A 17fc593c3df8
browser-reference is a command published in the GitHub repository serkan-ozal/browser-devtools-claude (8 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 415 tokens. 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 commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.