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/jnarowski/agentcmd/use-browsergit clone --depth 1 https://github.com/jnarowski/agentcmdWhat 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 | $0.00012 | $0.00699 |
| Opus 5 | $0.00006 | $0.00349 |
| Sonnet 5 | $0.00002 | $0.00140 |
| Haiku 4.5 | $0.00001 | $0.00070 |
Grade A, and why
use-browser 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Browser to Verify Feature
Automates browser testing to verify a feature is working correctly in the application. Logs into the app using test credentials, validates the feature, and iterates on fixes until successful.
Variables
- $featureSteps: $1 (required) - Description of the feature to verify (e.g., "user can create new projects", "dashboard displays metrics correctly")
- $testUrl: fetch TEST_URL from env
- $testUsername: fetch TEST_USERNAME from env
- $testPassword: fetch TEST_PASSWORD from env
Instructions
- ALWAYS use Playwright MCP tools for browser automation
- Log in using credentials from environment variables TEST_USERNAME and TEST_PASSWORD
- Login URL: $testUrl
- Test the feature thoroughly based on the description provided
- If issues are found, fix them and re-test
- DO NOT finish until the feature is verified as working
- Take screenshots of failures to help with debugging
- Report all issues found and fixes applied
Workflow
-
Authenticate
- Navigate to $testUrl from environment
- Fill in username field with $testUsername from environment
- Fill in password field with $testPassword from environment
- Submit the login form
- Verify successful login (check for redirect or dashboard)
-
Test the Feature
- Navigate to the relevant page/section for the feature
- Perform the actions described in $featureSteps
- Capture any errors, unexpected behavior, or visual issues
- Take screenshots if verification fails
-
Iterate on Issues
- If issues found: a. Document the specific problem b. Identify the root cause (use code search, read relevant files) c. Implement fixes to the codebase d. Return to step 1 (re-authenticate and re-test)
- Repeat until feature works correctly
-
Final Verification
- Run one complete end-to-end test of the feature
- Verify no console errors or warnings
- Confirm expected behavior matches requirements
- Document the successful test result
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 First seen · 97 lines · 12 tokens per session scan A daba5c048d0e
use-browser is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 12 tokens to every session and 699 once invoked, about $0.0001 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 2026-09-01.
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.