Borrowing it
Nothing to install: this file belongs to hlalljie/agent-workflow-presets. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hlalljie/agent-workflow-presets/main/.cursor/skills/testing/run-manual-browser-test/SKILL.mdgit clone --depth 1 https://github.com/hlalljie/agent-workflow-presetsWrote 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/hlalljie/agent-workflow-presets/run-manual-browser-test)<a href="https://agentmods.dev/skills/hlalljie/agent-workflow-presets/run-manual-browser-test"><img src="https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/run-manual-browser-test/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/hlalljie/agent-workflow-presets/run-manual-browser-test"><img src="https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/run-manual-browser-test.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 | $0.00050 | $0.00393 |
| Opus 5.5 | $0.00020 | $0.00157 |
| Sonnet 5.5 | $0.00010 | $0.00079 |
| Haiku 4.5 | $0.00005 | $0.00039 |
Grade A, and why
run-manual-browser-test 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 22d 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
Run manual browser test
Job
Always spawn a subagent to execute this skill. When running multiple checklists, spawn one subagent per checklist in parallel. Execute one tests/manual/*.md checklist as written. Does not change application code or the checklist file (unless the procedure says to note results elsewhere).
Before any browser tool call
- Read the checklist file end-to-end.
- Start state — start server with exact env/command from doc; use entry URL from doc. No improvised production URLs.
- Preconditions — build, fixtures, flags satisfied.
- Vitest prerequisite — if present, run in terminal first, confirm success.
- MCP browser — read project/browser tool schemas; snapshot before clicks; fresh snapshot after navigation; use refs from latest snapshot only.
Execution
- Walk Procedure steps in order; compare to pass / fail criteria.
- Blocked (no server, login, prod only) → report BLOCKED, do not PASS.
- Done → report PASS or FAIL with which step broke.
Typical callers
run task loop, verify commit, run tests, or standalone QA.
Related
write manual browser test for creating/updating the same files.
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.
- 22d ago Changed bfb8816d9d1b
- 1mo ago First seen · 36 lines · 50 tokens per session scan A 6ada55da849b
run-manual-browser-test is a skill published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 20d ago), licensed MIT. It adds 50 tokens to every session and 393 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
cast-verify
Prove the work before calling it done, and leave the evidence where reviewers read it. Runs the repository's checks, exercises the change in the human's own browser or on the command line, captures screenshots or output, attaches them to the task and the thread, and only then marks the work done. Use before declaring…
e2e-check
Run E2E tests or interactive browser verification. Triggers on: 'run e2e', 'e2e test', 'browser test', 'check in browser', 'verify UI', 'interactive test'.
aif-test
Run unit, integration, e2e and UI tests with coverage analysis, build verification, visual regression and QA reports.
ac-qa-e2e-review
Reviews spec implementation with E2E visual browser validation via Playwright. Triggers on keywords: e2e review, visual review, spec review, browser validation.
ac-qa-test-e2e
Executes E2E tests from definition files with Playwright browser automation. Triggers on keywords: test e2e, run e2e, execute e2e test, e2e test runner.
ac-qa-browser
Opens browser at URL for E2E testing via playwright-cli. Provides CLI commands for navigation, screenshots, and interaction. Triggers on keywords: browser, open browser, playwright browser, e2e browser.