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.
git clone --depth 1 https://github.com/yechao-zhang/red-team-agent-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/commands/yechao-zhang/red-team-agent-skills/use-dev-browser)<a href="https://agentmods.dev/commands/yechao-zhang/red-team-agent-skills/use-dev-browser"><img src="https://agentmods.dev/badge/commands/yechao-zhang/red-team-agent-skills/use-dev-browser/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/commands/yechao-zhang/red-team-agent-skills/use-dev-browser"><img src="https://agentmods.dev/badge/commands/yechao-zhang/red-team-agent-skills/use-dev-browser.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 | $0.00012 | $0.00298 |
| Opus 5 | $0.00006 | $0.00149 |
| Sonnet 5 | $0.00002 | $0.00060 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
use-dev-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 10d 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
Context
The user explicitly prefers the dev-browser-skill (persistent sessions, stealth) over the generic plugin:playwright (stateless, detectable).
Your Task
When the user asks to "browse", "visit", "test", or "automate" a website, you must:
- Verify that
dev-browser-skillis being used, NOTplaywright. - Guide the agent to use the correct tool if it attempts to use the wrong one.
Guardrails
- NEVER use
plugin:playwrightorplaywright-skillunless explicitly requested. - ALWAYS use
dev-browserfor web interaction tasks. - If
dev-browseris not installed, prompt the user to install it (refer toCLAUDE.md).
Steps
- If a web task is requested, check available tools.
- Select
dev-browsertoolset (e.g.,dev_browser_navigate,dev_browser_click). - If only
playwrightis available, stop and inform the user: "I see you want to browse, but only Playwright is available. Please installdev-browseras per your preference."
Generated by /reflect-skills from repeated user corrections
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.
- 10d ago First seen · 28 lines · 12 tokens per session scan A 3940826da8c3
use-dev-browser is a command published in the GitHub repository yechao-zhang/red-team-agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 298 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 2026-08-31.
Other commands, from other repositories
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
can-i-use
Check browser support for web platform features against the project's browser targets.
gh-issue-use-cypress
Like /gh-issue-use-browser, but pinned to the Cypress MCP — use when your project runs the Cypress MCP for browser automation. Example — /gh-issue-use-cypress "Composer > Save" saving toasts failure but the record persists.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
verify-pr
Verify a PR's frontend changes through browser automation.