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 rules/udecode/plate-template/agent-browser-issuegit clone --depth 1 https://github.com/udecode/plate-templateWhat 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 | $0.00052 | $0.00318 |
| Opus 5 | $0.00026 | $0.00159 |
| Sonnet 5 | $0.00010 | $0.00064 |
| Haiku 4.5 | $0.00005 | $0.00032 |
Grade A, and why
agent-browser-issue 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 yesterday.
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.
This is a copy
100% identical to agent-browser-issue — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Agent Browser Issue
Handle $ARGUMENTS.
Use this only for likely reusable agent/browser tooling bugs. Do not use it for:
- auth or SSO gates
- manual human gates
- product bugs on the site itself
- one-off flaky noise with no minimal repro
Collect
Capture only the minimum:
- page or URL
- action attempted
- exact block
- expected vs actual
- minimal repro
- screenshot only if it adds signal
Issue
Open a GitHub issue with:
- a short title focused on the browser/tool failure
- label
agent:browser - concise body
Body shape:
## URL
<url>
## Action
<what the agent tried>
## Block
<what failed>
## Expected
<what should have happened>
## Actual
<what happened instead>
## Repro
1. ...
2. ...
3. ...
After
- if the browser/tool failure exposes a user-action parity gap, load
agent-native-reviewerand note that gap in the issue - link the issue in the task caveat or handoff
- keep moving if the product task is still otherwise fixable
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.
- yesterday First seen · 66 lines · 52 tokens per session scan A 6717bcbcb296
agent-browser-issue is a cursor rule published in the GitHub repository udecode/plate-template (59 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 318 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agent-browser-issue, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
dev-browser
Fallback browser automation with persistent Chrome state. Use only when Browser Use is unavailable or blocked.
browser-debug-setup
One-time setup for a persistent debug browser on 127.0.0.1:9222 for dev-browser --connect. Use when browser work is needed but no reusable debug browser is running yet.
agent-browser-issue
Open a concise GitHub follow-up for reusable browser-use limitations. Use when browser automation is blocked by a likely tool-side issue that is worth fixing separately, especially for clicks, dropdowns, file inputs, focus traps, or other repeatable agent/browser failures.
components
React component architecture for creating composable, accessible components with data attributes. Use when creating/updating composable components, not for higher-level feature/page components.
react
React patterns with destructured props, compiler optimization, Effects, and Tailwind v4 syntax. ALWAYS use when using React.
hard-cut
Remove a feature completely with no backward compatibility. Use when the user says "hard cut", "rip it out", "delete it", "unship", "kill this feature", or wants dead code removed instead of deprecated. Delete the surface, callers, tests, docs, comments, fallbacks, and stubs.