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 skills/udecode/plate-template/agent-browser-issuenpx skills add udecode/plate-template --skill 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 | $0.00057 | $0.00346 |
| Opus 5 | $0.00028 | $0.00173 |
| Sonnet 5 | $0.00011 | $0.00069 |
| Haiku 4.5 | $0.00006 | $0.00035 |
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 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.
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.
- 2d ago First seen · 70 lines · 57 tokens per session scan A 0477f8c6e3dd
agent-browser-issue is a skill published in the GitHub repository udecode/plate-template (59 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 346 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 skills, from other repositories
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.
dev-browser
Fallback browser automation with persistent Chrome state. Use only when Browser Use is unavailable or blocked.
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.
autogoal
Create, verify, repair, and close durable Codex goals with measurable outcomes, evidence gates, plan templates, blocker handling, completion audits, and goal-backed workflow repair.
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.