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 skills add rozek/browsercard-ai-broker --skill browsercard-livegit clone --depth 1 https://github.com/rozek/browsercard-ai-brokerWrote 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/rozek/browsercard-ai-broker/browsercard-live)<a href="https://agentmods.dev/skills/rozek/browsercard-ai-broker/browsercard-live"><img src="https://agentmods.dev/badge/skills/rozek/browsercard-ai-broker/browsercard-live/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/rozek/browsercard-ai-broker/browsercard-live"><img src="https://agentmods.dev/badge/skills/rozek/browsercard-ai-broker/browsercard-live.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 | $0.00079 | $0.02266 |
| Opus 5.5 | $0.00032 | $0.00906 |
| Sonnet 5.5 | $0.00016 | $0.00453 |
| Haiku 4.5 | $0.00008 | $0.00227 |
Grade A, and why
browsercard-live 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: browsercard-live
Work with a live, running BrowserCard instance via the BrowserCard-AIBroker MCP server.
See also:
browsercard-referenceskill — full widget property reference and complete scripting API (apply it alongside this skill to avoid exploratorywidget_getcalls).
Prerequisites
The MCP server (BrowserCard-AIBroker) must be running and BrowserCard must be open in a browser tab. The server exposes 30 tools. All tools except connection_status require an active connection.
Step 1 — Check connection
Always start with connection_status before any other tool call.
connection_status()
connected: true→ proceedconnected: false→ tell the user to open BrowserCard and connect via "Deck menu → MCP Settings…", then retry
The response also gives deck_name and current_card — use them for orientation.
Step 2 — Understand the deck structure
Before making any changes, build a mental model of the deck:
deck_get() → deck metadata (name, dimensions, grid, script)
list_cards() → all cards with id, name, widget count, has_script
list_widgets(card_id) → all widgets on a card with id, name, type, position
Only call list_widgets for cards you actually need to work on. Do not dump all cards upfront.
Tool reference
Connection (group 1)
| Tool | Description |
|---|---|
connection_status |
Connection state, deck name, current card. Works without BC. |
Deck (group 2)
| Tool | Key params |
|---|---|
deck_get |
— |
deck_patch |
props: DeckProps |
deck_save |
— (persists to IndexedDB) |
DeckProps (all optional): Name, readOnly, swipeToAdjacentCard, Script, CardWidth, CardHeight, SnapToGrid, GridWidth, GridHeight
Navigation (group 3)
| Tool | Key params |
|---|---|
list_cards |
— |
list_widgets |
card_id |
find |
query: FindQuery |
FindQuery (all optional): scope (cards/widgets/all), namePattern, widgetType, valueContains, scriptContains
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.
- 2mo ago First seen · 254 lines · 79 tokens per session scan A 8607603bd2d9
browsercard-live is a skill published in the GitHub repository rozek/browsercard-ai-broker (0 stars, last pushed 3mo ago), licensed MIT. It adds 79 tokens to every session and 2,266 once invoked, about $0.0003 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.
browsercard-live compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| browsercard-liverozek/browsercard-ai-broker | Skill | 0 | 3mo ago | MIT | A | 79 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | today | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | today | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.9k | today | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 906 | yesterday | MIT | A | 40 | Claude Code |