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 GZ-L/agent-cardroom --skill play-cardroomgit clone --depth 1 https://github.com/GZ-L/agent-cardroomWrote 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/gz-l/agent-cardroom/play-cardroom)<a href="https://agentmods.dev/skills/gz-l/agent-cardroom/play-cardroom"><img src="https://agentmods.dev/badge/skills/gz-l/agent-cardroom/play-cardroom/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/gz-l/agent-cardroom/play-cardroom"><img src="https://agentmods.dev/badge/skills/gz-l/agent-cardroom/play-cardroom.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 | $0.00021 | $0.00269 |
| Opus 5 | $0.00010 | $0.00134 |
| Sonnet 5 | $0.00004 | $0.00054 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
play-cardroom 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
Play Cardroom
Use the agent-cardroom MCP server to play poker. All chips are virtual and
have no cash value.
Before asking the human player to act, call get_table and use its result to
determine whose turn it is, the current cards, and the legal actions. Do not invent cards, opponents, chip counts, game state, or legal actions: report only values returned by the server.
To begin a hand, call start_game with the requested game and opponents, then
call render_table with the returned game_id. This opens the interactive
table in the current Agent conversation. The player can then click the legal
action and virtual-Token amount options directly; those controls call the
server tools and redraw from their results.
If the client does not render the table or the player explicitly asks to play
in text, call the relevant game-action tool with the player's selected legal
action, then call get_table and render_table before presenting the next
choice.
Always label every Token and chip amount as virtual only. Do not offer real-money play, payments, wagering, conversion, or account services.
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 · 27 lines · 21 tokens per session scan A 1639892fdff2
play-cardroom is a skill published in the GitHub repository GZ-L/agent-cardroom (0 stars, last pushed 23d ago), licensed MIT. It adds 21 tokens to every session and 269 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 skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration in proposals and decision-facing writing. Use when the user asks to rewrite or audit a proposal, plan, research contribution, executive summary, or similar text for directness. Do not use for ordinary code work or unrelated prose.