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 Edge-City/agentvillage --skill gold-starsgit clone --depth 1 https://github.com/Edge-City/agentvillageWrote 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/edge-city/agentvillage/gold-stars)<a href="https://agentmods.dev/skills/edge-city/agentvillage/gold-stars"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/gold-stars/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/edge-city/agentvillage/gold-stars"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/gold-stars.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 | $0.00073 | $0.01334 |
| Opus 5.5 | $0.00029 | $0.00534 |
| Sonnet 5.5 | $0.00015 | $0.00267 |
| Haiku 4.5 | $0.00007 | $0.00133 |
Grade A, and why
gold-stars 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gold Stars
Gold Stars are tokens of gratitude in the Village Rolodex. Open: https://agents.edgecity.live/rolodex#gold-stars
The owner can send from this paired private Telegram conversation, or open the website, find the person's card and tap Send star. Use the website when the native tool is unavailable; never bypass it with shell/API calls.
- Each person gets three stars per day, at most one per recipient per day.
- Unused stars expire at midnight Asia/Kolkata (India time); the new day has three stars. This is a calendar-day allowance, not a rolling 24-hour window.
- By default, the gratitude bot posts both names and the note to the village's Gold Stars Telegram topic.
- Send anonymously hides both names and the note in that topic. It still posts anonymous gratitude. The recipient sees the sender and note privately in the Rolodex, and admins can identify the sender and recipient. Do not describe anonymous as hidden from the recipient, admins, or the Telegram feed.
The person's remaining allowance and received stars are live account data.
For remaining allowance, call village with operation: "gold-stars.quota" in
the paired owner's private chat. Quote the returned remaining count, day and
reset time. This tool cannot read received stars or messages. If unavailable,
link to the Rolodex; never assume all three remain. The owner must install Gold
Stars in Mini-apps; the control plane stages this skill and provisions scoped
access for the paired agent. An expired sign-in needs the usual
https://agents.edgecity.live/signin. Never ask for credentials in chat.
Reflection and gratitude
After a relevant meeting follow-up, or when the owner wants to reflect on their day, ask one gentle question such as “Who made your day brighter?” or “Was there a moment you'd like to thank them for?” They can thank someone for a talk, yoga, a conversation, a shared sunset or something said online; no Rolodex meeting mark is required. Offer a star only when it fits their answer. Never infer that a meeting was meaningful, pressure them to use their allowance, repeatedly ask after a decline, or rank people by stars.
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 Changed · +2 lines b9fda16a13a4
- 11d ago Changed · +2 lines 83e1d576b4d5
- 13d ago Changed · +4 lines · +7 tokens per session d32d454d772a
- 15d ago First seen · 89 lines · 66 tokens per session scan A 025b2c3da1e6
gold-stars is a skill published in the GitHub repository Edge-City/agentvillage (21 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 1,334 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 2026-10-13.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.