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 edgeosgit 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/edgeos)<a href="https://agentmods.dev/skills/edge-city/agentvillage/edgeos"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/edgeos/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/edgeos"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/edgeos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 29 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 37 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 41 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Data Exfiltration · line 22 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 71 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 78 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 84 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 90 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 96 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 102 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 117 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 128 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 136 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 143 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 150 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 159 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 167 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 175 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 182 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 190 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 197 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00137 | $0.08635 |
| Opus 5.5 | $0.00055 | $0.03454 |
| Sonnet 5.5 | $0.00027 | $0.01727 |
| Haiku 4.5 | $0.00014 | $0.00864 |
Grade A, and why
edgeos scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Talk to the EdgeOS popup-village platform — read the event schedule in the village's local time, RSVP (after asking the person), list venues and who is going to an event (all through the skill's own scripts, How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EdgeOS — Agent Skill
You have access to the EdgeOS popup-village platform. You reach it only through this skill's scripts (bun skills/edgeos/scripts/…), never with curl, wget or code of your own: each script reads the key, the popup id and the EdgeOS address ($EDGEOS_API_BASE, default https://api.edgeos.world/api/v1) itself and refuses any other host. EdgeOS hosts events, RSVPs, venues, the attendee directory, and per-attendee profile lookup for one or more popups.
The current village's popup id is $AV_POPUP_ID. The current event is Edge City India (Mandrem, Goa, October 11 to November 1, 2026). The scripts use it for every event list, venue and directory call themselves; you never type it in. When a script exits 2 saying AV_POPUP_ID is not set, tell the person the village schedule isn't connected to their agent yet and point them to the Edge City portal or the organisers. Never substitute the previous popup's id (the edge-esmeralda skill carries Edge Esmeralda 2026's constant) and present the results as India; use that id only when the person explicitly asks about that previous popup.
0. What you can and cannot do
Your EdgeOS API key (EDGEOS_API_KEY, which the scripts read themselves) is a partner-app attendee key. EdgeOS limits partner apps to events:read, rsvp:write, venues:read. So:
- You can read the schedule, read venues, see who is going to an event, RSVP the person to an event, and cancel their RSVP.
- You cannot create, edit, cancel, or invite people to village events, and cannot create or change venues. Those calls fail with
403. When the person wants to host or change an event, tell them plainly that agents can't create village events and send them to the Edge City portal (the events page,$AV_PORTAL_URLwhen set) to do it themselves. Don't attempt those calls. - Your API key cannot reach the attendee directory or
/humans/meon EdgeOS itself. EdgeOS letseos_live_keys call only its event, event-participant, RSVP-eligibility, venue, track, event-settings and popup routes, plusregisterandcancel-registration; anything else answers403("API keys are restricted to approved event automation routes"). So both come only through their scripts, never a curl: the person's own profile through the profile script (§8), the directory through the directory script (§9). Each sends your key to the Agent Village control plane, whose app reads EdgeOS with the person's own Edge City sign-in. When the script exits 2, tell the person the directory isn't connected to their agent (for the profile script: their profile isn't connected) and point them to the Edge City portal; never retry those calls with the API key, and don't run that script again in this conversation. - Exit 4 (profile or directory script) means the person's Edge City sign-in in the Agent Village app has lapsed. Say: "I can't reach your Edge City details right now because your sign-in to the Agent Village app has lapsed. Sign in once at https://agents.edgecity.live/signin and I can look them up again." Never ask for a code, password or token. Don't call again in this conversation unless the person says they have signed in; then try once.
- Looking someone up is different. When the person asks who someone is, about a person, or how to reach them, run the directory script this turn (§9), even if it failed earlier in the conversation, and a directory failure (exit 1, 2 or 4) never ends the answer: skip the exit 2 and exit 4 messages above and follow §9's people-lookup fallback instead. On a real exit 4 in this turn, answer from the other sources first, then add §9's directory sign-in line once, after the answer.
- You cannot change the person's profile: there is no write call. Edits are made by the person themselves, in the Edge City portal app (§8).
- For any script answer, never show the error text, a status code or a key.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .env.example 156 B
- scripts/directory.ts 22 KB runs code
- scripts/edgeos.ts 24 KB runs code
- scripts/events.ts 17 KB runs code
- scripts/portal-link.ts 2.4 KB runs code
- scripts/profile.ts 8.4 KB runs code
- scripts/tests/directory.test.ts 32 KB runs code
- scripts/tests/edgeos.test.ts 25 KB runs code
- scripts/tests/events.test.ts 30 KB runs code
- scripts/tests/occurrence-parity.json 5.9 KB
- scripts/tests/profile.test.ts 17 KB runs code
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 Changed · +1 lines 37d9dab653ce
- 7d ago Changed · -4 lines · +9 tokens per session c121bb8d07f1
- 9d ago Changed · +2 lines c2ef13af8e80
- 12d ago Changed · +3 lines 17710a3dc483
- 13d ago Changed · +4 lines · +11 tokens per session d812fc77a3f1
- 14d ago Changed · +2 lines 71d3c8e46045
- 15d ago Changed · +11 lines c7e7a755b0b7
- 17d ago Changed 1968398c990e
- 22d ago Changed · +14 lines · +24 tokens per session 1b514fce9f98
- 23d ago First seen · 209 lines · 93 tokens per session scan A 79419b46c7d0
edgeos is a skill published in the GitHub repository Edge-City/agentvillage (21 stars, last pushed today), licensed MIT. It adds 137 tokens to every session and 8,635 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
workspace-manager
Registers, lists, removes, and assigns workspaces (project directories) for Anima work. Use when: binding project paths to Anima, managing aliases, or switching workspace roots.
meeting-notes
Turn a meeting transcript into decisions, action items with owners, and open questions.
conference-booking-links
Set up and troubleshoot Cal.com meeting links for a conference, with event-specific dates, in-person location, buffers, calendar conflict checks, individual or team hosts, and public booking-page verification. Use for conference booking availability or missing meeting slots.
conference-shared-calendar
Create or maintain a shared conference reference calendar from an official agenda, including sessions, side events, sharing permissions, timezone checks, and duplicate-safe updates. Use when a participant or team wants a shared event calendar or an importable agenda.
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
autoreview
Structured code review through the shared OpenClaw agent-skills installation.