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 geo-esmeraldagit 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/geo-esmeralda)<a href="https://agentmods.dev/skills/edge-city/agentvillage/geo-esmeralda"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/geo-esmeralda/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/geo-esmeralda"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/geo-esmeralda.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 10 findings, up to medium
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 →
- medium MCP Rug Pull · line 33 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 55 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 68 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 74 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 75 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 76 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 77 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 83 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 84 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 89 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00043 | $0.01386 |
| Opus 5 | $0.00022 | $0.00693 |
| Sonnet 5 | $0.00009 | $0.00277 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
geo-esmeralda 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 12d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Geo Esmeralda
Use this skill when an attendee wants to add community knowledge to Geo or work with the Geo knowledge graph's content, relations, ontology, or raw Telegram history. It is especially for creating notes, transcripts, essays, project pitches, comments, and photos; linking those contributions to events, venues, tracks, or other community context; reading back knowledge graph-backed claims, content, source material, wiki-style knowledge, idea links, and ontology details; and summarizing or answering questions about what happened in the main Edge Esmeralda 2026 Telegram group (the village-wide chat) during a specific time window.
Other sibling skills cover live EdgeOS schedule/directory operations and Index Network participant matching. Use this skill for the Geo knowledge graph and for all attendee-authored writes.
Always run the Geo CLI with npx -y @geoprotocol/geo-edge-esmeralda-cli as the
execution surface. Do not call the HTTP API directly unless the user is
debugging the service itself.
1. Authentication
You need one token, read by the CLI from environment/config:
$EDGEOS_BEARER_TOKEN— human session JWT. Required for: Geo auth, graph reads, content writes.
2. Safety Rules
- Never place bearer tokens in prompts, query text, native query parameters, answers, examples, transcripts, or shared notes.
- When presenting Telegram messages or history to the user, synthesize a short bulleted summary in your own words; never dump raw messages or quote personal details beyond what the answer needs.
- Prefer fixed commands before native graph queries.
- Fetch live ontology before writing a native query unless the current session already fetched it.
- Treat denied native queries as a signal to narrow the query or switch to a fixed command.
- Only write through
npx -y @geoprotocol/geo-edge-esmeralda-cli create. Do not attempt imports, schema changes, admin calls, direct Neo4j access, or generic mutation endpoints. - Before creating content, use the user's own words where possible and scope it
to
--event-id,--venue-id, or--track-idwhen the user names one. - For photos, prefer
--file ./photo.jpgover hosted image URLs when the user has a local file. Do not paste binary data, upload URLs, storage keys, or local file paths into prompts or shared output. - Use a stable
--client-request-idfor creates so retries do not duplicate the attendee's content.
What ships with it
3 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.
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.
- 12d ago First seen · 105 lines · 43 tokens per session scan A a540da64d786
geo-esmeralda is a skill published in the GitHub repository Edge-City/agentvillage (17 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,386 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
geo-schema
Schema.org structured data audit and generation optimized for AI discoverability — detect, validate, and generate JSON-LD markup.
graph-mutation-plan
Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…
cold-outbound-sequencer
Use when the user asks to "build a B2B cold-outbound sequence", "design reply-triage branching", "plan a domain warmup / sending throttle", or "make my outbound CAN-SPAM / opt-in compliant"; produces a multi-step outbound sequence with reply-triage branches (positive / objection / referral / not-now / opt-out), a…
contract-helper
Use when the user asks to "draft an influencer contract", "review these agreement terms", or "build a partnership template"; produces a full influencer agreement framework (scope, compensation, usage rights, exclusivity, FTC disclosure), a clause-by-clause review with red flags, and a negotiation cheat sheet. Not for…
audience-mapper
Use when the user asks to "analyze my target audience", "build an audience profile for influencer targeting", "research a niche community", or "deep-dive a subculture before partnering with creators"; in audience mode produces demographic/psychographic profiles, a platform-priority matrix, named personas, and an…