emem-recall-polygon

emem-recall-polygon is a skill for Claude Code from Vortx-AI/emem. It costs 99 tokens per session (1,446 once invoked), scanned A, original, Apache-2.0.

A tool for retrieving Earth-observation facts across a user-defined map region. It accepts GeoJSON or a closed list of longitude-and-latitude points.

In plain words
What is it for?
Use it to recall values such as NDVI, precipitation, or elevation for every sampled cell inside a polygon, with a receipt for each cell.
Why use it?
It answers regional questions that a single map point cannot, such as conditions across a watershed or administrative area.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to recall values such as NDVI, precipitation, or elevation for every sampled cell inside a polygon, with a receipt for each cell.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vortx-ai/emem/emem-recall-polygon
Install

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.

Any agent
npx skills add Vortx-AI/emem --skill emem-recall-polygon
Clone the repo
git clone --depth 1 https://github.com/Vortx-AI/emem

Made for: Claude Code.

Wrote 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.

agentmods badge for emem-recall-polygon

README.md
[![agentmods](https://agentmods.dev/badge/skills/vortx-ai/emem/emem-recall-polygon/github.svg)](https://agentmods.dev/skills/vortx-ai/emem/emem-recall-polygon)
Your own site
<a href="https://agentmods.dev/skills/vortx-ai/emem/emem-recall-polygon"><img src="https://agentmods.dev/badge/skills/vortx-ai/emem/emem-recall-polygon/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.

agentmods 80×15 button for emem-recall-polygon

Your own site · 80×15
<a href="https://agentmods.dev/skills/vortx-ai/emem/emem-recall-polygon"><img src="https://agentmods.dev/badge/skills/vortx-ai/emem/emem-recall-polygon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,446 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 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 Data Exfiltration · line 35
    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 69
    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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00099 $0.01446
Opus 5 $0.00049 $0.00723
Sonnet 5 $0.00020 $0.00289
Haiku 4.5 $0.00010 $0.00145

Measured 11d ago against content hash d8b157e521a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

emem-recall-polygon 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 11d 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.

allowed-tools: Bash(curl:*) Bash(jq:*) Read
claude-skills/emem-recall-polygon/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

emem-recall-polygon

This skill calls /v1/recall_polygon to fetch facts inside an arbitrary polygon. The responder samples every cell64 whose centre falls inside the polygon (cap: 1024 cells per request, max_cells, default 64), recalls the requested band(s) at each, and returns a structured response with a per-cell receipt for verification.

When to invoke

The user defines a region rather than a point:

  • "What's the average NDVI inside this watershed: [coords]?"
  • "Show me precipitation across the area bounded by …"
  • "Recall elevation across this admin boundary."
  • The user pastes GeoJSON or a list of [lng, lat] pairs.

If the user just wants a single cell, use emem-locate-and-recall. If they want a similar-cells list rather than a polygon, use emem-find-similar.

How to invoke

The polygon is a closed ring: [[lng0, lat0], [lng1, lat1], …, [lng0, lat0]]. Coordinates are WGS-84 decimal degrees, longitude first (GeoJSON convention).

curl -sf -X POST https://emem.dev/v1/recall_polygon \
  -H 'content-type: application/json' \
  -d '{
    "polygon": [
      [77.55, 12.95],
      [77.65, 12.95],
      [77.65, 13.05],
      [77.55, 13.05],
      [77.55, 12.95]
    ],
    "bands": ["indices.ndvi", "weather.precipitation_mm"]
  }' | jq '{
    cells_returned: (.by_cell | length),
    facts_total:    (.by_cell | to_entries | map(.value.facts | length) | add),
    area_km2:       .area_km2
  }'

Picking the band

If the user asked about precipitation, use weather.precipitation_mm (current 24 h) or era5.precip (1940→ present hourly). If they asked about vegetation, use indices.ndvi (computed live from S2) or modis.ndvi_mean (16-day MODIS composite, larger pixels but global). If they asked about elevation, use copdem30m.elevation_mean (30 m, terrestrial only; gmrt.topobathy_mean for ocean depths). Full band list at https://emem.dev/v1/bands.

Computing aggregates

The response is per-cell facts; the agent does the rollup:

Read the full file on GitHub · 140 lines

Changes

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.

  1. 11d ago First seen · 140 lines · 99 tokens per session scan A d8b157e521a6

Subscribe to this mod's changes

emem-recall-polygon is a skill published in the GitHub repository Vortx-AI/emem (56 stars, last pushed today), licensed Apache-2.0. It adds 99 tokens to every session and 1,446 once invoked, about $0.0005 per session on Opus 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.