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 Vortx-AI/emem --skill emem-field-signalsgit clone --depth 1 https://github.com/Vortx-AI/ememWrote 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/vortx-ai/emem/emem-field-signals)<a href="https://agentmods.dev/skills/vortx-ai/emem/emem-field-signals"><img src="https://agentmods.dev/badge/skills/vortx-ai/emem/emem-field-signals/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/vortx-ai/emem/emem-field-signals"><img src="https://agentmods.dev/badge/skills/vortx-ai/emem/emem-field-signals.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 | $0.00126 | $0.02099 |
| Opus 5.5 | $0.00050 | $0.00840 |
| Sonnet 5.5 | $0.00025 | $0.00420 |
| Haiku 4.5 | $0.00013 | $0.00210 |
Grade A, and why
emem-field-signals 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 4d 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.
curl -sf -X POST https://emem.dev/v1/field_boundaries \ How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
emem-field-signals
Network use. The commands in this skill send and receive JSON (and, where a step says so, an image or a raster file) to
https://emem.devonly, the service the plugin's MCP server connects to. Nothing they download is executed. The files underscripts/read local files and make no network calls.
Field-scale questions, each one call, each answer carrying the fact cids it was computed from and a signed receipt.
| Call | Answers |
|---|---|
POST /v1/field_boundaries (MCP emem_field_boundaries) |
the field polygons inside a bbox or place, from Fields of The World (CC-BY-4.0) |
POST /v1/field_burn_scar |
was residue burned between two dates: burn, signal_only, no_burn or inconclusive |
POST /v1/field_actual_et |
actual evapotranspiration over a window, in mm and m³/ha |
GET /v1/scene.png?bbox=w,s,e,n |
a true-colour Sentinel-2 crop of the plot at native 10 m, up to 1024 px a side |
POST /v1/field_series (MCP emem_field_series) |
an index over the field per scene: ndvi, ndwi, ndmi (alias lswi), evi, or Sentinel-1 vv, vh, vh_vv |
field_series takes geometry (or bbox), index, start_date and
end_date. Radar reads one relative orbit; pass orbit to choose it.
Radar rows have no clear_fraction: mean is the dB of the mean
linear power, with se_db, pixel_enl, below_nesz_share and
bright_rejected. Pass fields: [{id, geometry}] for up to 500 fields
in one window of at most 512 px a side. inner_buffer_m drops pixels
near the edge, and min_support_px (4 to 30) sets the fewest pixels a
scene needs. polygon_cid identifies each outline. On optical indices
a scene that both time neighbours refute gets quality: "suspect" and
a scene_check, and the trend leaves it out. A fields answer adds a
suspect column and suspect_dates.
field_burn_scar and field_actual_et take the same body: start and
end (YYYY-MM-DD, inclusive, at most 400 days), and the field as
geometry_geojson (a GeoJSON Polygon or MultiPolygon, or
{"bbox":[w,s,e,n]}) or as cells (cell64s). budget_ms (default
25000, max 300000) is a warm-up budget: after it the call answers from
what is stored, and the warm-up continues, so a retry reads more.
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.
- 4d ago Changed · -1 lines baa46db96093
- 7d ago Changed · +1 lines a1868dd4ce6a
- 11d ago Changed · +13 lines 40e14c46b67b
- 28d ago Changed · +2 lines e05c16ad1211
- 29d ago First seen · 114 lines · 126 tokens per session scan A bf1fced45253
emem-field-signals is a skill published in the GitHub repository Vortx-AI/emem (76 stars, last pushed today), licensed Apache-2.0. It adds 126 tokens to every session and 2,099 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 2026-09-29.
Other skills, from other repositories
iso-24495-3
Sector-specific Plain Language standard for science and technical writing (ISO 24495-3:2026). Applied during software documentation, architecture specs, and technical analysis.
autoresearch
Run a rigorous autonomous experiment loop for any optimization target using explicit hypotheses, repeated trials, structured experiment logs, and local HTML reports. Use when asked to "run autoresearch", "optimize X in a loop", "start experiments", or "improve this with benchmark-driven iteration".
warrant-review
Review a pull request of s0fractal/warrant that the review loop says is due (its head version is at the pull request's head, CI is green there, and no verdict stands), then file findings against that head version or accept it, through the warrant MCP server, and push the records onto the pull request; or give a…
ml-experiment-review
Use this skill when reviewing an ML experiment, benchmark, ablation, or training run.
r-btw-cli
Use the btw CLI to access R documentation, manage R package development, query CRAN, inspect the R environment, and discover or fetch skills from the command line. Use when you need to: (1) read R help pages or vignettes, (2) run R CMD check, tests, or devtools::document(), (3) search CRAN for packages, (4) check…
nen-math-card
Frame a mathematical challenge as a bounded proof, model, or measurement inquiry and decide whether it can construct, repair, choose, or clarify anything. Use when a user asks whether a math problem is useful, wants to turn a competition or puzzle into reusable understanding, needs to separate formal proof from world…