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-document-evidencegit 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-document-evidence)<a href="https://agentmods.dev/skills/vortx-ai/emem/emem-document-evidence"><img src="https://agentmods.dev/badge/skills/vortx-ai/emem/emem-document-evidence/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-document-evidence"><img src="https://agentmods.dev/badge/skills/vortx-ai/emem/emem-document-evidence.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 | $0.00133 | $0.01828 |
| Opus 5.5 | $0.00053 | $0.00731 |
| Sonnet 5.5 | $0.00027 | $0.00366 |
| Haiku 4.5 | $0.00013 | $0.00183 |
Grade A, and why
emem-document-evidence 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 28d 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/ocr \ How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
emem-document-evidence
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.
Three calls, each signed, each chained to the one before by a hash:
| Call | Signs | Provenance |
|---|---|---|
POST /v1/ocr (MCP emem_ocr) |
which image (blake3), engine, language and text produced this reading | model_output: a reading, not a fact |
POST /v1/lab_report_parse |
the fields a deterministic parser read from that text | deterministic_index |
POST /v1/land_record_parse |
the same, for land records | deterministic_index |
Nothing is persisted. The receipts are self-contained: the verifier below needs only the response and, if you have it, the document.
When to invoke
- "Read this residue certificate and tell me whether anything exceeds the MRL."
- "Pull the owner, survey number and area out of this 7/12 extract."
- An EUDR or food-safety file needs the lab or land document bound to
the same evidence trail as the satellite facts
(
emem-eudr-due-diligence).
Step 1: OCR the image
base64 -w0 report.png | jq -Rs '{image_b64: ., lang: "eng"}' > ocr_req.json
curl -sf -X POST https://emem.dev/v1/ocr \
-H 'content-type: application/json' -d @ocr_req.json > ocr.json
jq '{engine, lang, image_blake3_b32, text_blake3_b32}' ocr.json
jq -r .text ocr.json
Or pass "url" instead of image_b64 (png, jpeg, tiff, webp, gif, bmp;
8 MiB). lang takes Tesseract codes, joined with + (eng+hin+mar).
A responder with no OCR engine answers 501 ocr_unavailable.
Read the text before you trust anything parsed from it. The OCR receipt proves which image and engine produced the text, not that the reading is right.
Step 2: parse
Send the OCR response itself as ocr: the parser refuses it with
422 text_hash_mismatch unless its text hashes to its
text_blake3_b32, so the parse is bound to the signed reading. Or send
your own text, or a url / image_b64 to OCR and parse in one call.
What ships with it
2 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.
- 28d ago Changed · +7 lines 9b7e13b0c3ae
- 29d ago First seen · 126 lines · 133 tokens per session scan A c862e5621da5
emem-document-evidence is a skill published in the GitHub repository Vortx-AI/emem (76 stars, last pushed today), licensed Apache-2.0. It adds 133 tokens to every session and 1,828 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
pydicom
Reads, inspects, writes, transforms, and preflights local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
pptx-posters
Creates and audits editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Used when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.
nature-paper-trans
A workflow for translating selected pages or a complete English research-paper PDF into a simplified-Chinese, image-based PDF. bioRxiv is not mentioned in the provided details; the workflow applies to research-paper PDFs generally.
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
extracting-lab-tables
Detects and extracts tabular laboratory panels from PDFs, scans, and images into structured rows ready for OpenMed and FHIR. Use when the user has a CBC, CMP, lipid panel, or other lab report as a scanned image / PDF / spreadsheet and needs the test name, value, unit, reference range, and abnormal flag as clean rows.…
figures
Makes publication-quality plots from data with matplotlib, learning curves, scaling laws, benchmark and ablation comparisons, Pareto trade-offs, heatmaps and confusion matrices, sized for the page, vector, with uncertainty shown. Use whenever results are plotted, charted or visualized for a paper, report or answer, or…