Agentero is a local research workspace that connects papers, structured reading material, Markdown notes, and AI agents in one place. Researchers use it to read and annotate PDFs, extract formulas and figures, organize literature, and collaborate with agents on research tasks while keeping context locally. Its catalogue skills and instruction support agent-assisted research workflows in Agentero.
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 poco-ai/Agentero --skill vault-normalizergit clone --depth 1 https://github.com/poco-ai/AgenteroWrote 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/poco-ai/agentero/vault-normalizer)<a href="https://agentmods.dev/skills/poco-ai/agentero/vault-normalizer"><img src="https://agentmods.dev/badge/skills/poco-ai/agentero/vault-normalizer/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/poco-ai/agentero/vault-normalizer"><img src="https://agentmods.dev/badge/skills/poco-ai/agentero/vault-normalizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 22 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00057 | $0.02187 |
| Opus 5.5 | $0.00023 | $0.00875 |
| Sonnet 5.5 | $0.00011 | $0.00437 |
| Haiku 4.5 | $0.00006 | $0.00219 |
Grade A, and why
vault-normalizer 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 1mo 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault Normalizer
Goal
Convert an existing research directory into an Agentero-compatible Vault without losing user-written notes or original files.
Safety rules
- Inspect first; do not move, rename, delete, or overwrite files until the user approves a concrete migration plan.
- Preserve user-written Markdown, PDFs, TeX/source archives, annotations, Obsidian
[[wikilinks]], and any existingAGENTS.mdcontent. - If a directory already has
AGENTS.md, read it as local instructions and do not replace it; only propose an append/merge draft when the user asks. - Prefer copying or staged moves when the source directory is not already a Vault.
- Never treat
.agentero/catalog.sqliteas disposable cache; it is the authoritative paper collection and metadata store. - Do not make root
PAPERS.md,library.bib, or per-papermetadata.jsonthe source of truth. They are optional exports or projections. - Treat link repair as a separate, reviewable change. Do not invent missing notes, select an ambiguous candidate, or rewrite a user-authored link without approval.
Target layout
agentero-vault/
├── AGENTS.md
├── papers/
│ ├── <paper-id-or-citekey>/
│ │ ├── NOTES.md
│ │ ├── <id>.pdf
│ │ ├── PAPER.md # optional derived readable body
│ │ ├── marks/ # optional JSON highlights / asks / translations
│ │ ├── source/ # optional original TeX / e-print
│ │ ├── assets/ # optional note images or derived figures
│ │ └── attachments/ # optional extras: supplement PDFs, slides, code repos
│ └── <topic>/.../<paper-id-or-citekey>/
├── notes/
├── plans/
├── assets/ # optional non-paper media
├── .agents/
│ └── skills/
└── .agentero/
├── catalog.sqlite
├── config.json
└── .trash/
Directory rules
papers/contains all cataloged papers. Topic folders are allowed at any depth.- A paper folder is the smallest paper unit and is recognized by direct children such as
NOTES.md,PAPER.md,marks/,source/,assets/, or transitionalmetadata.json. - A topic folder under
papers/is not a paper unless it directly contains a paper marker. - Catalog identity is the Vault-relative paper folder path, e.g.
papers/nlp/transformers/1706.03762, not just the leaf directory name. - Local PDFs for a paper should live at the paper folder root, not inside
source/. Extra PDFs (supplement, slides, reviews) belong in{paper}/attachments/, not the paper root. - TeX, arXiv e-print contents, and original source archives belong in
{paper}/source/. Do not put user extras there. - Supporting materials (code repos, datasets, extra PDFs) belong in
{paper}/attachments/. Create that directory only when adding files; do not create emptyattachments/folders.attachments/is not a paper-identity marker. - User notes about one paper belong in
{paper}/NOTES.md. - For new organization, prefer
notes/for concept notes and cross-paper notes, andplans/for research plans, TODOs, and drafts; do not force-move existing folders that already work for the user. - Markdown-embedded images belong beside the Markdown file in
./assets/and should use relative links like. - PDF selection artifacts belong in
{paper}/marks/*.json; do not write them into the PDF binary or catalog body. .agentero/is application state and should not be shown or edited as ordinary notes.
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.
- 1mo ago Changed 7d4c10bd6e95
- 1mo ago First seen · 154 lines · 57 tokens per session scan A e3f15d275998
vault-normalizer is a skill published in the GitHub repository poco-ai/Agentero (1,032 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 2,187 once invoked, about $0.0002 per session on Opus 5.5. 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
officecli-academic-paper
Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column journal layout. Trigger on: 'research paper', 'journal paper'…
officecli
Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
pptx
A set of instructions for working with PowerPoint presentation files, including extracting content, editing slides, and creating decks.
surfsense-data
Work out numbers from spreadsheet and CSV sources (.xlsx, .csv, .tsv) by writing a pandas script that surfsenseanalyzedata runs: totals, averages, trends, rankings, comparisons, cleaning, and charts that can go into a document. Load it whenever the user asks for figures from a table, or a chart of one.
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…