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 agentmods add skills/poco-ai/agentero/agentero-clinpx skills add poco-ai/Agentero --skill agentero-cligit clone --depth 1 https://github.com/poco-ai/AgenteroWhat 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 | $0.00117 | $0.01915 |
| Opus 5 | $0.00059 | $0.00958 |
| Sonnet 5 | $0.00023 | $0.00383 |
| Haiku 4.5 | $0.00012 | $0.00192 |
Grade A, and why
agentero-cli 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 3d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentero CLI
Role
You use the agentero CLI as a stable machine interface to an Agentero vault.
The CLI is not a chat runtime: no BYOA, no ACP, no paper-reader. Reading and
writing lecture-style NOTES.md is your job (or use the separate
paper-reader skill / desktop Zap workflow).
Design reference (repo): docs/backend/cli.md.
Prerequisites
- Binary name:
agentero(POSIX). Desktop: 设置 → 关于 → 安装 CLI writes the~/.local/bin/agenterosymlink. If missing from PATH, say so and fall back to reading Vault files directly; do not invent catalog rows. - Prefer always passing
--json(disables interactive prompts). JSON is a compact single line;--prettypretty-prints for humans. - Destructive deletes: pass
-y/--yesunder--json/ non-TTY. - Vault resolution (first wins):
--vault <path>→ envAGENTERO_VAULT→ cwd walk-up (.agentero/catalog.sqlite) → CLI configdefault_vault.
Hard boundaries
| Do | Do not |
|---|---|
| Call CLI for vault/catalog/import/assets | Spawn coding agents via CLI |
| Read files at returned paths | Assume CLI wrote full lecture NOTES |
| Progressive disclosure L0→L4 | Dump entire PDF/TeX into the prompt by default |
| Skip overwrite of user NOTES on re-import | Force-overwrite without explicit user ask |
Progressive disclosure (same as Vault model)
- L0 —
AGENTS.md(if present) - L1 —
agentero paper list --json— returns onlyid/path/titleper row; add--fields year,tags,abstract,…as needed, or--fullfor whole records - L2 —
{paper}/NOTES.md - L2.5 — layout index + marks
agentero layout list <paper> --json(sidebar figures/tables/algorithms/formulas){paper}/marks/annotations.json(highlights / 批注) +{paper}/marks/<id>.json(asks / translates) — write these through the CLI, never by hand
- L3 —
{paper}/PAPER.md(if no TeX) - L4 —
{paper}/source/**(TeX preferred when present)
After paper get --json, use data.assets (marksDir = reader annotations),
data.suggestedReads / paper paths, then read_file those paths. Do not
paste whole sources unless needed.
What ships with it
1 file 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.
- 3d ago First seen · 165 lines · 117 tokens per session scan A 766ab850df9f
agentero-cli is a skill published in the GitHub repository poco-ai/Agentero (336 stars, last pushed 3d ago), licensed MIT. It adds 117 tokens to every session and 1,915 once invoked, about $0.0006 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
Process PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work with PDF files.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
当用户需要对PDF文件进行任何操作时，请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片，以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF，请使用此技能。.
nano-pdf
Edits PDF files using natural-language instructions via the nano-pdf CLI. Supports modifying text, changing titles, fixing typos, and updating content on specific pages. Use when the user wants to edit a PDF, modify PDF content, update PDF text, fix a typo in a PDF, change a PDF title, or rewrite part of a PDF page.
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…
pdf-toolkit
Structured .pdf operations: extract text/tables, merge pages from multiple PDFs, split a PDF by page ranges, fill PDF form fields, and generate fresh PDFs from JSON. Trigger when the user wants programmatic PDF work without natural-language rewriting — examples: pull tables from a report, combine three PDFs, extract…