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 instructions/poco-ai/agentero/agents-mdgit 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 | $0.02040 | $0.02040 |
| Opus 5 | $0.01020 | $0.01020 |
| Sonnet 5 | $0.00408 | $0.00408 |
| Haiku 4.5 | $0.00204 | $0.00204 |
Grade A, and why
Agentero AGENTS.md 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
项目概览
Agentero 是一个基于 Tauri 2 + React 19 的本地优先科研工作台。Vault 中笔记与源文件以 Markdown/文件为准,论文结构化 metadata 以 .agentero/catalog.sqlite 为准。离开应用后数据仍可被外部工具读取。
核心能力:
- 论文库:Catalog SQLite 管理论文集合,支持表头排序/选列/标签筛选、BibTeX 导出
- 魔棒入库:通过 URL/arXiv ID/DOI 一键导入论文,自动下载 PDF、解压 LaTeX 源码
- PDF 阅读与标注:分屏阅读(左 PDF/右笔记),划词高亮/批注/翻译/提问,大纲与页码导航
- Agent 工作流:BYOA 接入本机 ACP Agent,支持论文总结/问答/精读,选区上下文与 @ 提及
- Markdown 编辑:Plate 编辑器,双链
[[...]]、Obsidian Callout、嵌套标题引用、内嵌图片管理 - Zotero Connector:兼容官方浏览器扩展,一键保存文献到当前 Vault
架构总览:docs/architecture.md
论文单元
papers/<id>/ 是最小论文单元(语义对象,不是普通文件夹)。内部约定:
papers/<id>/
├── NOTES.md # 人/Agent 笔记
├── <id>.pdf # 主 PDF(可选)
├── PAPER.md # 无 TeX 时的派生正文
├── source/ # TeX / e-print(不要往这里塞附件)
├── marks/ # 阅读标注
├── assets/ # NOTES 内嵌图
└── attachments/ # 支撑材料:补充 PDF、幻灯片、代码仓库
- 支撑材料只放
{paper}/attachments/,不要堆在论文根目录,也不要放进source/。 - 不要预建空的
attachments/;有文件再创建。 - 文件树默认把论文当叶子。
attachments/非空时论文行才出 chevron,子项直接挂在论文下(不显示attachments桶本身,也不展开source//marks/等内部文件)。 attachments/不是论文身份 marker。
布局细则:docs/backend/data-model.md;树交互:docs/frontend/vault-tree.md。Vault 内 Agent 读的是盘上 AGENTS.md(创建时由 Host 模板写入)。
技术速览
| 层 | 技术栈 | 关键能力 | 入口 |
|---|---|---|---|
| 前端 | React 19、TypeScript、Tailwind CSS 4、shadcn/ui、AI Elements | zustand 按域状态管理、Plate Markdown 编辑器、EmbedPDF 渲染、Dockview 多面板工作区 | docs/frontend/ |
| Host | Rust、Tauri 2、feature-first 布局 | 文件系统与 Vault 树、Catalog SQLite、Wiki 双链索引、ACP Client、本地文件监听、可选 loopback MCP | docs/backend/ |
| CLI | Rust、agentero bin |
headless Vault/Catalog 操作、论文标签管理、BibTeX 导入导出 | docs/backend/cli.md |
开发规则
- 优先做小而聚焦的改动,避免无关重构。
- 保持 local-first:不要引入私有存储作为事实来源。
- 高内聚、低耦合。
- 尽可能能复用能力,避免重复造轮子。
- 未经明确确认,不要覆盖用户手写的 Vault 文件。
- 在 UI 修改的过程中尽量少加入无关的、非必须的i18n 文案,如果能用icon表达,就不要加额外的描述
- 修改完成后,把当次相关的改动按照 commit 部分的要求提交。=
- 编辑或生成 Markdown 时保留 Obsidian 兼容的双链文本(
[[...]])。 - UI 保持简约:图标按钮必须有可访问名称和 Tooltip;避免常驻解释文案。操作失败用
notifyErrorToast,不在侧栏 header 挂常驻错误条。 - 国际化(i18n):所有面向用户文案必须经
t()走react-i18next。en 源语言 → 同步zh-CN(src/i18n/locales/)。详见 docs/frontend/shell.md。 - 修改后需同步更新相关文档,并检查 Roadmap 和 Todo。
- 如果修改了 Template 下的 Skill,需要对应更新版本号。
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 · 117 lines · 2,040 tokens per session scan A 6658e9eff599
Agentero AGENTS.md is an instructions file published in the GitHub repository poco-ai/Agentero (336 stars, last pushed 3d ago), licensed MIT. It adds 2,040 tokens to every session, about $0.0102 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 instructions, from other repositories
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
InvestSkill GEMINI.md
Instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
sortie copilot-instructions.md
Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).
crust AGENTS.md
Instructions for chenxin-yan/crust, covering tests, documentation, changesets, agent skills and issue tracker.
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.