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/zimoliao/scholaraio/setupnpx skills add ZimoLiao/scholaraio --skill setupgit clone --depth 1 https://github.com/ZimoLiao/scholaraioWrote 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/zimoliao/scholaraio/setup)<a href="https://agentmods.dev/skills/zimoliao/scholaraio/setup"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/setup.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.03229 |
| Opus 5 | $0.00017 | $0.01614 |
| Sonnet 5 | $0.00007 | $0.00646 |
| Haiku 4.5 | $0.00003 | $0.00323 |
Grade B, and why
setup scanned grade B with 2 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 6d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- `Graphviz dot`: `diagram --format svg` 的 DOT→SVG 渲染后端;Linux 可用 `sudo apt-get install graphviz` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl -I --max-time 10 http://localhost:8000` How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup / 环境配置
当用户需要配置、安装、初始化 ScholarAIO 时,按以下流程操作:
1. 诊断当前状态
scholaraio setup check --lang zh
阅读输出,了解哪些组件已就绪、哪些缺失。 如果用户明确是在让 agent 代为配置,而不是自己逐步操作:
- 默认先跑
scholaraio setup check --lang zh - 优先利用检查输出中的错误说明和建议链接,直接继续下一步配置
- 只有在会影响后续决策时,才回头问用户一个关键问题
- 对失败项要用“现状 + 原因 + 建议动作”的方式转述,不要只说“没装”或“不可达”
1.1 跨项目 agent 接入
如果用户想在其他软件项目目录里复用 ScholarAIO,或者问“agent 是否能自己看到 ScholarAIO skills 并决定什么时候用”,优先使用自动化命令:
scholaraio setup agent
scholaraio setup agent --apply
scholaraio setup agent check --lang zh
说明时要区分三层:
- CLI runtime:
SCHOLARAIO_CONFIG和scholaraio命令路径,让任何目录都能调用当前 ScholarAIO runtime。 - skill discovery:Codex / OpenClaw 的
~/.agents/skills/scholaraio,以及 Qwen 等 target-project wrapper。 - host-specific entry:Claude Code 插件命令、Cursor/Cline/Windsurf/Copilot 项目 wrapper 等。
默认先跑 scholaraio setup agent 预览;只有用户明确要求代为配置,或已经确认预览内容时,才跑 scholaraio setup agent --apply。执行后提醒用户重启 agent session,让新注册的 skills / wrapper 被重新发现。
如果使用 --target-project,要提醒用户这些 wrapper 是本机集成块,里面可能包含当前 ScholarAIO checkout / config 的绝对路径;提交到共享仓库前必须检查 managed block。
不要再默认手工追加 .bashrc 或手工创建 symlink,除非:
setup agent命令不可用;- 用户所在平台不允许自动创建 symlink / wrapper;
- 用户明确要求手工步骤。
Claude Code 是例外:setup agent 只会打印插件 slash-command;插件安装仍需用户在 Claude Code 内执行。
1.5 核心配置 vs 附加配置
默认把 setup 分成两层:
- 核心配置:依赖、
config.yaml、LLM key、PDF 解析器选择、MinerU token、contact_email - 附加配置:
Semantic Scholar API key、Zotero API key、非默认 LLM backend / base_url 等按需项目
执行顺序要求:
- 先完成核心配置
- 再明确告诉用户“还有一些附加配置,可提升特定能力,要不要继续配置”
- 只有用户表示需要相关能力时,才继续展开附加配置
对每个附加项,agent 必须按同一模板说明:
- 用途:它解决什么问题
- 何时需要:哪些用户才值得配
- 做法:写到哪里、命令或字段是什么
- 开销:免费 / 通常单独计费 / 取决于第三方政策
2. 根据缺失项引导用户
依赖缺失
- 告诉用户缺少哪些依赖,解释每组依赖的用途:
embed: 语义向量检索(Qwen3 嵌入模型)topics: BERTopic 主题建模import: Endnote / Zotero 导入Graphviz dot:diagram --format svg的 DOT→SVG 渲染后端;Linux 可用sudo apt-get install graphvizInkscape: Beamer\includesvg插入 SVG 时需要;Linux 可用sudo apt-get install inkscapefull: 全部功能
- 运行
pip install -e ".[full]"或按需安装
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.
- 6d ago First seen · 210 lines · 35 tokens per session scan B 034baa2d2350
setup is a skill published in the GitHub repository ZimoLiao/scholaraio (567 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 3,229 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
thoughtdag
Open the current Codex session in ThoughtDAG (desktop app direct; local bridge fallback — data never leaves this machine), or query local session history with why / find / recall.
research-workflow
This skill should be used when the user asks research questions, needs information lookup, wants comparisons, asks "what is", "how does", "explain", "compare", "best practices", "latest developments", or any query requiring web search, documentation lookup, or synthesis of multiple sources. Provides optimal routing…
gigaxity-deep-research
Deep research MCP server wrapping Qwen3-30B-A3B-Thinking via OpenRouter. Use when an agent needs cross-source synthesis with citations, exploratory expansion of an unfamiliar topic, chain-of-thought reasoning over evidence, or fast conversational lookups grounded in live web search. Exposes six MCP tools — two…
design-lab
Scope the physical and interface design of a laboratory before configuring it. Use when a user asks how to approach a lab buildout, how to break a cell into components, which mechanism or instrument to choose, how to tailor a reference design to their material system or hazards, whether a design is over-engineered, or…
start-here
Establish or resume an OpenSDL laboratory through a normal agent conversation. Use when a user says start here, set up or configure my lab, plan a new lab or cell, describe existing equipment, continue a lab build, or turn a laboratory idea into a simulator-first implementation plan.
develop-workflow
Design, change, validate, and test an OpenSDL workflow through a simulation manifest. Use when building or iterating on a laboratory workflow without live equipment.