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/onescience-ai/oneskills/onescience-clinpx skills add onescience-ai/OneSkills --skill onescience-cligit clone --depth 1 https://github.com/onescience-ai/OneSkillsWhat 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 | $0.00097 | $0.03814 |
| Opus 5 | $0.00048 | $0.01907 |
| Sonnet 5 | $0.00019 | $0.00763 |
| Haiku 4.5 | $0.00010 | $0.00381 |
Grade A, and why
onescience-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 2d 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
输入获取方式
本技能支持两种输入方式：
- 上下文 handoff（默认）：从调用方传入的
step_handoff获取任务信息。 - 文件 handoff（autonomous_mode）：从
.onescience/handoff/step_{step_id}.yaml读取任务信息。执行后，将结果写入.onescience/handoff/step_{step_id}_result.yaml。
启动时优先检查 .onescience/handoff/ 目录是否存在对应的交接文件；若存在则使用文件模式，否则使用上下文模式。
文件交接格式参见 skills/onescience-orchestrator/references/file_handoff_contract.md。
OneScience CLI 技能
本技能根目录： 与当前 SKILL.md 同目录。资产路径均按本技能根目录解析，不按当前工作目录猜测。
需要环境检测与远程连接细则时，读取 ./references/cli_rules.md。
需要可渲染命令模板时，读取 ./references/cli_flow.md。
1. 职责与边界
本技能是在远端环境执行任意 onescience 命令的统一入口。onescience 命令需预先安装，本技能不检查或安装 onescience 工具。本技能不限制子命令范围，任何 onescience 支持的子命令均可透传执行。
负责：
- 执行
discover -> precheck（先检查计算节点 → 再检查环境）-> execute运行闭环 - 根据命令级别（lightweight/normal/compute）自动选择执行通道
- 轻量命令（help/list/info/config）走快速通道，跳过环境探测与检查
- 消费
execution_mode、access_mode、execution_channel、hardware_profile - 连接远端环境（参照
onescience-installer的主机发现与连接方式） - 环境检查：确认当前 shell 在计算节点上、环境已加载
- 调用
onescience命令执行用户请求的子命令 - 返回执行结果与状态
不负责：
- 安装或修复 OneScience 完整环境（由
onescience-installer负责） - 安装或修复
onescience工具 - 计算节点申请与 SLURM 作业提交（由
onescience-runtime负责） - 修改远端代码、配置或依赖
- 安装系统级组件或驱动
- 深度诊断训练/测试失败的业务原因
- 决定当前命令步骤之外的后续业务 executor 或全局工作流下一阶段
2. 固定阶段
| 阶段 | 触发条件 | 目标 | 关键输出 |
|---|---|---|---|
discover |
每次执行 | 命令级别判定 + 连接远端环境，收集运行目标与环境事实 | execution_mode、hardware_profile、remote_access_info、command_level |
precheck |
非 lightweight 级别 | 检查环境是否满足运行条件（先计算节点 → 再环境） | env_ready、on_compute_node、precheck_outcome |
execute |
precheck 通过或 lightweight 快速通道 | 通过 onescience 命令执行用户请求的子命令 |
onescience_command、execution_state、output |
三阶段按顺序推进，每阶段向用户实时汇报当前步骤。lightweight 级别跳过 precheck 直接进入 execute 快速通道。
precheck 发现不在计算节点时，交由 onescience-runtime 通过 sbatch 提交作业处理。precheck 发现环境未加载时，提示调用 onescience-installer。
CLI 只允许在当前命令步骤内进行这些显式委托：onescience-runtime 用于计算节点申请 / 提交 / 运行治理，onescience-installer 用于环境初始化。除这两类窄委托外，CLI 不得自行决定其他 downstream 业务技能；若后续问题超出 CLI 当前命令执行边界，必须返回 onescience-orchestrator 决策。
What ships with it
3 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.
- 2d ago First seen · 337 lines · 97 tokens per session scan A 93516f6e1572
onescience-cli is a skill published in the GitHub repository onescience-ai/OneSkills (18 stars, last pushed 19d ago), licensed MIT. It adds 97 tokens to every session and 3,814 once invoked, about $0.0005 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
nsfc-length-aligner
基于国自然标书篇幅预算标准；检查目标标书篇幅并总结差距；给出针对性优化建议；在尽量不改变原意的前提下扩写/压缩到达标。.
nsfc-research-foundation-writer
当用户明确要求"写/改研究基础""研究基础+工作条件+风险应对编排"时使用。为 NSFC 正文"（三）研究基础"写作/重构，并同步编排"工作条件"和"研究风险应对"，用证据链证明项目可行、资源条件对位研究内容、风险预案可执行。.
nsfc-code
根据 NSFC 标书正文内容，结合申请代码推荐库，为你给出 5 组申请代码1/2（主/次）推荐与理由；输出到 NSFC-CODE-vYYYYMMDDHHmm.md（只读，不修改标书）.
optim-agent
Use when the user wants to optimize configurable system parameters against a measurable scalar objective, especially for model training, inference, quantitative strategies, reinforcement learning, scientific workflows, or other expensive black-box evaluations where reading the project can improve trial selection.
paper-navigator
Find and read academic papers (S2 + arXiv). Disambiguate ambiguous queries, search by keyword + citation graph + recommendations + snippets, judge relevance against an authored rubric, and read with L1/L2/L3 strategy. Trigger phrases: find papers, search papers, related work, citation analysis, recent advances, read…
alphafold2
Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022, github.com/sokrypton/ColabFold; AlphaFold2 Jumper et al. 2021). Reach for this skill to fold a sequence or complex with the AF2/AF2-Multimer evoformer, to validate designed sequences by self-consistency…