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-runsitenpx skills add onescience-ai/OneSkills --skill onescience-runsitegit clone --depth 1 https://github.com/onescience-ai/OneSkillsWrote 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/onescience-ai/oneskills/onescience-runsite)<a href="https://agentmods.dev/skills/onescience-ai/oneskills/onescience-runsite"><img src="https://agentmods.dev/badge/skills/onescience-ai/oneskills/onescience-runsite.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 | $0.00093 | $0.03302 |
| Opus 5 | $0.00046 | $0.01651 |
| Sonnet 5 | $0.00019 | $0.00660 |
| Haiku 4.5 | $0.00009 | $0.00330 |
Grade C, and why
onescience-runsite scanned grade C with 1 finding 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 5d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
--ssh-data '{"host":"cluster","hostname":"192.168.1.100","port":22,"user":"alice","identity_file":"~/.ssh/id_rsa","remote_work_dir":"/home/alice/work"}' \ How it starts
The opening of the file, as written. The whole thing — 220 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 运行站点
onescience-runsite 是独立的配置工作流。它只负责把用户的运行位置、调度方式、接入方式、账号信息和资源提示整理成项目根目录的
onescience.json,然后把交接信息交回调用它的技能;若没有明确调用方,交回 onescience-orchestrator 让其规划下一步。
先读哪个
强制先读 references/runsite_interaction_flow.md,并按其中的分支顺序推进。不要一次性并行读取所有参考文件,也不要在没有命中分支前加载本地、远程、检查和契约等全部文档。
执行顺序必须是:
- 先检查
./onescience.json。 - 按
runsite_interaction_flow.md判断分支:存在且完整、存在但不完整、不存在。 - 只读取当前分支需要的一个工作流文件。
- 若当前分支还需要字段含义或交接格式,再读取
runsite_contract.md。
| 任务 | 读取 |
|---|---|
| 入口顺序、分支判断、中文补问顺序 | references/runsite_interaction_flow.md |
| 职责边界、字段含义、交接格式 | references/runsite_contract.md |
检查、复用或修改已有 onescience.json |
references/check_existing_config.md |
| 创建本地配置 | references/local_runsite.md |
| 创建远程配置,包含 SSH 或 SCnet | references/remote_runsite.md |
补问硬规则
预配置免交互(Autonomous Mode)
当上游 step_handoff.execution_flags.autonomous_mode 为 true 时:
- 若
onescience.json已存在且完整,直接验证并使用,不触发任何补问流程。 - 若
onescience.json缺失或不完整,按以下优先级自动处理:- 检测本地环境(GPU/CUDA、conda 等)是否可用 → 自动生成本地配置(
run_site=local),不向用户提问。 - 若本地不支持但存在
.onescience/default_remote.json预配置文件 → 读取并使用。 - 若必须使用远程环境但配置信息不完整 → 返回
status: blocked并输出缺失字段清单(不进入逐字段补问流程)。
- 检测本地环境(GPU/CUDA、conda 等)是否可用 → 自动生成本地配置(
- 禁止在 autonomous_mode 下向用户发起任何交互式提问。
标准补问规则(默认模式)
- 不允许只说“请提供 SSH 信息”“请提供 SCnet 信息”“请提供 cluster 信息”。
- 需要用户提供信息时,必须逐一列出字段名、含义、是否可留空或默认值。
- 可以逐字段一问一答,也可以给出一个字段清单让用户一次性填写;但字段清单必须完整。
- 远程配置必须分阶段补问:先让用户在 SSH 和 SCnet 中选择一种接入方式;用户选定后,立刻只补问该接入方式的连接信息并完成连接验证;连接信息完成后,才询问是否使用 Slurm。
- 远程执行必须补齐 SSH 信息;如果用户选择 SCnet,先补问 SCnet 连接字段并验证登录,再补问 SSH 连接字段并验证 SSH,然后才询问是否使用 Slurm。
- 如果用户选择 SCnet,只能先补问 SCnet 连接字段;不要同时补问 SSH 字段或 Slurm 集群资源字段。SCnet 验证完成后,再单独补问 SSH 字段。
- 如果用户选择 SSH,只能先补问 SSH 连接字段;不要同时补问 Slurm 集群资源字段。
- 只有用户明确选择使用 Slurm 后,才补问 Slurm 集群资源字段。
- 已有
onescience.json不完整时,必须先根据run_site、execution_mode、access_mode判断哪些配置块是必填,再只补问这些必填块中缺失的字段;补问时仍必须列出每个缺失字段。 - 远程连接验证失败后,要求用户重新提交信息时,也必须列出对应接入方式需要重新提供的字段。
- 只要
run_site=remote,都必须校验并补齐 SSH 字段:host/别名、hostname、port、user、identity_file、remote_work_dir。 - 只要
run_site=remote且access_mode=scnet,都必须额外校验并补齐 SCnet 字段:SCNET_ACCESS_KEY、SCNET_SECRET_KEY、SCNET_USER、region、remote_work_dir。 - 只要
execution_mode=slurm,都必须校验并补齐 Slurm 字段:partition、nodes、gpus_per_node、cpus_per_task、memory、time_limit、gpu_type、ntasks_per_node。 - 用户提供完整运行信息后,必须检测对应运行平台加速器类型:本地直接/本地 Slurm 检测本机;远程 SSH 直接/远程 SSH Slurm 通过已验证 SSH Host 别名检测远程。若未检测出,先询问用户确认
dcu还是gpu,再生成配置。
What ships with it
17 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.
- assets/cluster_profliles/slurm.json 207 B
- assets/env_vars/config.json 162 B
- assets/hardware_profiles/dcu_hardware_profiles.json 1.8 KB
- assets/hardware_profiles/gpu_hardware_profiles.json 4.0 KB
- assets/runsite_profiles/local.json 40 B
- assets/runsite_profiles/scnet_remote.json 142 B
- assets/runsite_profiles/ssh_remote.json 213 B
- assets/runsite.example.json 1.8 KB
- references/check_existing_config.md 3.9 KB
- references/local_runsite.md 3.5 KB
- references/optimization_plan.md 17 KB
- references/remote_runsite.md 9.8 KB
- references/runsite_contract.md 6.8 KB
- references/runsite_interaction_flow.md 9.1 KB
- scripts/runsite_config.py 43 KB runs code
- scripts/scnet_config.py 7.9 KB runs code
- scripts/ssh_config.py 10 KB runs code
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.
- 5d ago First seen · 220 lines · 93 tokens per session scan C 60a98ebe1a57
onescience-runsite is a skill published in the GitHub repository onescience-ai/OneSkills (20 stars, last pushed 22d ago), licensed MIT. It adds 93 tokens to every session and 3,302 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
results-analysis
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
nsfc-budget
当用户明确要求“写/生成 NSFC 预算说明书”“写预算说明”“生成 budget.tex / budget.pdf”“写国自然预算 justification”时使用。基于用户标书正文或补充材料,输出一份可提交的预算说明书 LaTeX 项目并渲染 budget.pdf。若用户未指定工作目录,必须暂停并先要求其指定。⚠️ 不适用:用户只是想了解预算原则;用户仅要预算表数字而不写说明书;或用户是 2026 青年 A/B/C 默认包干制且无需预算说明书的场景。.
paper-select-journal
当用户明确要求“推荐投稿期刊”“帮我的论文选 SCI 杂志”“这篇 manuscript 适合投哪些 journal”“期刊匹配/选刊/投稿建议”时必须使用。适用于用户提供全文、摘要、Markdown、LaTeX、PDF、Word 或混合材料的场景;本 skill 会基于 manuscript 与用户偏好,先用内置 2023IF.xlsx 做最小硬过滤生成候选池,再由宿主模型自主规划 Set1/Set2/Set3,并联网核验 scope / 质量 / 近 3 个月 PubMed 论文,最后输出 1 份按推荐度排序的 Markdown 选刊报告。⚠️…
paper-search
Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc). Use when the user asks to find papers, search for research, look up academic literature, download a paper PDF, or extract text from a paper.
bio-ortholog-inference
Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when…