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-runtimenpx skills add onescience-ai/OneSkills --skill onescience-runtimegit 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 | $0.00208 | $0.03939 |
| Opus 5 | $0.00104 | $0.01969 |
| Sonnet 5 | $0.00042 | $0.00788 |
| Haiku 4.5 | $0.00021 | $0.00394 |
Grade A, and why
onescience-runtime 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 — 196 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 Runtime
执行流程
每次任务固定按 discover -> preflight -> execute -> diagnose 顺序处理。execute 是硬门禁阶段:只有 preflight 明确产出 preflight_passed=true、execution_readiness=ready 且 evidence.preflight.status=passed 后,才能读取和执行任何 execute 分支。缺少这些证据时,必须回到 preflight,不得直接提交本地、SSH、SLURM 或 SCnet 任务。
1. discover
先读取项目根目录 onescience.json,并立即调用 skills/onescience-runsite/SKILL.md 对当前运行站点配置做校验、复用或补齐;不要直接信任已有 onescience.json。只有 onescience-runsite 完成已有配置检查、远程连接验证或缺失字段补齐并写回后,runtime 才重新读取 onescience.json,再优先消费:
runtime.execution_profile.run_siteruntime.execution_profile.execution_moderuntime.execution_profile.access_mode
execution_channel 由这三个字段派生;当前约定是 run_site=local 时 access_mode 允许为空,execution_mode 为空/none 视为非调度直接执行。若配置中已有 execution_channel,只作为对照证据,不作为唯一 routing 来源。
需要进入 discover 细节时,读取:
./references/discover.md
2. preflight
discover 得到通道后,runtime 不再自行执行环境检测。preflight 阶段改为完整委托 onescience-installer 执行环境就绪预检:
- 组装 preflight 上下文:
execution_channel、runtime.conda、入口脚本路径、业务依赖列表等 - 以
installer_reason=preflight_validation委托skills/onescience-installer/SKILL.md执行完整的环境就绪检查 - installer 返回
preflight_result:status=passed:设置preflight_passed=true、execution_readiness=ready,进入 executestatus=partial:记录警告和建议,若可继续执行则进入 executestatus=failed:installer 已进入修复流程;修复成功后重新读取onescience.json,从 preflight 重新开始status=blocked:记录阻断原因,停止并向 orchestrator 报告
职责说明:环境就绪检测(conda 校验、Python 解释器、onescience/torch 导入、CUDA 扩展、入口脚本语法、环境依赖一致性、GPU 可访问性、GPU 显存预算、共享库检查等)全部由 installer 的 preflight-validation.md 统一执行。runtime 只消费 installer 返回的 readiness 结果,不自行做环境探测。
What ships with it
16 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/templates/local_direct.sh 1.1 KB runs code
- assets/templates/slurm_cpu.sh 936 B runs code
- assets/templates/slurm_dcu.sh 1.4 KB runs code
- assets/templates/slurm_gpu_multinode_torchrun.sh 1.3 KB runs code
- assets/templates/slurm_gpu.sh 1.2 KB runs code
- assets/tpl.slurm 1.4 KB
- references/contract.md 12 KB
- references/diagnose.md 4.2 KB
- references/discover.md 3.8 KB
- references/execute-local-direct.md 3.6 KB
- references/execute-local-slurm.md 4.4 KB
- references/execute-scnet-skill.md 7.4 KB
- references/execute-ssh-direct.md 4.9 KB
- references/execute-ssh-slurm.md 5.4 KB
- references/preflight.md 3.5 KB
- references/slurm-resource-retry.md 4.7 KB
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 · 196 lines · 208 tokens per session scan A cf83e09533b2
onescience-runtime is a skill published in the GitHub repository onescience-ai/OneSkills (18 stars, last pushed 19d ago), licensed MIT. It adds 208 tokens to every session and 3,939 once invoked, about $0.0010 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
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
evo-memory
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory MI (feasible/unsuccessful directions) and Experimentation Memory ME (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after…
map-wayfind
Decision-frontier wayfinding: build and work a durable map of open design decisions BEFORE planning, for large or foggy efforts where /map-plan would force premature decomposition. Use when a task is too big or too vague to decompose — many unknowns, tangled decisions, or "I'm not even sure what to build yet" — and…
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
alphafold-database
Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.