onescience-runtime

A controlled workflow for running and diagnosing OneScience jobs. It checks project settings and execution readiness before allowing work to run locally, over SSH, on a SLURM cluster, or through SCnet.

In plain words
What is it for?
Use it to validate a project’s onescience.json configuration, prepare the runtime environment, submit an approved job through the configured channel, and investigate the result.
Why use it?
It prevents jobs from starting with missing or unverified environment, connection, queue, or resource settings. Each run follows discovery, preflight checks, execution, and diagnosis.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/onescience-ai/oneskills/onescience-runtime
Any agent
npx skills add onescience-ai/OneSkills --skill onescience-runtime
Clone the repo
git clone --depth 1 https://github.com/onescience-ai/OneSkills

Made for: Claude Code, Codex.

Per session 208 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,939 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash cf83e09533b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 5 executable files (assets/templates/local_direct.sh, assets/templates/slurm_cpu.sh, assets/templates/slurm_dcu.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/onescience-runtime/SKILL.md · 196 lines

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:

  1. 上下文 handoff(默认):从调用方传入的 step_handoff 获取任务信息。
  2. 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=trueexecution_readiness=readyevidence.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_site
  • runtime.execution_profile.execution_mode
  • runtime.execution_profile.access_mode

execution_channel 由这三个字段派生;当前约定是 run_site=localaccess_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:

  1. 组装 preflight 上下文:execution_channelruntime.conda、入口脚本路径、业务依赖列表等
  2. installer_reason=preflight_validation 委托 skills/onescience-installer/SKILL.md 执行完整的环境就绪检查
  3. installer 返回 preflight_result
    • status=passed:设置 preflight_passed=trueexecution_readiness=ready,进入 execute
    • status=partial:记录警告和建议,若可继续执行则进入 execute
    • status=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。

Read the full file on GitHub · 196 lines

Changes

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.

  1. 2d ago First seen · 196 lines · 208 tokens per session scan A cf83e09533b2

Subscribe to this mod's changes

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.

Related

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…

leo-lilinxiao/codex-autoresearch · 80 tokens

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…

EvoScientist/EvoSkills · 186 tokens

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…

azalio/map-framework · 182 tokens

clipboard

Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".

CodeAlive-AI/ai-driven-development · 36 tokens

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…

neo4j-contrib/neo4j-skills · 152 tokens

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.

agent-skills-hub/agent-skills-hub · 54 tokens