onescience-orchestrator

onescience-orchestrator is a skill for Claude Code, Codex from onescience-ai/OneSkills. It costs 241 tokens per session (16,350 once invoked), scanned A, original, MIT.

A task coordinator for OneScience that turns a user’s goal into a tracked plan and assigns parts of the work to suitable specialist tools.

In plain words
What is it for?
It helps organize complex science and coding workflows, such as finding expert guidance, splitting work into executable steps, and coordinating coding, paper reproduction, runtime, installation, and evaluation tasks.
Why use it?
It removes the need to choose, sequence, and combine specialist tools by hand. It also keeps the task state, resources, plans, and handoffs together.

Skill for Claude CodeCodex

Part of the oneskills plugin — 18 skills shipped together

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

Made for: Claude Code, Codex.

Or install oneskills, the plugin that ships this one along with the rest of its 18 skills.

Wrote 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.

agentmods badge for onescience-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/onescience-ai/oneskills/onescience-orchestrator.svg)](https://agentmods.dev/skills/onescience-ai/oneskills/onescience-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/onescience-ai/oneskills/onescience-orchestrator"><img src="https://agentmods.dev/badge/skills/onescience-ai/oneskills/onescience-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 241 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 16,350 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00241 $0.16350
Opus 5 $0.00120 $0.08175
Sonnet 5 $0.00048 $0.03270
Haiku 4.5 $0.00024 $0.01635

Measured 5d ago against content hash f8df0dbde6d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onescience-orchestrator scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- 测速类操作(`curl -r ... -o /dev/null`、`timeout ... curl` 等)只允许执行 `speed_measurement.max_attempts` 次不同测速策略的测试;同一策略的重复执行视为同一次尝试
skills/onescience-orchestrator/SKILL.md · 811 lines

How it starts

The opening of the file, as written. The whole thing — 811 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OneScience Orchestrator

你是 OneScience / OneSkills 的通用任务编排主控。你的职责是把用户目标组织成可追踪、可融合、可执行的任务闭环,循环执行直至任务完成。

核心职责

  1. 按职责选择并调用 type=resource 技能获取资源:先检查可用 type=resource 技能的 description 是否覆盖 orchestrator 当前职责所需的知识,再仅调用匹配的 resource 技能,输入用户请求和 Task State,获取 matched_resources 列表(摘要模式)
  2. 基于资源识别用户意图:分析已召回资源的 matched_resources 和用户请求,生成 intent_profile
  3. 执行专家召回:以 intent_profile.intent_aspects 为唯一召回驱动,逐个方面查找对应的 type=expert 专家技能,并记录本轮召回状态;每个匹配结果都必须进入 Task State,未命中的方面也必须保留空结果痕迹
  4. 收集专家规划结果:对所有命中的专家逐个传递上下文并接收 planner_proposal;只要某个意图方面命中专家,就必须执行该专家的规划回执收集,不能因为其他专家已返回而跳过
  5. 融合优化为 Global Plan:先收集完所有命中的专家 proposals,再合并生成全局计划
    • 在任何计划融合、direct_step 规划、下一步选择之前,必须先完整查询当前所有可用的 type=executor 技能。
    • 枚举所有 executor 后,必须逐个完整读取其权威 SKILL.md,再形成当前轮次的 executor 能力视图;技能名称、frontmatter description 和交接参考文档中的简写职责,只能用于初筛和索引,不能作为最终职责判定依据。
    • 查询结果必须形成当前轮次的 executor 能力视图台账;对每个 executor 至少记录:skill_namesource_of_truth、输入要求、输出产物、负责事项、明确不负责事项、下游交接对象、覆盖的专门原子动作、前置条件,以及对应证据段落。
    • 同时必须维护当前轮次的内部 executor inventory:all_executor_skillsread_executor_skillsmissing_executor_skillsexecutor_inventory_complete
    • 在继续规划前必须做集合校验:set(all_executor_skills) == set(read_executor_skills);若不相等,立刻计算 missing_executor_skills,设置 executor_inventory_complete=false,并停止后续 proposal 融合、Global Plan 生成和 Next Step Spec 选择。
    • 必须按可调用的执行技能能力边界做最终拆分:如果一个大步骤可以由宽泛 executor 一次性完成,但其中某些子动作已有更专门的 type=executor 技能可执行,则必须拆成多个 executor_step,而不是把完整子任务交给宽泛 executor。
    • 若任一 executor 未完成完整读取、能力台账字段缺失,或职责边界仍未核定,则先补齐查询结果与边界核定,再继续本轮规划;在信息补齐前不要融合 proposal、生成最终 Global Plan,也不要选择 Next Step Spec
  6. 循环规划执行:
    • 基于最新的 Task StateartifactsobservationsGlobal Plan 选择当前唯一一个 Next Step Spec
    • 每一轮只执行一个 Next Step Spec;完成 observation 并更新 Task State 后,可在同一 skill 调用内进入下一轮并继续调用后续 executor,直到完成或阻断。
    • 调用 type=executor 执行技能执行当前步骤
    • 执行结果返回后,先进入 observation,记录 artifacts 和 observation,并写回 Task State
    • 随后在同一 skill 内重新判断:继续规划下一步、进入修复、进入验证、进入阻断或完成任务后,继续下一轮
    • 重复直至任务完成或阻断

核心循环流程:

Read the full file on GitHub · 811 lines

Files

What ships with it

7 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.

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. 5d ago First seen · 811 lines · 241 tokens per session scan A f8df0dbde6d4

Subscribe to this mod's changes

onescience-orchestrator is a skill published in the GitHub repository onescience-ai/OneSkills (20 stars, last pushed 22d ago), licensed MIT. It adds 241 tokens to every session and 16,350 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.