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-orchestratornpx skills add onescience-ai/OneSkills --skill onescience-orchestratorgit 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-orchestrator)<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>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 | $0.00241 | $0.16350 |
| Opus 5 | $0.00120 | $0.08175 |
| Sonnet 5 | $0.00048 | $0.03270 |
| Haiku 4.5 | $0.00024 | $0.01635 |
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 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
- 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) - 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 - 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 - 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 - 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、frontmatterdescription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_name、source_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_skills、read_executor_skills、missing_executor_skills、executor_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。
- 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
- 循环规划执行:
- 基于最新的
Task State、artifacts、observations和Global 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
- 基于最新的
核心循环流程:
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.
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 · 811 lines · 241 tokens per session scan A f8df0dbde6d4
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.
Other skills, from other repositories
html-portal-generator
Convert a codebase into a self-contained HTML portal app for ingestion into AI application systems. Produces a single deployable HTML file with embedded CSS, JS, and data.
api-designer
Design RESTful APIs with best practices for consistency and usability.
coding-assistant
Provides coding assistance with best practices and code review.
debug-helper
Systematic debugging approach for identifying and fixing issues.
test-writer
Write thorough tests following TDD and BDD principles.
git-workflow
Git best practices for version control and collaboration.