agentmods.dev

onescience-primitives

onescience-primitives is a skill for Claude Code, Codex from onescience-ai/OneSkills. It costs 79 tokens per session (7,716 once invoked), scanned A, original, MIT.

A resource-search tool for finding reusable OneScience building blocks. It searches a catalogue for the most relevant scientific workflow components and returns their supporting details and usage contracts.

In plain words
What is it for?
Use it to find OneScience primitives related to a request, then resolve their implementation parts, contracts, locations, and companion resources. It does not create an implementation plan, edit code, or run scripts.
Why use it?
It reduces the need to search through resource files manually or choose components without checking their intended scope. It also enforces a controlled process for retrieving those resources.

Skill for Claude CodeCodex

Part of the oneskills plugin — 18 skills shipped together

18 20d ago A scan 79 tokens original MIT
View the source file onescience-ai/OneSkills
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-primitives
Any agent
npx skills add onescience-ai/OneSkills --skill onescience-primitives
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.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,716 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 $0.00079 $0.07716
Opus 5 $0.00039 $0.03858
Sonnet 5 $0.00016 $0.01543
Haiku 4.5 $0.00008 $0.00772

Measured 3d ago against content hash 372766492f20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onescience-primitives 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 3d ago.

The scan reads SKILL.md. This mod also ships 12 executable files (assets/bio/application/bio_cell_imaging_cytometry_app/script/bio_cell_imaging_tools/cytometry_table_qc.py, assets/bio/application/bio_cell_imaging_cytometry_app/script/bio_cell_imaging_tools/label_mask_measurements.py, assets/bio/application/bio_lab_quality_asm_app/script/bio_lab_quality_tools/convert_to_asm.py, …), 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-primitives/SKILL.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OneScience Primitives Resource

你负责从 skills/onescience-primitives/assets/ 中找到最相关的 OneScience 原语，通过范围判定、快速过滤和语义匹配进行召回。不生成实现方案、不改代码、不执行脚本。

强制协议

本技能的 assets/ 目录仅供本技能内部使用。调用方（orchestrator / coder / 其他技能）不得：

  • 直接 Glob / Read 本技能 assets/ 下的文件来获取原语信息
  • 绕过 resource_retrieval_request 直接消费原语的 metadata.json、spec.md、usage.md 等文件内容
  • 在未收到或构造 resource_retrieval_request 之前，禁止阅读或引用 assets/ 下的任何文件

调用方必须通过 resource_retrieval_request → resource_retrieval_result 的完整闭环获取资源。

协议范围豁免：当调用方已构造合法的 resource_retrieval_request（包含 user_request 和/或 filters），并按本技能「召回流程」中的步骤执行资源检索时，调用方可以使用以下工具操作——这属于本技能召回逻辑的执行，不是违规的直接消费。豁免范围分为两级：

优先路径 —— catalog_search + catalog_resolve：

  • 使用 catalog_search 工具（kind=primitive, domain=..., q=...）搜索原语
  • 使用 catalog_resolve 工具（part=body/contract/location）获取 companions 和契约
  • catalog_search 搜索的是 OneCode 内置 catalog（含 bundled seed 原语），不依赖本地文件系统

降级路径 —— 文件系统 Glob/Read（仅当 catalog_search 无结果且确认 skills/onescience-primitives/assets/ 目录在本地存在时使用）：

  • 枚举候选集（步骤 2）：Glob 列出资源目录
  • 快速过滤/语义匹配（步骤 3-4）：Read 各资源的 metadata.json
  • 内容组织（步骤 7）：Read 命中资源的 spec.md、usage.md、workflow_planning.md 及经白名单校验的执行资产
  • 命名直查（命名直查模式步骤 3-4）：Glob 搜索目录名、Read metadata.json

调用方仍然不得沿 matched_resources[].path 自由读取任意文件，不得在未构造请求的情况下随意浏览 assets/ 目录，不得消费未在 execution_assets 白名单中声明的脚本或文件。

当本技能被上游技能调用时，resource_retrieval_request 是输入控制消息，不是需要回显给用户的最终内容。本技能直接执行召回流程并返回 resource_retrieval_result。

原语资产目录

assets/
  <domain>/
    <category>/
      <resource_name>/
        metadata.json            ← 基础信息（name, type, domain, description, tags, version）
        spec.md                  ← 规格知识（架构、参数、依赖）
        usage.md                 ← 使用知识（启动示例、接口、限制）
        workflow_planning.md     ← 规划决策知识（时机、流程、约束）
        scripts/                 ← 可选受控执行资产；必须由 spec.md 的 # execution_assets 结构化白名单 白名单声明

当前 assets/ 顶层按 domain 组织，实际目录以仓库中的现状为准；当前可见的顶层 domain 包括：

  • bio
  • cfd
  • climate
  • matchem

每个 domain 下的 category 目录可能不同，按实际存在的目录检索，不要求所有 domain 都具有同一套子目录。当前常见 category 包括：

Read the full file on GitHub · 318 lines

Files

What ships with it

60 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. 3d ago First seen · 318 lines · 79 tokens per session scan A 372766492f20

Subscribe to this mod's changes

onescience-primitives is a skill published in the GitHub repository onescience-ai/OneSkills (18 stars, last pushed 20d ago), licensed MIT. It adds 79 tokens to every session and 7,716 once invoked, about $0.0004 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.

Scientificagent-skillsai4scienceclaude-codecodex-climcp-serverscientific-research
Related

Other skills, from other repositories

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。.

huangwb8/ChineseResearchLaTeX · 138 tokens

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。⚠️…

huangwb8/ChineseResearchLaTeX · 194 tokens

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.

openags/paper-search-mcp · 62 tokens

bioprobench

Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.

PKU-YuanGroup/OpenAI4S · 46 tokens

paper-planning

Guides pre-writing planning for academic papers with 4 structured steps: story design (task-challenge-insight-contribution-advantage), experiment planning (comparisons + ablations), figure design (pipeline + teaser), and 4-week timeline management. Includes counterintuitive planning tactics (write a mock rejection…

EvoScientist/EvoSkills · 166 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