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/oneworks-ai/app/create-entitynpx skills add oneworks-ai/app --skill create-entitygit clone --depth 1 https://github.com/oneworks-ai/appWhat 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 | $0.00031 | $0.01802 |
| Opus 5 | $0.00015 | $0.00901 |
| Sonnet 5 | $0.00006 | $0.00360 |
| Haiku 4.5 | $0.00003 | $0.00180 |
Grade A, and why
create-entity 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
在用户要求“创建实体”“新增 agent/entity”“按某个角色沉淀实体”“把当前工作流变成实体”时使用这个 skill。
如果用户要求修改已有实体,使用 update-entity。
目标
把用户的自然语言需求转成可运行、可维护的 OneWorks entity。完成后,项目里应该出现一个清晰命名的实体定义,必要时配套默认 prompt 文件、规则引用、技能引用和继承关系。
信息收集
开始前先收敛这些信息;如果用户已经给出,就不要重复询问:
- 实体的职责:它负责什么问题、什么时候应该被选择。
- 使用场景:开发、评审、验证、调研、文档、运维或项目特定流程。
- 输出风格:汇报格式、语气、详略、是否优先列风险或结论。
- 能力边界:它不该做什么,什么时候应该交还给用户或其他实体。
- 可复用资产:是否应继承已有实体,是否需要引用已有 rules、skills、MCP server 或 tool filter。
如果需求仍然模糊,先用一个保守实体落地,再在 final answer 里列出可继续补充的字段。
资产检查
创建前先检查当前项目已有资产:
- 本地实体目录:避免实体名冲突,并观察本项目实体写法。
- 本地 rules 目录:优先引用已有规则,不要重复复制规则正文。
- 本地 skills 目录:优先引用已有技能,不要把大型操作流程塞进 entity prompt。
- 插件实体:如果项目启用了插件并配置了 scope,继承时使用
scope/name,例如std/dev-reviewer。
不要凭空引用不存在的 rule 或 skill。确实需要新增配套资产时,先确认用户需求是否要求一起创建;否则在结果里说明缺口。
实体目录定位
不要硬编码 .oo。先解析本地资产根目录和实体目录,再创建文件:
__ONEWORKS_PROJECT_BASE_DIR__=.oneworks时,本地资产根目录从.oo变成.oneworks。__ONEWORKS_PROJECT_ENTITIES_DIR__=agents时,实体目录从<asset-root>/entities变成<asset-root>/agents。- 如果不确定配置,先检查
.env和现有实体目录;仍不确定时使用默认.oo/entities/。 - 后文的
<entity-dir>指解析后的本地实体目录,不一定是.oo/entities。
新实体只能写入当前项目的本地实体目录。不要修改这些上游或受管理位置:
node_modules/**packages/plugins/**<asset-root>/plugins/**/oneworks/**- 任意插件包或 marketplace 同步下来的实体文件
如果用户想“改某个插件实体”,创建一个本地派生实体,并用 extends: scope/name 继承插件实体。
文件布局
优先使用目录型实体:
<entity-dir>/<entity-name>/README.md
当实体提示较长,或需要拆分身份、人格、记忆时,继续使用默认会被加载的文件:
<entity-dir>/<entity-name>/INTRODUCTION.md
<entity-dir>/<entity-name>/PERSONALITY.md
<entity-dir>/<entity-name>/MEMORY.md
简单实体可以使用单文件:
<entity-dir>/<entity-name>.md
命名使用 kebab-case,例如 frontend-reviewer、release-coordinator。名称应体现角色和场景,不要使用 new-entity、agent1 这类临时名。
Frontmatter 模板
README.md 的 frontmatter 保持可读、最小够用:
---
name: frontend-reviewer
description: 评审前端交互、样式、focus、主题和移动端布局风险的实体。
tags:
- frontend
- review
extends:
- std/dev-reviewer
inherit:
prompt: append
rules: merge
skills: merge
tools: replace
mcpServers: replace
rules:
- frontend-standard
skills:
- frontend-review
tools:
include:
- Read
- Grep
---
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 · 179 lines · 31 tokens per session scan A f320e50dbedc
create-entity is a skill published in the GitHub repository oneworks-ai/app (18 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 1,802 once invoked, about $0.0002 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
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.
neo4j-document-import-skill
Ingests unstructured and semi-structured documents into Neo4j as a knowledge graph. Use when chunking PDFs, HTML, plain text, or Markdown; extracting entities and relationships from text with an LLM (SimpleKGPipeline, neo4j-graphrag); loading JSON via apoc.load.json; building Document→Chunk→Entity graph structures; or…
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…
lov-env-management
统一管理平台、账号与多组 API Key,维护有效期和启用状态,安全同步到 zsh 或用户会话环境,并提供脱敏 Dashboard;用户说“管理环境变量”“rotate API keys”时使用。.
lov-deploy-to-vercel
Deploy frontend projects to Vercel with automatic custom domain setup. Handles Vite, Next.js, CRA, and static sites. Auto-configures Cloudflare DNS CNAME records and Vercel domain aliases. Supports SPA routing via vercel.json. Trigger when user says "deploy to vercel", "部署到 vercel", "vercel deploy", or mentions a…