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 skills add ZTE-AICloud/Co-OmniSpec --skill design-interfacegit clone --depth 1 https://github.com/ZTE-AICloud/Co-OmniSpecWrote 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/zte-aicloud/co-omnispec/design-interface)<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/design-interface"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/design-interface/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/design-interface"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/design-interface.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00042 | $0.02342 |
| Opus 5 | $0.00021 | $0.01171 |
| Sonnet 5 | $0.00008 | $0.00468 |
| Haiku 4.5 | $0.00004 | $0.00234 |
Grade A, and why
design-interface 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 9d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-interface
使用时机
- 仅被
designskill 显式调用
接口定义
- 接口是“能力边界”的可执行表达: 将逻辑实体对外提供的能力与协作方式,抽象为可被调用、可被测试、可被版本化的契约(HTTP API、RPC、消息事件、SDK 函数等)。
- 接口契约应明确其能力语义(做什么/为何需要)、输入输出(参数、返回、错误)、调用场景(谁在何时调用)、处理流程(核心步骤与关键分支)以及代码映射(如可推导)。
- 接口分为两类:
- 对外接口: 逻辑实体边界之外的调用方可直接调用(系统外部或内部其他模块)
- 内部接口: 仅用于逻辑实体内部/实体间协作的实现细节,不应作为“直接对外能力”暴露
注意事项:
- 以逻辑实体为单位收敛“能力清单”,将能力映射为接口候选,并为每个候选明确:
- 所属逻辑实体:
ENTITY-XXX - 接口类型: 对外接口 / 内部接口
- 调用方: 实体边界之外的调用者是谁(对外)或协作方是谁(内部)
- 结合有效架构约束文档(见下「架构文档解析」)校验:
- 对外接口的暴露形式与所在层次是否合理(避免在低层泄露上层语义或形成反向依赖)
- 内部接口是否被错误地当作对外能力暴露(导致边界外泄)
架构文档解析(与 design / design-entity 一致)
按以下顺序选用第一个存在的文件作为本次步骤的架构输入;均不存在则不阻塞,不将「缺少架构文件」视为失败,依赖 FEATURE_SPEC、context.md 与 IMPL_DESIGN 已有分层描述进行接口层次校验,并在必要时在契约说明中显式记录假设:
${DOC_DIR}/on-demand/logic_architecture.md(按需反构,优先)${DOC_DIR}/specs/logic_architecture.md(规格库)
下文所称「有效架构约束文档」指按上式解析得到的文件;若未解析到任何文件,则称「未加载架构文档」。
指令
步骤1: 明确输入与上下文
- 实体输入: 读取 IMPL_DESIGN 中的「逻辑实体」章节(特别是实体职责边界、协作关系、方法/能力说明)。
- 架构约束: 按「架构文档解析」加载有效架构约束文档;若已加载,据此明确系统分层、跨层调用方向与允许的依赖边界;若未加载,基于 IMPL_DESIGN /
FEATURE_SPEC中的分层假设校验接口暴露层次与调用方向。 - 上下文文件: 优先读取
FEATURE_DIR/context.md中的「相关接口文档」章节,作为既有接口的主要参考来源。 - on-demand 上下文(可选优先):
- 若
context_mode = evidence_first,优先消费on_demand.scope.interfaces、on_demand.traceability、on_demand.contract_deltas、on_demand.risks、on_demand.evidence_gaps。
- 若
步骤2: 分析接口与确定动作类型
基于步骤1输入与上下文,按「接口定义」识别并产出本次变更涉及的全部接口条目(含INSERT/MODIFY/DELETE/REFER),作为后续步骤的范围基线。
动作类型定义:
- MODIFY: 业务意图要求调整既有接口的语义、参数/返回或行为约束时。优先基于
FEATURE_DIR/context.md指向的既有接口文档进行修改。 - INSERT:
- 理解既有接口,现有接口无法表达该能力边界或会导致语义混淆/职责过载时。
- 不存在既有接口时,则需新增所需接口。
- DELETE: 除非删除具有明确业务必要性且风险可控,否则不删除;必须给出充分理由与影响分析(依赖方、兼容策略、回滚策略)。
- REFER: 既有接口已充分覆盖当前业务意图,无需对接口内容作任何修改,但需建立引用关系以支持后续波及分析。
on-demand 接口消费规则(仅 evidence_first 模式):
- 以
on_demand.scope.interfaces建立接口基线(白名单)。 - 以
on_demand.contract_deltas作为契约变化的主输入:request_added[]→ 请求参数新增/约束response_added[]/response_modified[]→ 响应结构变化与兼容策略
- 通过
on_demand.traceability校验每个接口是否有对应功能来源,避免“无来源接口”。 - 未在 scope 且无证据链支撑的接口不得进入主契约(防止边界外扩)。
on_demand.risks/on_demand.evidence_gaps至少映射到一个错误处理或兼容说明条目。
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.
- 9d ago First seen · 138 lines · 42 tokens per session scan A 71f262ac4b78
design-interface is a skill published in the GitHub repository ZTE-AICloud/Co-OmniSpec (54 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 2,342 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
feature-flag-policy
Cargo feature flags for crates/xberg — ORT-incompatible targets (WASM, Android x8664 emulator), type-only and tract inference companion features, WASM/Android-safe variants, PDF backend, mutually-exclusive ORT variants, platform-conditional deps, aggregate feature sets, and build profiles. Load when adding, wiring, or…
ocr-pipeline-and-quality
Change or evaluate Xberg OCR backends, preprocessing, caching, page acceptance, geometry, hOCR structure, table reconstruction, or cross-backend quality. Load for OCR behavior and A/B quality work, not ordinary PDF text extraction.
pdf-backends
Change or diagnose Xberg PDF extraction, native/Pdfium backend selection, PDF rendering sessions, encrypted documents, OCR fallback, or backend-specific capability gaps. Load for PDF engine work, not generic image OCR.
add-sharepoint
Adds SharePoint Online connector to a Power Apps code app. Use when reading lists, managing documents, or integrating with SharePoint sites. Can also create new SharePoint lists.
using-the-mcp-server
Use when converting HTML to Markdown or extracting metadata and tables through the html-to-markdown MCP server's tools, rather than shelling out to the CLI. Covers the tool surface, the auto-installing launcher, and when MCP beats the CLI or SDK.
nw-diagram
Generates C4 architecture diagrams (context, container, component) in Mermaid or PlantUML. Use when creating or updating architecture visualizations.