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 eval-designgit 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/eval-design)<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/eval-design"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/eval-design/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/eval-design"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/eval-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 40 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 49 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00039 | $0.01872 |
| Opus 5 | $0.00019 | $0.00936 |
| Sonnet 5 | $0.00008 | $0.00374 |
| Haiku 4.5 | $0.00004 | $0.00187 |
Grade A, and why
eval-design 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
方案文档质量评测量规
适用范围
由 design skill 在 design 步骤调用。对 design.md 进行多维度质量评测，输出 badcase 清单与 surface_reason。严格不产出根因分析与提示词缺陷诊断。
变量定义
| 变量 | 含义 | 默认值 |
|---|---|---|
{SPECIFY_ROOT} |
OmniSpec 根目录 | 当前工作目录的上一级（../） |
{feature_dir} |
设计文档所在目录 | 由调用方（design skill）传入 |
五维量规（满分 100）
| 维度 | 权重 | 评测重点 |
|---|---|---|
| 结构完整性（structure） | 20% | 7 章覆盖度、层级合理性（深度≤4）、逻辑顺序、粒度均衡 |
| 语义准确性（semantic） | 30% | 与 spec 的语义一致、关键概念覆盖、设计决策一致性 |
| 业务规则准确性（business_rules） | 20% | 规则完整性、正确性、一致性、FMEA 覆盖度 |
| 规则合规性（compliance） | 10% | 格式规范（标题层级、表格格式、图表语法） |
| 文档质量（quality） | 20% | 逻辑连贯性、详细程度、可读性、完整性 |
结构完整性检查项（对齐 7 章）
参考 {SPECIFY_ROOT}/verification/design-content-generator/references/document-structure.md：
| 部分 | 最低要求 |
|---|---|
| 第 1 部分 | 1.1 业务背景 >= 3 句话（痛点+现状+诉求）；1.2 方案价值为一段话（非列表） |
| 第 2 部分 | 2.1 方案概述一段话；2.2 新旧对比表 >= 3 维度；2.3 时序图参与者 >= 4、交互步骤 >= 6、变更点红色标注、含 legend |
| 第 3 部分 | 每变更点含位置+类型+默认值+说明；无变更时简要说明 |
| 第 4 部分 | 每子模块：业务说明 >= 3 句 + PlantUML + 业务规则表 >= 2 行 |
| 第 5 部分 | 无风险时 >= 2 段话；有风险时含 FMEA 分析表 |
| 第 6 部分 | 无影响时 >= 2 段话；有影响时含性能评估表 |
| 第 9 部分 | 9.1 包结构 >= 2 层；9.2 组件 >= 3 个含 legend；9.3 类关系 5 分区含 legend |
| 全文 | 总行数 >= 250 |
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 · 162 lines · 39 tokens per session scan A 03959f7fed55
eval-design is a skill published in the GitHub repository ZTE-AICloud/Co-OmniSpec (54 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,872 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.