Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ZTE-AICloud/Co-OmniSpec/plugin install omni-dsddWrote 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)<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/design"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/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/design"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/design.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00027 | $0.11076 |
| Opus 5 | $0.00014 | $0.05538 |
| Sonnet 5 | $0.00005 | $0.02215 |
| Haiku 4.5 | $0.00003 | $0.01108 |
Grade A, and why
design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 548 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design
行为准则
- ❗ 每个步骤必须按顺序执行，不得跳过或截断
- ❗ 步骤 1 继承 specify 已落盘的
FEATURE_DIR/BRANCH_NAME（paths.json/env.sh）；init 仅扩展 design 字段，不得新建特性目录或改分支名；步骤 1.2 之后以IMPL_DESIGN等为路径基准 - ❗ 产物落盘优先于对话输出 — 必须用 Write/Edit 写入约定路径；禁止仅在回复中展示却未落盘
- ❗ Harness 门禁优先于完成报告 — 每步须
design-gate且gate_exit=0；全量verify-design-artifacts.sh通过后方可报告完成 - ❗ 私域知识检索强约束 — 当 Step 2.2 判定知识源就绪（
ready/self_healed，含自愈后）时，必须真实派发knowledge-retrieval-agent，并以其返回如实填写${FEATURE_DIR}/.runs/internal/knowledge-retrieval.json的knowledge_retrieval字段（executed:true+hits+config_hit/vector_built/graph_built/mode）。禁止在知识源就绪时跳过派发或填executed:false。派发后须运行design-gate --step kr --record，gate_exit=0方可进入步骤 3；gate_exit=1按errors补齐后重跑（最多 2 次）。仅知识源缺失/为空（skip）是合法跳过路径。
环境初始化
本技能所有路径拼接与脚本调用，均依赖以下两个变量。
| 变量 | 含义 | 用途 |
|---|---|---|
CLAUDE_PLUGIN_ROOT |
Omni 插件安装根目录 | 定位本技能脚本、design-resolve-context、check-prerequisites |
CLAUDE_WORKING_DIR |
用户当前工作区目录（可为 Git 仓库子目录） | 定位 .omni-infra/、changes/、Harness 落盘 |
FEATURE_DIR / BRANCH_NAME |
特性目录与分支名（绝对路径 / 名称） | 继承 specify；design-resolve-context.sh 或 source env.sh |
KNOWLEDGE_DIR |
私域知识库根目录（私域知识检索用，与反构文档库 DOC_DIR 独立） |
继承 specify（source env.sh 后已导出）；缺失回退 ${CLAUDE_WORKING_DIR}/omni-doc |
Step 0.1 检查变量
test -n "${CLAUDE_PLUGIN_ROOT:-}" && test -d "${CLAUDE_PLUGIN_ROOT}"
test -n "${CLAUDE_WORKING_DIR:-}" && test -d "${CLAUDE_WORKING_DIR}"
任一项失败 → Step 0.2 补全（仅 Agent 层一次）：
-
CLAUDE_WORKING_DIR缺失时用export CLAUDE_WORKING_DIR="$(pwd)"（不用git rev-parse --show-toplevel）。 -
KNOWLEDGE_DIR（处理方式对标CLAUDE_WORKING_DIR：已注入则沿用）：本技能在 specify 之后执行，${FEATURE_DIR}/.runs/env.sh已含export KNOWLEDGE_DIR，步骤 1source env.sh后即自动获取；若 source 后仍为空（独立调用 / env.sh 缺失），回退默认：# 步骤 1 source env.sh 之后追加（已注入则不覆盖） export KNOWLEDGE_DIR="${KNOWLEDGE_DIR:-${CLAUDE_WORKING_DIR}/omni-doc}"KNOWLEDGE_DIR是可选知识源，不强制目录存在；目录缺失/为空时 Step 2.2 私域检索合法跳过（skip），目录存在时由 Step 2.2 机器闸门判定（ready/self_healed必须派发，详见行为准则 5）。
What ships with it
15 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.
- references/template-contract.json 7.0 KB
- scripts/bash/design-finalize.sh 334 B runs code
- scripts/bash/design-gate.sh 328 B runs code
- scripts/bash/design-harness-common.sh 446 B runs code
- scripts/bash/design-init-harness.sh 1.6 KB runs code
- scripts/bash/design-resolve-context.sh 2.0 KB runs code
- scripts/bash/verify-design-artifacts.sh 1.3 KB runs code
- scripts/powershell/design-finalize.ps1 236 B runs code
- scripts/powershell/design-gate.ps1 230 B runs code
- scripts/powershell/Design-HarnessCommon.ps1 1.2 KB runs code
- scripts/powershell/design-init-harness.ps1 1.5 KB runs code
- scripts/powershell/verify-design-artifacts.ps1 1.3 KB runs code
- scripts/python/design_harness.py 41 KB runs code
- scripts/python/design_template_gate.py 8.0 KB runs code
- scripts/python/test_design_template_gate.py 7.6 KB runs code
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.
- 10d ago First seen · 548 lines · 27 tokens per session scan A c73345debc65
design is a skill published in the GitHub repository ZTE-AICloud/Co-OmniSpec (54 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 11,076 once invoked, about $0.0001 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.