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.
git 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/plugins/zte-aicloud/co-omnispec/omni-dsdd)<a href="https://agentmods.dev/plugins/zte-aicloud/co-omnispec/omni-dsdd"><img src="https://agentmods.dev/badge/plugins/zte-aicloud/co-omnispec/omni-dsdd.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
omni-dsdd 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 8d 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.
What it actually says
{
"name": "omni-dsdd",
"version": "v3.1.4",
"description": "面向规范驱动开发(DSDD)的Harness工程解决方案插件包,覆盖按需求反构、规约制定、需求分析、方案设计、任务拆解、实施与归档全流程,通过多种工作流引导AI编程助手高效交付高质量软件。",
"homepage": "https://github.com/ZTE-AICloud/Co-OmniSpec",
"author": {
"name": "ZTE-AICloud"
},
"license": "MIT",
"keywords": ["SDD", "Harness engineer"]
}
What it installs
The manifest is a name and a version. 40 skills, 16 agents, 1 hook travel with it, and installing the plugin installs all of them — 3,768 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill design A 27 tokens
- Skill implement A 37 tokens
- Skill quarkus-patterns A 52 tokens
- Skill code-review A 32 tokens
- Skill create-branch A 69 tokens
- Skill knowledge-retrieval A 97 tokens
- Skill analyze A 66 tokens
- Skill e2e-varify A 101 tokens
- Skill quarkus-security A 36 tokens
- Skill design-entity A 37 tokens
- Skill design-interface A 42 tokens
- Skill e2e-design A 94 tokens
- Skill design-function A 35 tokens
- Skill eval-design A 39 tokens
- Skill eval-design-consistency-check A 78 tokens
- Skill local-sandbox-fix A 54 tokens
- Skill e2e-specify A 121 tokens
- Skill eval-code A 61 tokens
- Skill eval-code-evaluator A 66 tokens
- Skill brainstorming-sdd-bridge A 49 tokens
- Skill archive A 68 tokens
- Skill clarify A 81 tokens
- Skill checklist A 72 tokens
- Skill eval-specify A 73 tokens
- Skill mini-design A 40 tokens
- Skill mini-implement A 32 tokens
- Skill mini-design-review A 16 tokens
- Skill incremental-coverage C 117 tokens
- Skill brainstorming A 37 tokens
- Skill golang-patterns A 27 tokens
- Skill jpa-patterns A 33 tokens
- Skill golang-testing A 35 tokens
- Skill python-patterns A 33 tokens
- Skill python-testing A 24 tokens
- Skill cpp-coding-standards A 48 tokens
- Skill django-security A 30 tokens
- Skill java-coding-standards A 50 tokens
- Skill cpp-testing A 34 tokens
- Skill fastapi-patterns A 35 tokens
- Skill mini-implement-review A 14 tokens
- Agent test-impl-design A 74 tokens
- Agent test-analysis-design A 109 tokens
- Agent constitution A 34 tokens
- Agent function-identifier A 159 tokens
- Agent logical-architectures-knowledge-extractor A 133 tokens
- Agent requirements-knowledge-extractor A 187 tokens
- Agent function-tree-builder A 138 tokens
- Agent test-case-analyzer A 153 tokens
- Agent complexity-analyzer A 42 tokens
- Agent simple-on-demand-reverse-agent A 80 tokens
- Agent complex-on-demand-function-analyzer A 91 tokens
- Agent knowledge-retrieval-agent A 98 tokens
- Agent mini-design-review A 29 tokens
- Agent mini-implement-review A 28 tokens
- Agent system-contexts-knowledge-extractor A 131 tokens
- Agent scenarios-knowledge-extractor A 190 tokens
- Hook UserPromptExpansion A not measured
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.
- 8d ago First seen · 12 lines scan A af2569e52848
omni-dsdd is a plugin published in the GitHub repository ZTE-AICloud/Co-OmniSpec (54 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins marketplace
Plugin marketplace listing 98 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
ecc
Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses.