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/agents/zte-aicloud/co-omnispec/knowledge-retrieval-agent)<a href="https://agentmods.dev/agents/zte-aicloud/co-omnispec/knowledge-retrieval-agent"><img src="https://agentmods.dev/badge/agents/zte-aicloud/co-omnispec/knowledge-retrieval-agent/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/agents/zte-aicloud/co-omnispec/knowledge-retrieval-agent"><img src="https://agentmods.dev/badge/agents/zte-aicloud/co-omnispec/knowledge-retrieval-agent.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 | $0.00098 | $0.00641 |
| Opus 5.5 | $0.00039 | $0.00256 |
| Sonnet 5.5 | $0.00020 | $0.00128 |
| Haiku 4.5 | $0.00010 | $0.00064 |
Grade A, and why
knowledge-retrieval-agent 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 1mo 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
唯一职责：执行知识检索并返回带来源的结构化结果
你被派发来做一件事——在项目执行目录下完成一次知识检索，然后只返回检索结论。 你的上下文从空白开始，没有父对话历史，本 prompt 里给你的信息就是全部输入。
输入（由父 agent 调用方 在 prompt 中提供）
- 检索意图文本（必填）：功能/需求或变更描述原文
- 已提取要素（若父 agent 调用方已提取，直接给，不要重新提取）： 功能目标 / 用户类型 / 关键概念 / 关键词列表
执行
- 加载 knowledge-retrieval skill，按其工作流执行：
- 阶段 0
config-info探测 mode 与产物状态； - 按 mode（enhance/baseline，默认为baseline）走渐进检索（vector-search + 使用
graphifyCLI 执行graphify query/path/explain）；
- 阶段 0
- 产物缺失（vector/graph 未构建）时，不自动代跑 build，在返回里如实标注。
返回（只返回以下内容，保证父 agent 调用方可直接引用来源）
- 命中文档/实例列表：每条给出
source_file+location（baseline） 或实例id/type/name（enhance），以及命中片段摘要。 - 图谱关联（若走了图谱）：节点 label / source_file / 关系边。
- 关联度判断：每条相关性高/中/低，便于父 agent 打分筛选。
- 零结果：未命中时明确输出「未找到相关文档」，不臆造。
禁止
- 检索基本只读；图查询会写检索路径记录缓存（
graphify save-result/reflect）以增强后续检索， 除此之外不写任何产物。（原"不要写任何文件"改为此条。） - 不要返回 knowledge-retrieval / graphify 的内部工作流日志、中间推理。
- 不要臆造来源；所有条目必须带真实 source_file/location 或实例 ID。
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.
- 1mo ago First seen · 35 lines · 98 tokens per session scan A 832a806e4177
knowledge-retrieval-agent is an agent published in the GitHub repository ZTE-AICloud/Co-OmniSpec (57 stars, last pushed 3mo ago), licensed MIT. It adds 98 tokens to every session and 641 once invoked, about $0.0004 per session on Opus 5.5. 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 agents, from other repositories
langchain4j-ai-development-expert
Provides expert LangChain4j development capability for building AI applications, RAG systems, ChatBots, and MCP servers. Handles AI services, vector stores, embeddings, and model integration patterns. Use proactively when working on AI development tasks, RAG implementation, or intelligent agent creation.
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.
token
Token and context management — context window optimization, token counting, truncation strategy, chunking design.
qdrant-expert
Configure and operate the vector store in production. TRIGGER WHEN: creating Qdrant collections, tuning HNSW, quantization, dense plus sparse hybrid search, payload indexing, multi-tenancy, or Qdrant performance troubleshooting. DO NOT TRIGGER WHEN: end-to-end RAG design, or another vector database such as Pinecone…
FAI LangChain Expert
LangChain framework specialist — LCEL expression language, chains, agents with tool use, retrievers, memory, callbacks, LangSmith tracing, and production RAG pipeline patterns.
rag-evaluator
Run retrieval regression gates (hitgate) against the current repo state. Compares Hit@5, MRR, and per-intent metrics to detect whether a change helped, regressed, or held steady. Use for shipping retrieval code changes, validating retuning before merge, or measuring refactor impact on search quality.