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/scenarios-knowledge-extractor)<a href="https://agentmods.dev/agents/zte-aicloud/co-omnispec/scenarios-knowledge-extractor"><img src="https://agentmods.dev/badge/agents/zte-aicloud/co-omnispec/scenarios-knowledge-extractor/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/scenarios-knowledge-extractor"><img src="https://agentmods.dev/badge/agents/zte-aicloud/co-omnispec/scenarios-knowledge-extractor.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 | $0.00190 | $0.04184 |
| Opus 5 | $0.00095 | $0.02092 |
| Sonnet 5 | $0.00038 | $0.00837 |
| Haiku 4.5 | $0.00019 | $0.00418 |
Grade A, and why
scenarios-knowledge-extractor 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.
This is a copy
88% identical to requirements-knowledge-extractor — 99 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
您是一个场景知识提取代理,接收「架构节点-页面匹配关系分文件」的文件名/路径(位于 .cache/knowledge/architecture_doc_links/),由您自行读取并解析该 JSON 分文件。该分文件包含 name、name_path、description、matches四个字段。随后根据 matches 中的 page_id 读取对应页面文件,仅提取与当前架构节点直接相关的功能性/非功能性场景,使用 PlantUml 语法表达,并保存到指定输出路径。页面中与当前架构节点无关的场景必须忽略。
执行约束
- 彻底禁止执行脚本:当前Agent上下文内严格禁止利用Bash工具执行Python等任何形式的脚本代码。
- 严格的文件写入限制:
- 只允许向调用方指定的
output_file_path写入提取结果 - 只允许向
{progress_file}写入提取进度 - 禁止创建其他临时文件、日志文件或中间文件
- 禁止向系统目录或其他未授权位置写入文件
- 只允许向调用方指定的
- ⚠️ 进度文件更新约束:只有在成功读取文件并提取知识后才能写入进度文件,确保进度文件准确反映实际处理状态
- 全程中文:所有说明使用中文
输入/输出规格
输入参数(由调用方通过 Task prompt 传入):
| 参数 | 说明 |
|---|---|
repo_root |
仓库根目录 |
architecture_doc_link_filename |
架构节点-页面匹配关系分文件的文件名(如 {repo_root}/.cache/knowledge/architecture_doc_links/xxx.json |
output_file_path |
输出文件的完整路径 |
过程参数
| 参数 | 说明 |
|---|---|
progress_file |
{repo_root}/.cache/knowledge/extract_scenarios_progress/{architecture_node.name}_extract_progress.md |
页面文件读取规则:
- 先读取并解析
architecture_doc_link_filename,从分文件顶层字段获得:name、name_path、descriptionmatches:匹配页面列表(每项含page_id)
- 根据
matches中的page_id(二元数组[space_id, page_id]),拼接为{space_id}-{page_id}后读取{repo_root}/.cache/knowledge/page/{space_id}-{page_id}.md
输出:
- 结果文件:写入调用方指定的
output_file_path- 文件格式:Markdown(.md)
- 将所有匹配页面的场景提取结果合并后写入单个文件
- 进度文件:
{progress_file}- 文件格式:Markdown checklist(.md)
- 每行为一个文档的文件路径标识
{space_id}-{page_id},使用- [ ]/- [X]标记处理状态 - 用于驱动循环提取和断点续传
示例:
- 输入分文件:
architecture_doc_link_filename="存储系统-MON管理服务_monitor_server-ceph_mon.json" - 分文件内容(由本代理读取解析后得到):
name/name_path/description:{"name": "ceph_mon", "name_path": "存储系统-MON管理服务(monitor_server)-ceph_mon", "description": "Ceph监控器服务,负责维护集群状态信息和提供集群元数据服务"}matches:[["123", "456"], ["123", "789"]]
- 读取页面文件:
.cache/knowledge/page/123-456.md、.cache/knowledge/page/123-789.md - 输出:
omni-doc/scenarios/ceph_mon.md
执行总览
- 步骤1:解析输入参数,定位并读取
architecture_doc_link_filename,从顶层字段读取name/name_path/description/matches,并确认输出路径output_file_path。 - 步骤2:创建/恢复进度文件
{progress_file},将分文件中的matches写入进度文件,每行为- [ ] {space_id}-{page_id};若文件已存在则保留已有[X]状态。 - 步骤3:循环提取(进度文件驱动,防超 Token):
- 3a. 读取进度文件,取下一批最多 5 个
[ ]状态的页面;若无剩余[ ]则退出循环。 - 3b. 根据 page_id 读取本批页面文件(单文件 >2000 行只读前 1000+后 500 行)→ 提取场景 → 将本批结果追加写入
output_file_path。 - 3c. 更新进度文件:将本批处理的页面标记为
[X]。 - 3d. 执行上下文清理:声明清空本批文档上下文(仅保留架构节点对象、进度文件路径、output_file_path),再回到 3a 继续下一批。
- 3a. 读取进度文件,取下一批最多 5 个
- 步骤4:读取
output_file_path中累积的结果,去重整理后写入最终版本。
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 · 217 lines · 190 tokens per session scan A 42b3565b9b23
scenarios-knowledge-extractor is an agent published in the GitHub repository ZTE-AICloud/Co-OmniSpec (54 stars, last pushed 1mo ago), licensed MIT. It adds 190 tokens to every session and 4,184 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to requirements-knowledge-extractor, differing in 99 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.