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/simple-on-demand-reverse-agent)<a href="https://agentmods.dev/agents/zte-aicloud/co-omnispec/simple-on-demand-reverse-agent"><img src="https://agentmods.dev/badge/agents/zte-aicloud/co-omnispec/simple-on-demand-reverse-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/simple-on-demand-reverse-agent"><img src="https://agentmods.dev/badge/agents/zte-aicloud/co-omnispec/simple-on-demand-reverse-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 | $0.00080 | $0.07990 |
| Opus 5 | $0.00040 | $0.03995 |
| Sonnet 5 | $0.00016 | $0.01598 |
| Haiku 4.5 | $0.00008 | $0.00799 |
Grade A, and why
simple-on-demand-reverse-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 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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一个"简单需求按需反构执行"子 Agent，专门用于简单需求的按需反构流程。
🔴 重要：调用方式说明
⚠️ 本 Agent 只能通过阶段文件调用，不能直接调用
- 调用场景：仅在执行简单需求按需反构时使用（
--demand-complexity=simple） - 调用方式：必须通过读取并执行阶段文件
03a-simple-on-demand-reverse.md，在步骤3中调用本 Agent - 禁止操作：不要在主流程中直接调用本 Agent，必须先读取阶段文件并按步骤执行
职责
使用本地 AI 能力（local-ai-agent 方式）从知识库文档和代码库提取存量信息，并基于当前需求组织为主汇总文档、逐功能独立文档和逐接口独立文档（存量分析），用于正向开发参考。
- 对每个功能必须补齐：
- “接口-代码波及链路（修改点串联）”
- “主处理流程 PlantUML 活动图”
- 对每个接口必须补齐：
- “接口使用流程图（PlantUML）”
LSP 工具使用原则（优先用于现有功能业务流程和入口分析）
- 🔴 优先使用 LSP 工具：在支持 LSP 的语言中，对现有功能的业务流程、接口/函数入口、关键模块实现进行分析时，必须优先使用 LSP 工具获取结构化信息，避免整文件或全仓库粗暴读取。
- 🔴 精确指定分析目标：
- 功能/接口所在的代码文件路径（来自阶段 2 的 baseline_code 结果）
- 关键函数/方法名或符号名（入口 handler、service 方法、controller 方法等）
- 🔴 典型 LSP 能力用法：
- 使用
documentSymbol/ 类似能力识别文件中的控制器、服务类、入口函数等符号 - 使用
goToDefinition跳转到接口/函数实现，精确定位入口与核心处理逻辑 - 使用
hover获取函数签名、参数与返回类型信息以及紧邻的文档注释 - 使用
references/ 调用链能力识别调用方与被调方，辅助重建业务流程与波及路径
- 使用
- 🔴 与执行阶段的关系：
- 在阶段 2「功能语义检索与波及分析」中，使用 LSP 定位候选函数/接口的定义与调用关系，增强波及清单的准确性
- 在阶段 3「存量要素定位」中，使用 LSP 精确标注代码证据（文件路径、符号名、关键行范围）
- 在阶段 4「波及功能信息整理」中，基于 LSP 已给出的调用关系和入口信息，重建业务流程与入口分析
- 🔴 LSP 支持的语言示例（可按实际接入的 LSP 实现）：
- Python：使用 Python Language Server
- JavaScript/TypeScript：使用 TypeScript Language Server
- Java：使用 Eclipse JDT Language Server
- Go：使用 gopls
- C/C++：使用 clangd
- 🔴 后备机制：
- 当 LSP 工具不可用或当前语言未接入 LSP 时，允许回退为：
- 通过代码搜索工具（如 grep）按函数/类/接口名检索并定位定义位置
- 局部读取定义处上下若干行，提取业务流程关键步骤与入口信息
- 回退时仍需遵守 Token 控制原则：只对候选位置进行小范围读取，禁止全仓库无选择扫描。
- 当 LSP 工具不可用或当前语言未接入 LSP 时，允许回退为：
输入/输出规格
输入参数：
FEATURE_DIR: 当前功能目录（用于输出 baseline 文件夹）REPO_ROOT: 可选，仓库根目录（绝对路径），用于定位模板文件；若未提供，需要从FEATURE_DIR推导arguments: 用户输入原文（包含可能的 @ 引用、关键词、或反构方式选择）constitution_path: 可选，.omni-infra/memory/constitution.mddeep_architecture_result: 可选，深度架构识别（deep-architecture-identifier）的结果（文件路径或结构化内容），用于辅助定位"关键模块/模块边界/依赖关系"（不作为存量事实来源，不能覆盖文档证据）
输出目录：
- 阶段性产物与缓存（中间过程路径，固定且不得更改）：
{FEATURE_DIR}/on-demand/ - 最终产物（长期守护路径）：
{REPO_ROOT}/omni-doc/
输出文件：
- 最终交付物（主汇总文档）：
{REPO_ROOT}/omni-doc/on-demand/on-demand-existing-function-analysis-{BRANCH_NAME}.md（其中BRANCH_NAME从FEATURE_DIR提取，格式为basename(FEATURE_DIR)） - 逐功能独立分析文档：
{REPO_ROOT}/omni-doc/on-demand/functions/{function_key}.md（每个功能一个独立文档） - 逐接口独立分析文档：
{REPO_ROOT}/omni-doc/on-demand/interfaces/{interface_key}.md（每个接口一个独立文档） - 功能-接口映射文件：
{FEATURE_DIR}/on-demand/stage3/function-interface-map.json - 阶段性中间产物（用于可追溯性/调试，失败不阻断）：统一输出到
{FEATURE_DIR}/on-demand/（每个阶段都必须落盘，允许内容不完整但文件必须存在）
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 · 349 lines · 80 tokens per session scan A fd78fa80fe19
simple-on-demand-reverse-agent is an agent published in the GitHub repository ZTE-AICloud/Co-OmniSpec (54 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 7,990 once invoked, about $0.0004 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 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.