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.
npx agentmods add agents/feimacode/feima-copilot-llms-extension/overviewgit clone --depth 1 https://github.com/feimacode/feima-copilot-llms-extensionWrote 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/feimacode/feima-copilot-llms-extension/overview)<a href="https://agentmods.dev/agents/feimacode/feima-copilot-llms-extension/overview"><img src="https://agentmods.dev/badge/agents/feimacode/feima-copilot-llms-extension/overview.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.02578 |
| Opus 5 | $0.00015 | $0.01289 |
| Sonnet 5 | $0.00006 | $0.00516 |
| Haiku 4.5 | $0.00003 | $0.00258 |
Grade A, and why
overview 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 3d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
智能体(Agent)是一种能自主完成编码任务的 AI 助手。给它一个高层目标，它会将目标分解为步骤、跨文件编辑项目、运行命令，并在出现问题时自我纠正。例如，智能体(Agent)不会仅仅建议如何修复失败的测试，而是跨文件识别根本原因、更新代码、重新运行测试并提交变更。
VS Code 让你能够按照最适合工作流程的方式运行智能体(Agent)。可以在编辑器中与它们交互，或通过 CLI 让它们在后台自主运行。智能体(Agent)可以在你的机器上、远程云环境中，或通过 Anthropic、OpenAI 等第三方提供商运行。你可以控制给予它们多少自主权——从批准每次工具调用(Tool Call)到让它们完全自主工作——还可以创建自定义智能体(Custom Agent)来定制其行为以适应你的项目。
无论智能体(Agent)在哪里运行，你都可以从聊天视图中的统一会话列表中监控和交互所有会话。如果你更倾向于通过提示词(Prompt)工作，Agents 应用提供了专用界面，以会话和聊天为核心体验，并内置所有 AI 自定义内容的访问入口。
提示 在 VS Code 设置中启用智能体（
chat.agent.enabled）。你的组织也可能禁用了智能体(Agent)——请联系管理员启用此功能。
💡 国内用户替代方案 除了 GitHub Copilot 官方订阅，您也可以使用 飞码扣插件 — 在 GitHub Copilot Chat 中直接使用通义千问(Qwen3)、DeepSeek V3.2、GLM-5 等国内顶级 AI 模型，按次计费，无需月付订阅。立即开始 → 打开飞码扣
智能体(Agent)类型
智能体(Agent)根据需要运行在不同的环境中。两个关键维度是：智能体(Agent)在_哪里_运行（你的机器或云端）以及_如何_与之交互（交互式还是在后台自主运行）。
- 本地（Local）：使用 VS Code 智能体(Agent)循环在编辑器中交互式运行，可完全访问工作区、工具和模型。
- Copilot CLI：使用 Copilot CLI 在本机后台运行，可选择使用 Git worktree 进行隔离。
- 云端（Cloud）：使用 GitHub Copilot 远程运行，并与 GitHub 拉取请求(Pull Request)集成以进行团队协作。
- 第三方（Third-party）：使用 Anthropic 和 OpenAI 的第三方智能体(Third-party Agent) SDK，既可在本机运行也可在云端运行。
从聊天视图中的智能体(Agent)目标下拉菜单选择智能体(Agent)类型。
我应该使用哪种智能体(Agent)类型？
使用下表找到适合你任务的智能体(Agent)类型：
| 我想要... | 使用 |
|---|---|
| 交互式地头脑风暴、探索或迭代一个想法 | 本地智能体(Local Agent) |
| 查询我的代码库 | 本地智能体(Local Agent)（Ask） |
| 创建结构化实施计划 | 本地智能体(Local Agent)（Plan） |
| 修复需要编辑器上下文的问题（测试失败、lint 错误、调试输出） | 本地智能体(Local Agent) |
| 使用集成浏览器构建和测试 Web 应用 (实验性) | 本地智能体(Local Agent)。参见浏览器智能体(Agent)测试指南。 |
| 使用特定的 VS Code 扩展工具或 MCP 服务器 | 本地智能体(Local Agent) |
| 在我继续工作的同时实现定义明确的任务 | Copilot CLI 或 云端智能体(Cloud Agent) |
| 探索多个变体或概念验证 | Copilot CLI 或 云端智能体(Cloud Agent) |
| 为团队审查创建 PR | 云端智能体(Cloud Agent) |
| 将 GitHub Issue 分配给智能体(Agent) | 云端智能体(Cloud Agent) |
| 使用特定 AI 提供商（Anthropic、OpenAI） | 第三方智能体(Third-party Agent) |
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.
- 3d ago First seen · 108 lines · 31 tokens per session scan A 159f0698a5ca
overview is an agent published in the GitHub repository feimacode/feima-copilot-llms-extension (5 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 2,578 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
agent_types
This document describes how the unified three-layer Device Agent architecture is implemented across different platforms. While the core framework (State, Processor, Command layers) remains consistent, each platform implements specialized agents optimized for their native control mechanisms and hierarchies.…
server_client_architecture
Device agents in UFO are partitioned into server and client components, separating high-level orchestration from low-level execution. This architecture enables safe, scalable, and flexible task execution across heterogeneous devices through the Agent Interaction Protocol (AIP).
advisor
Opus 级高级技术顾问，提供第二意见、方案比较和风险审阅。适用于技术选型、实现规划、架构/API/并发/安全问题、疑难 bug 根因、代码或调查结论审阅，以及任何需要判断“是否/哪种/怎么做”的任务；可读取调用方明确列出的证据文件，不负责实现或验证。.
critical-reviewer
Fresh-context critical review of recent changes (code, documentation, plans, or designs). Read-only. Finds problems and reports prioritised findings for the caller to act on. Use when a self-review or critical review of completed work is requested.
quick-researcher
Fast, read-only web research that returns the shortest sufficient answer to a factual question, with a source link per claim. Use for "what/which/when/how much/is X still..." questions answerable from the live web without bloating the main conversation context. Not for software implementation guides (use…
orchestrator
Agent "orchestrator" from openinterpreter/openinterpreter, covering user updates spec, reviews and general guidelines.