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/local-agentsgit 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/local-agents)<a href="https://agentmods.dev/agents/feimacode/feima-copilot-llms-extension/local-agents"><img src="https://agentmods.dev/badge/agents/feimacode/feima-copilot-llms-extension/local-agents.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 | $0.00033 | $0.02001 |
| Opus 5 | $0.00016 | $0.01001 |
| Sonnet 5 | $0.00007 | $0.00400 |
| Haiku 4.5 | $0.00003 | $0.00200 |
Grade A, and why
local-agents 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 5d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
本地智能体(Local Agent)在 Visual Studio Code 内部以交互方式运行，在你的机器上工作。它们使用当前工作区，可以访问 VS Code 中可用的所有工具和模型，包括扩展提供的工具和 MCP 服务器。通过创建自定义智能体(Custom Agent)，你可以让智能体(Agent)承担特定角色或角色身份，例如代码审查者、测试工程师或文档撰写者。
本地智能体(Local Agent)在 VS Code 的聊天界面中运行。当你关闭聊天会话时，本地智能体(Local Agent)保持活跃，你可以在会话视图中跟踪它。
💡 国内用户提示 如果您希望使用国内 AI 模型，安装 飞码扣插件 即可在 GitHub Copilot Chat 中使用通义千问(Qwen3)、DeepSeek、GLM 等模型，按次计费。了解更多 → 打开飞码扣
为什么使用本地智能体(Local Agent)？
- 需要即时反馈的交互式对话，例如头脑风暴、规划或尚未完全定义的任务
- 需要从开发环境获取上下文的任务，例如 lint 错误、堆栈跟踪、单元测试结果
- 需要访问 VS Code 扩展或 MCP 服务器的特定工具，或需要使用特定模型（如 BYOK 模型）的任务
- 不需要与其他团队成员协作的任务
主要特性
- 在本机 VS Code 中运行，使用当前工作区
- 基于聊天的交互界面，支持实时反馈和迭代
- 完全访问工作区、文件和上下文
- 可以访问 VS Code 中配置的所有智能体(Agent)工具，包括内置工具、MCP 工具和扩展提供的工具
- 可以使用 VS Code 中为你可用的所有模型，包括 BYOK 模型和其他提供商的模型
内置智能体(Agent)
本地智能体(Local Agent)会话(Agent Session)使用三种内置智能体(Agent)之一，每种针对不同类型的任务进行优化。你可以在聊天会话中随时通过聊天视图中的智能体(Agent)选择器切换智能体(Agent)。对于更专业的工作流程，你可以创建自己的自定义智能体(Custom Agent)。
Agent
Agent 针对基于高层需求的复杂编码任务进行优化，可能需要运行终端命令和工具。AI 自主操作，确定相关上下文和要编辑的文件，规划所需工作，并在出现问题时迭代解决。
VS Code 直接在编辑器中应用代码变更，编辑器覆盖控件让你能够在建议的编辑之间导航并审查它们。智能体(Agent)可能会调用多个工具来完成不同任务。
你可以通过添加 MCP 服务器或安装提供工具的扩展来用额外工具自定义聊天。
重要提示 如果你没有看到智能体(Agent)选项，请确保在 VS Code 设置中启用了智能体（
chat.agent.enabled，此设置由组织级别管理）。你的组织也可能禁用了智能体(Agent)，请联系管理员启用。
Plan
Plan 智能体(Agent)针对为编码任务创建结构化实施计划进行优化。当你想在实施之前将复杂功能或变更分解为更小、更易管理的步骤时，使用 Plan 智能体(Agent)。
Plan 智能体(Agent)生成详细计划，概述所需步骤，并提出澄清性问题以确保全面理解任务。然后你可以将计划移交给实施智能体(Agent)，或将其作为指导使用。
了解更多：使用智能体(Agent)规划。
Ask
Ask 最适合回答有关代码库、编码和通用技术概念的问题。当你想了解某些工作原理、探索想法或获得编码任务帮助时，使用 Ask。
Ask 使用智能体(Agent)能力研究你的代码库并收集相关上下文。响应可以包含代码块，你可以单独应用到代码库中。要应用代码块，将鼠标悬停在代码块上并选择在编辑器中应用按钮。
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.
- 5d ago First seen · 124 lines · 33 tokens per session scan A 38f991f93ccb
local-agents is an agent published in the GitHub repository feimacode/feima-copilot-llms-extension (5 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 2,001 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.