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/copilot-cligit clone --depth 1 https://github.com/feimacode/feima-copilot-llms-extensionWhat 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 | $0.00037 | $0.02684 |
| Opus 5 | $0.00018 | $0.01342 |
| Sonnet 5 | $0.00007 | $0.00537 |
| Haiku 4.5 | $0.00004 | $0.00268 |
Grade A, and why
copilot-cli 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 2d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Studio Code 支持通过 GitHub Copilot CLI 在后台运行智能体(Agent)会话(Agent Session)。你可以从 VS Code 的统一聊天视图中启动、监控和管理 Copilot CLI 会话，而智能体(Agent)在本机自主运行，你可以继续在编辑器中进行其他工作。并行运行多个 Copilot CLI 会话，同时处理多个独立任务。
要启动 Copilot CLI 会话，可以创建新会话，也可以将本地智能体(Local Agent)会话(Agent Session)移交给 Copilot CLI，传递现有上下文。
💡 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
提示 OpenAI Codex 等第三方提供商也提供后台能力。了解更多：第三方智能体(Third-party Agent)。
什么是 Copilot CLI 会话？
Copilot CLI 会话在本机后台独立运行，使用 Copilot CLI 智能体(Agent)框架。VS Code 通过 Copilot SDK 与这些智能体(Agent)集成，用于启动、停止和监控后台会话的进度。VS Code 会自动为你安装和配置 Copilot CLI。
Copilot SDK 会话在 VS Code 之外运行，当你关闭 VS Code 窗口时仍会继续在后台运行。这与使用 VS Code 智能体(Agent)框架在编辑器内部运行并在 VS Code 停止时也停止的本地智能体(Local Agent)不同。
你可以从统一聊天视图与 Copilot CLI 会话交互。当后台会话需要你的输入或需要权限来执行操作时，你可以在聊天中进行操作。智能体(Agent)状态指示器也会在会话需要输入时提供提示。
由于 Copilot CLI 会话在后台运行，它们非常适合范围明确、拥有所有必要上下文且不需要频繁用户交互的任务。例如，从计划实施功能、创建概念验证的多个变体，或实施明确定义的修复或功能。
Copilot CLI 在聊天中支持斜杠命令(Slash Command)，包括可重用提示词(Prompt)、智能体(Agent)技能、Hooks、用于管理长对话的 /compact，以及用于切换工具自动批准的 /yolo 或 /autoApprove。在 Copilot CLI 会话的聊天输入框中输入 / 可查看可用命令。
隔离模式
Copilot CLI 支持两种隔离模式来管理智能体(Agent)变更如何应用到代码库：Worktree 和 Workspace 隔离。你可以在创建新的 Copilot CLI 会话时选择隔离模式。
要隔离 Copilot CLI 智能体(Agent)的变更并防止干扰你的当前工作，使用 Worktree 隔离。在此模式下，VS Code 为 Copilot CLI 会话在单独的文件夹中创建一个 Git worktree。智能体(Agent)所做的所有变更都应用到 worktree，与你的主工作区保持分离，直到你准备好审查并应用它们。
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.
- 2d ago First seen · 131 lines · 37 tokens per session scan A 237e668fe88f
copilot-cli is an agent published in the GitHub repository feimacode/feima-copilot-llms-extension (5 stars, last pushed 5d ago), licensed MIT. It adds 37 tokens to every session and 2,684 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
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。.
code-reviewer
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
minimal-helper
项目目录定义的最小只读助手，用于独立分析给定上下文并返回简洁结论。.
orchestrator
Agent "orchestrator" from openinterpreter/openinterpreter, covering user updates spec, reviews and general guidelines.
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
security-champion-agent
Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.