copilot-longrun-bridge
Use this skill when the user wants Codex to hand off a task to GitHub Copilot CLI LongRun for unattended execution, prompt generation, status checks, or resuming previous long-running missions. Trigger on requests mentioning longrun, Copilot CLI long tasks, resumable missions, or asking Codex to launch Copilot as the execution backend.
Best use case
copilot-longrun-bridge is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use this skill when the user wants Codex to hand off a task to GitHub Copilot CLI LongRun for unattended execution, prompt generation, status checks, or resuming previous long-running missions. Trigger on requests mentioning longrun, Copilot CLI long tasks, resumable missions, or asking Codex to launch Copilot as the execution backend.
Teams using copilot-longrun-bridge should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/copilot-longrun-bridge/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How copilot-longrun-bridge Compares
| Feature / Agent | copilot-longrun-bridge | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use this skill when the user wants Codex to hand off a task to GitHub Copilot CLI LongRun for unattended execution, prompt generation, status checks, or resuming previous long-running missions. Trigger on requests mentioning longrun, Copilot CLI long tasks, resumable missions, or asking Codex to launch Copilot as the execution backend.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# LongRun Bridge 这个 skill 让 Codex 成为 LongRun 的轻入口，真正的长跑由本机 GitHub Copilot CLI 执行。 ## 什么时候用 当用户要： - 启动一个无人值守长跑任务 - 只生成 prompt 而不立即执行 - 恢复最近一次或指定 run - 查看 `.copilot-mission-control/` 中的状态 ## 工作流 1. 如果本线程还没做过环境检查，先运行：`longrun-doctor` 2. 若 doctor 报缺：Copilot CLI / 登录 / bare skills / helper bundle / screen，则停止并回显准确修复命令 3. 环境通过后，把任务转发给 shell wrappers 4. 只回报关键结果：PID、日志路径、meta 路径、下一条状态命令 ## 后端 contract 所有命令都在**当前工作目录**执行： - `longrun "<task>"` - `longrun-prompt "<task>"` - `longrun-status latest` - `longrun-resume latest` LongRun launcher 默认： - 使用 `--autopilot --yolo --no-ask-user` - 采用 **Opus-first** 模型策略 - 在 rate limit / model unavailable 时自动 fallback 或 backoff - 默认语义是“跑到 mission 完成后退出”，不是常驻守护 ## 响应策略 - 不要在 Codex 内部重复实现 LongRun 的任务逻辑 - 成功 launch 后，不要在 Codex 本地再跑同一任务 - 若用户要 web-heavy research，可提醒 launcher 已尽量避免 URL 确认，但 raw `/longrun` in-session 方式仍可能继承普通权限模型 - 若用户明确说“不要自己结束 / 持续监控 / 长时间挂着”，优先推荐 detached launcher，而不是 raw `/longrun`
Related Skills
longrun
Orchestrate a long-running autonomous Copilot CLI mission from one prompt. Use when the user explicitly wants a one-shot, autopilot-style workflow with planning, workstream artifacts, evidence capture, recovery, and resumable state under .copilot-mission-control/.
longrun-status
Inspect the latest or a specified long-running Copilot CLI mission under .copilot-mission-control/ and report state, profile, current phase, delivered artifacts, blockers, evidence coverage, and the next likely step.
longrun-resume
Resume the latest or a specified long-running Copilot CLI mission from .copilot-mission-control/ without restarting completed work. Use when the user asks to continue, resume, or cleanly converge a previous /longrun run.
longrun-prompt
Generate a copy-paste GitHub Copilot CLI orchestrator prompt plus recommended launch command from a natural-language task. Use when the user wants prompt generation, orchestration templates, autopilot starter text, or a reusable Copilot CLI command instead of immediate execution.
pkg-memory-bridge
Bridge to PKG systems (Mem0, Graphiti, Solid PODs, Logseq) for individuated information indices
Deprecated skill path — v0.19 → v0.20 bridge
<!-- deft:deprecated-skill-redirect -->
legacy-bridge
Backward compatibility bridge that translates legacy @load patterns to new Skills format. Enables seamless migration with zero breaking changes during 6-month transition period.
github-copilot
AI-powered coding assistant providing inline suggestions, chat interface, code review, and autonomous coding agent across IDEs and GitHub.com
arweave-bridge
ZigZag Exchange Arweave Bridge - Pay with zkSync stablecoins (USDC/USDT/DAI) for permanent Arweave storage. Use for building dApps needing decentralized file storage, NFT metadata permanence, or Layer 2 storage solutions.
agent-skill-bridge
No description provided.
Copilot
Tool: GitHub's AI pair programmer (inline + chat)
retro-copilot
Run a retro for ~/.copilot assets and turn incident learnings into updates for copilot-instructions, instructions, skills, agents, and hooks. Triggers on retro, retrospective, incident learning, error analysis, copilot setup, instructions update, インシデント, and 知見反映.