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.
Best use case
longrun-status is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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.
Teams using longrun-status 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/longrun-status/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How longrun-status Compares
| Feature / Agent | longrun-status | 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?
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.
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
这是只读技能，不要修改文件。 ## Resolve run - 若 prompt 指定 run-id，就用它。 - 否则读取 `.copilot-mission-control/state/latest-run-id`。 - 若不存在 run，直接说明当前工作区还没有 LongRun 状态。 ## Read order 按下面顺序读取，够用即停： 1. `status.json` 2. `mission.md` 3. `plan.md` 4. `COMPLETION.md` 或 `final-summary.md`（若存在） 5. `journal.jsonl` 尾部 6. `hook-events.jsonl` 尾部（仅在需要解释错误/限流时） 7. `sources.jsonl` 和 `artifacts/` 列表（仅在 research / office 时） ## 输出要点 简洁返回： - run id - state / phase - profile / complexity - selected model / fallback reason（若有） - model control mode（`session-inherited | launcher-enforced | explicit-session-model`） - 已交付内容 - 当前 blocker / risk - sources / artifacts 覆盖情况（研究/办公任务） - 下一步 - 是否 `resumable` / `complete` / `blocked` 如果 `status.json` 仍是 `running`，但 `COMPLETION.md` / `final-summary.md` 已存在，或 deliverables 已完成，明确指出这是**脏状态**，建议用 `/longrun-resume latest` 进行收敛式 finalize，而不是从头重跑。 如果出现以下任一情况，也要明确指出是**脏状态 / state drift**： - `status=complete` 但 `deliverables` 为空 - `status=complete` 但 `activeWorkstreams` 不为空 - `status=complete` 但 `.copilot-mission-control/state/active-run-id` 仍指向当前 run - `plan.md` 顶部缺少 `LongRun Status Board` 或未和 `status.json` 同步 - `selectedModel=claude-opus-*`，但 `modelControlMode=session-inherited`
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-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.
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.
pr-status
Fetch and display the full status of the current PR — CI checks, GitHub Actions runs, reviews, and code comments — using GitHub MCP tools. Invoke manually with /pr-status.
status
Show current project status — worklog state, Phase progress, and layer implementation coverage. Use when you need a snapshot of where the project stands.
statuscake-automation
Automate Statuscake tasks via Rube MCP (Composio). Always search tools first for current schemas.
managing-code-status-discussions
Documents goals-of-care conversations with code status decisions and advance directive alignment. Use when discussing code status, documenting goals-of-care, or recording advance directive conversations.
documenting-mental-status-exams
Creates structured MSE documentation covering appearance, behavior, speech, mood, thought, cognition, and insight. Use when documenting mental status, writing MSE sections, or describing psychiatric findings.
calculating-performance-status
Documents ECOG and Karnofsky performance status with treatment eligibility implications. Use when assessing performance status, documenting ECOG scores, or evaluating treatment candidacy.
ediscovery-status-report
Generates a structured internal e-discovery status report tracking ESI from collection through attorney review. Covers custodian volumes, search term hit rates, review coding statistics, reviewer productivity, and projected timelines. Use when counsel, case managers, or clients need a progress report during the discovery phase of U.S. commercial litigation.
~aod-status
On-demand backlog snapshot and lifecycle stage summary. Regenerates BACKLOG.md from GitHub Issues and displays item counts per stage. Use this skill when you need to check backlog status, view stage counts, regenerate BACKLOG.md, or get a lifecycle overview.