본문으로 건너뛰기
cccskills
무료GitHub에 공개

ruos-host-run

Run a ruflo agent on your ruOS cloud desktop through an authenticated connection. Follow its output as it runs, record execution status in ruflo, and release the task claim when the run finishes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Run a ruflo swarm agent on the user's own ruOS cloud desktop through the tenant-authenticated fleet MCP, stream its output, and record it in ruflo's swarm state. Use when the user wants an agent to run on a ruOS desktop, asks to "run this on my ruOS desktop", or places a swarm agent on a remote ruOS host.

설치 방법 보기

이럴 때 유용합니다

  • Run an agent task on a ruOS desktop
  • Follow remote agent output as it runs
  • Record remote execution status in ruflo
  • Run unattended tasks from a terminal

포함된 파일(1)

  • SKILL.md4.1 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Run a ruflo agent on a ruOS desktop (session path, ADR-405)

Transport rules — non-negotiable:

  • Use ONLY the fleet MCP tools (mcp__ruos__*, or the claude.ai ruOS connector's equivalents) or the plugin CLI. Never call a desktop on port 17870 and never set a Host header yourself (ruOS ADR-070: that executor has no per-tenant auth).
  • Send ONLY the command strings printed by cli.mjs build. Never compose a desktop_exec command from task text.

CLI below is node "${CLAUDE_PLUGIN_ROOT}/scripts/cli.mjs".

desktop_exec output is framed: the first line echoes your command (▶ run: …), and the last lines are ✓ SUCCESS… and 📝 transcript:. Every marker the desktop prints is RUOS<nonce>_NAME, on its own line, where <nonce> is the nonce from CLI build. That token never appears in the echoed command, so match only complete lines that start with it. Output is capped at about 4 KiB, so poll returns 2 KiB slices. Never call desktop_delete or secret_delete; deleting is the user's job.

  1. Pick the host. Call desktop_status. Resolve the user's desktop by machine_id, fly_machine_id or exact display_name; if it is not in that list, stop. Save the raw JSON to a temp file (status.json) for step 4.
  2. Liveness. A desktop is up only if heartbeat_status is not asleep/missing/stale and last_heartbeat_at is recent. If it is down, ask before desktop_start (billable), then re-poll desktop_status until the heartbeat advances.
  3. Auto-stop. CLI status prints nextAutoStop (weekday 23:00 America/Toronto). If the run could cross it, tell the user and stop unless they accept. desktop_keepawake blocks idle autosleep only; it does not override the 23:00 stop.
  4. Build + record. Write the task to a file, then:
    • CLI build --prompt-file task.txt [--model sonnet] → JSON with runId, steps[], poll, stop, promptSha256.
    • CLI record start --run <runId> --desktop "<ref>" --desktop-status-file status.json --task "<one-line summary>" — registers the agent through ruflo's agent_spawn (with config.host) and claims ruos-run-<runId> via claims_claim. Before launching, call llm_route_get. Stop if the desktop has no route. If the gateway is "unconfigured" but the route is "shared", warn and continue.
  5. Launch. Call desktop_exec with each steps[i] in order (machine = the desktop's fly_machine_id). The last step prints RUOS<nonce>_SHA:<hash> — it must equal promptSha256, else desktop_exec the stop string and abort. RUOS<nonce>_NO_RUNNER means claude is not installed there.
  6. Stream. Call desktop_exec with poll (rebuild with CLI build --run <runId> --nonce <nonce> --offset <n> ... as the offset grows, or use CLI run for automatic polling). Output is RUOS<nonce>_POLL:<exit|->:<size>:<alive 0|1>:<base64>; pass the base64 to CLI record output --run <runId> --b64 <b64> and show the decoded text. Back off 1s→5s between empty polls — each poll is audited on ruOS and serialises behind the desktop's run lock.
  7. Finish. When exit is not - and all bytes are read: CLI record end --run <runId> --exit <code> (agent → idle, claim released). On failure, check desktop_status: a stopped desktop means it was auto-stopped mid-run.
  8. Stop early only on the user's request: desktop_exec the stop string.

For unattended runs from a terminal, CLI run --desktop "<ref>" --prompt-file task.txt does steps 1–7 itself (needs RUOS_MCP_URL + RUOS_MCP_TOKEN, or --transport ssh with RUOS_SSH_KEY when ruflo runs on a same-tenant ruOS desktop).

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Adding newly available router models to chat-ui
  • Writing concise descriptions of model capabilities
  • Updating production and development model entries together
ruvnet/ruflo7.7만2026년 10월 18일 업데이트

Create an Architecture Decision Record, a document for recording important design choices, with the next sequential number. It generates a Markdown template, registers the record in AgentDB, and links related decisions found through search.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Record the reasoning behind adopting a technology
  • Start an ADR for an API or data model change
  • Document an infrastructure decision
ruvnet/ruflo7.7만2026년 10월 18일 업데이트

adr-index

무료

Build a searchable index and relationship graph from ADRs, records of architectural decisions. Import two supported document formats, refresh existing metadata without duplicate relationships, and review summaries of statuses, missing references, and inconsistencies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Index ADRs imported from another project
  • Refresh a graph that differs from files on disk
  • Set up ADR tracking in an existing codebase
ruvnet/ruflo7.7만2026년 10월 18일 업데이트

Rebuild the index of ADRs, records of architectural decisions, after files or relationship lines are deleted. It clears stored records and relationships, indexes the files still present, and checks that the final record count matches.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Rebuild the index after deleting an ADR file
  • Remove stale relationships after editing an ADR
  • Reconcile the ADR index on a schedule
ruvnet/ruflo7.7만2026년 10월 18일 업데이트

Review code changes against accepted Architecture Decision Records, documents that capture agreed design choices. Report violations, outdated references, compliant changes, and areas without ADR coverage, then suggest code fixes or a new decision record where appropriate.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Check a pull request before merging
  • Review major code changes against agreed design decisions
  • Find references to superseded ADRs
ruvnet/ruflo7.7만2026년 10월 18일 업데이트

Check saved architecture decision records (ADRs) for broken references, circular replacement relationships, and inconsistent statuses. Use the results to verify imported records or stop a CI check when selected integrity rules fail.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Checking ADR integrity after import
  • Blocking CI when ADR issues are found
  • Reviewing ADR data before a release
ruvnet/ruflo7.7만2026년 10월 18일 업데이트

ruvnet의 스킬 모두 보기

이 스킬의 문제 신고