Borrowing it
Nothing to install: this file belongs to Mineru98/skills-store. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Mineru98/skills-store/main/.claude/skills/tmux-orchestrate/SKILL.mdgit clone --depth 1 https://github.com/Mineru98/skills-storeWrote 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/skills/mineru98/skills-store/tmux-orchestrate)<a href="https://agentmods.dev/skills/mineru98/skills-store/tmux-orchestrate"><img src="https://agentmods.dev/badge/skills/mineru98/skills-store/tmux-orchestrate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mineru98/skills-store/tmux-orchestrate"><img src="https://agentmods.dev/badge/skills/mineru98/skills-store/tmux-orchestrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00206 | $0.02782 |
| Opus 5 | $0.00103 | $0.01391 |
| Sonnet 5 | $0.00041 | $0.00556 |
| Haiku 4.5 | $0.00021 | $0.00278 |
Grade A, and why
tmux-orchestrate 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 12d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<step n="2" name="병렬 수집·요약">
pane 이 3개 미만이면 직접 `capture --lines 160` 을 돌려 읽는다.
3개 이상이면 pane 당 서브에이전트 1개를 <b>한 번에</b> 띄운다. 각 서브에이전트에게 준다.
- 실행할 명령: `node <스킬경로>/scripts/tmux-capture.mjs capture --scope all --target <paneId> --lines 160`
- 아래 <status-rules> 전문
- 반환 스키마: <pane-report>
tail 원문을 메인 컨텍스트로 끌어오지 않는다. 서브에이전트가 읽고 요약본만 돌려준다.
필요하면 서브에이전트가 `--lines 400` 으로 한 번 더 파고들 수 있다고 알려 준다.
</step>
<step n="3" name="교차 분석">
요약본을 모아 다음을 판정한다. 근거 없는 추측은 쓰지 않는다.
- 같은 파일·같은 브랜치를 두 세션이 만지고 있는가 (dirtyFiles 와 요약의 대상 파일로)
- 같은 일을 중복해서 하고 있는가
- WAIT 인 세션이 있는가 — 사람이 막고 있는 것이므로 항상 최우선
- ERROR 가 다른 세션의 전제를 깨는가
</step>
<step n="4" name="보고">
<output-format> 를 <b>글자 그대로</b> 지킨다. 섹션 순서·라벨·상태 토큰을 바꾸지 않는다.
매번 같은 모양이어야 훑어보는 비용이 0 에 수렴한다.
</step>
<step n="5" name="전파" optional="true">
사용자가 전파를 요청했거나, 4단계에서 충돌·중복을 발견해 알릴 필요가 있을 때만 간다.
1. 세션별 전송 문구를 <b>초안으로 먼저 보여주고</b> 승인받는다. 승인 없이 보내지 않는다.
2. `--dry-run` 으로 대상과 본문을 확인한다.
3. 승인되면 dry-run 을 뺀 같은 명령을 돌린다.
4. 결과 JSON 의 `sent` 를 확인해 실패한 pane 을 그대로 보고한다.
전 세션 동일 문구면 `broadcast`, 세션마다 다르면 `send` 를 세션 수만큼.
</step>
WAIT 사람 입력에서 멈춰 있다. 권한 승인 프롬프트, 선택지 목록(`❯ 1.`, `Do you want`),
질문으로 끝난 응답, 빈 입력창에 커서만 있고 직전이 질문인 경우.
WORK 지금 돌고 있다. 스피너·경과시간 표시(`✻`, `esc to interrupt`, `Running`),
도구 호출이 열린 채 끝남, 빌드·테스트 로그가 흐르는 중.
DONE 마지막 응답이 완료 보고이고 더 시킬 것이 없어 대기 중.
ERROR 실패로 끝났다. traceback, `error`/`failed`/`exit 1`, hook 차단, merge conflict.
IDLE 쉘 프롬프트만 있고 에이전트가 떠 있지 않다.
UNKNOWN 위 어디에도 확신이 안 선다. 억지로 배정하지 말고 이걸 쓴다.
판정 근거는 반드시 tail 에서 인용한 한 줄로 남긴다. 인용할 줄이 없으면 UNKNOWN 이다.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 168 lines · 206 tokens per session scan A fc2b36dbefa0
tmux-orchestrate is a skill published in the GitHub repository Mineru98/skills-store (13 stars, last pushed 14d ago), licensed MIT. It adds 206 tokens to every session and 2,782 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
stay-within-limits
Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.
crisis-holding
Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
agent-estate
Perpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains a persistent ledger across all sessions.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.