tmux
Skill0 starsChanged 3 months agoMITView on GitHub
Control tmux panes for interactive CLIs: capture pane output and send keys/text. Targets the current window by default.
69 other projects use a version of this, 11 of them edited.
Adopted by
Most recently taken up by
- insight68/Skillstheir own version, first seen Nov 8, 2026
- QVerisAI/QVerisBottheir own version, first seen Nov 1, 2026
- jav-ed/skill_Managtheir own version, first seen Nov 1, 2026
- bks-lab/open-bridgetheir own version, first seen Nov 1, 2026
- gabrielkoerich/skillstheir own version, first seen Nov 1, 2026
- jellydn/my-ai-toolstheir own version, first seen Oct 18, 2026
Used with
Projects with it also use taskflow-inbox-triage, session-logs and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AtomicBot-aiSkilltaskflow-inbox-triage
Also in 6 projects that use this
seedprodSkillsession-logs
Search and analyze your own session logs (older/parent conversations) using jq.
Also in 20 projects that use this
seedprodSkillvoice-call
Start voice calls via the OpenClaw voice-call plugin.
Also in 18 projects that use this
AtomicBot-aiSkilltaskflow
Also in 7 projects that use this
jiulingyunSkillBlueBubbles
为Clawdbot构建或更新BlueBubbles外部通道插件(扩展包,REST发送/探测,webhook入站)。
Also in 16 projects that use this
hkyutongSkillopenclaw-release-maintainer
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
Also in 4 projects that use this
- +5 more from seedprod
Other versions69 projects use a version of this.
Word for word · 0
None found.
Edited · 11
- moltbot/clawdbot★ 394k17% same
- steipete/warelay★ 394k17% same
- steipete/clawdis★ 394k17% same
- moltbot/moltbot★ 394k17% same
- clawdbot/clawdbot★ 394k17% same
- openclaw/openclaw★ 394k17% same
- molt-bot/clawdbot★ 391k17% same
- OpenBMB/PilotDeck★ 5k14% same
- friuns2/openclaw-android-assistant★ 57317% same
- OpenClawAndroid/openclaw-android-assistant★ 55617% same
1 more not listed
Wrote their own version · 58
- spinabot/brigade★ 11ksame name
- the-open-agent/openagent★ 5.7ksame name
- casibase/casibase★ 5.7ksame name
- linuxhsj/openclaw-zero-token★ 5.2ksame name
- mitsuhiko/agent-commands★ 3.2ksame name
- mitsuhiko/agent-stuff★ 3.2ksame name
- Bitterbot-AI/bitterbot-desktop★ 2.5ksame name
- higress-group/himarket★ 1.3ksame name
- OpenBMB/EdgeClaw★ 1.2ksame name
- understudy-ai/understudy★ 461same name
48 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- build-justfileSkill
- c4-sequenceSkill
- create-issueSkill
- create-prSkill
- create-repoSkill
- dadsSkill
- handoverSkill
- mouse-doctorSkill
- oss-bus-factorSkill
- ponytail-reviewSkill
- writing-documentsSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 64 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Use for existing interactive tmux sessions.
- Very specific: line 79
Use -l -- for arbitrary literal text.
“Common” is measured: kept by at least 6 in 10 of the 64 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
tmux
Use for existing interactive tmux sessions. For one-shot commands, use normal shell. For new non-interactive background jobs, use background execution.
Target
Target the window where this session runs — not the session's active window.
A bare relative target like .1 is a trap. tmux fills the omitted window with the session's current (active) window — whatever window the attached client is showing — which is usually NOT the window Claude runs in. $TMUX_PANE only fixes the session, never the window. So .1 silently drifts to another window's pane 1 whenever the user is looking elsewhere.
Anchor to Claude's own pane instead. $TMUX_PANE is set in this session's env; resolve it to a session:window prefix and build an absolute target:
W=$(tmux display-message -p -t "$TMUX_PANE" '#{session_name}:#{window_index}')
# then target panes as "$W.1", "$W.2", ...Each Bash call is a fresh shell, so set W in the same command block where you use it.
To reach a different window or session on purpose, use an explicit session:window.pane, e.g. shared:0.0.
List the panes in Claude's window:
W=$(tmux display-message -p -t "$TMUX_PANE" '#{session_name}:#{window_index}')
tmux list-panes -t "$W"See
W=$(tmux display-message -p -t "$TMUX_PANE" '#{session_name}:#{window_index}')
tmux capture-pane -t "$W.1" -p # current screen
tmux capture-pane -t "$W.1" -p -S - # full scrollback
tmux capture-pane -t "$W.1" -p | tail -20-p prints to stdout. -S - includes scrollback (bounded by history-limit). Full-screen apps (vim, less) show only the current screen, not past output.
Send
Send literal text and Enter separately, to avoid paste/newline surprises:
W=$(tmux display-message -p -t "$TMUX_PANE" '#{session_name}:#{window_index}')
tmux send-keys -t "$W.1" -l -- "Please continue"
tmux send-keys -t "$W.1" EnterSpecial keys (set W first, as above):
tmux send-keys -t "$W.1" C-c
tmux send-keys -t "$W.1" C-d
tmux send-keys -t "$W.1" EscapeUse -l -- for arbitrary literal text. Approve or select a prompt only after reading it:
W=$(tmux display-message -p -t "$TMUX_PANE" '#{session_name}:#{window_index}')
tmux capture-pane -t "$W.1" -p | tail -20 # read first
tmux send-keys -t "$W.1" -l -- "y"
tmux send-keys -t "$W.1" EnterNotes
- Target format is
session:window.pane. A bare.paneresolves the omitted window to the session's active window, NOT to$TMUX_PANE's window — so it drifts. Always anchor withW=$(tmux display-message -p -t "$TMUX_PANE" '#{session_name}:#{window_index}')and target"$W.pane". capture-pane -pprints to stdout.-S -captures full scrollback.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

