Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/team-commonly/commonly/tmuxnpx skills add Team-Commonly/commonly --skill tmuxgit clone --depth 1 https://github.com/Team-Commonly/commonlyWhat 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 | $0.00048 | $0.00529 |
| Opus 5 | $0.00024 | $0.00264 |
| Sonnet 5 | $0.00010 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
tmux 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 2d 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.
What it actually says
tmux — long-running session management
tmux is on PATH in the gateway. Sessions persist across tool-call
boundaries within the same agent's lifetime, so you can fire off a long task
and come back to it on the next heartbeat.
Start a detached session
# Run a long command in a fresh detached session named "build"
tmux new-session -d -s build "npm run build > /tmp/build.log 2>&1"
Check on a session
# List sessions
tmux list-sessions
# Capture the current pane's visible output
tmux capture-pane -t build -p | tail -40
# Capture the full scrollback (last 1000 lines)
tmux capture-pane -t build -p -S -1000
Send input to a session
# Send a command (note: end with C-m for Enter)
tmux send-keys -t build "echo done > /tmp/done.flag" C-m
End a session
tmux kill-session -t build
Common patterns
Long-running build with status flag
tmux new-session -d -s build "
npm run build > /tmp/build.log 2>&1
echo \$? > /tmp/build.exit
"
# Later (next heartbeat):
if [ -f /tmp/build.exit ]; then
EXIT=\$(cat /tmp/build.exit)
echo "Build finished with exit code \$EXIT"
tail -20 /tmp/build.log
else
echo "Build still running..."
fi
Tail a log without blocking
tmux new-session -d -s logs "kubectl logs -f -n commonly-dev deploy/backend > /tmp/backend.log"
# Read on demand:
tail -50 /tmp/backend.log
When NOT to use tmux
- For one-shot commands → run them directly with
acpx_runor shell. - For tasks that need to outlive the agent's gateway pod → use a different mechanism (cron, scheduled job, etc.).
- For interactive workflows → tmux works but can't take human input from inside an agent.
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.
- 2d ago First seen · 80 lines · 48 tokens per session scan A 8b3e2743cb94
tmux is a skill published in the GitHub repository Team-Commonly/commonly (1,323 stars, last pushed 3d ago), licensed Apache-2.0. It adds 48 tokens to every session and 529 once invoked, about $0.0002 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
review-agents-md
Audit Dograh AGENTS.md files for drift against the live repo and for bad scope boundaries between parent and child docs. Use when the user asks to review existing AGENTS files, identify stale guidance, decide whether a subtree needs its own AGENTS.md, or update the AGENTS.md hierarchy under the repo root, api/, or ui/.
review-pr
Review a Dograh pull request, branch diff, or pasted patch for repo-specific security and correctness risks that are not obvious from generic FastAPI, Next.js, or Python conventions. Use when the user asks to review a PR, audit a diff, check whether changes are safe to merge, review their own changes, or asks what to…
merge-pipecat-upstream
Merge the latest upstream pipecat-ai/pipecat tag into the pipecat submodule fork (dograh-hq/pipecat) and bump the dograh repo to it. Use whenever the user asks to bump, upgrade, sync, or merge pipecat, resolve pipecat merge conflicts, audit whether upstream changes break or supersede Dograh's in-fork patches, or…
experiment-tracking-swanlab
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.
review-polish
The before-review and before-handoff pass for RomM, covering both stacks. First shapes the code the checks can't see — comment and docstring discipline (the single most-corrected thing in this repo), duplicated constants/types/getters, imprecise names, loose typing in tests. Then runs the verification gate that keeps…
frontend-v2-components
Building or modifying components in the RomM v2 frontend (frontend/src/v2/). Use when creating/editing v2 primitives (R components in src/v2/lib/), shared composites, or feature composites — covers the three-tier model, file/folder conventions, SFC structure, import order, barrels, Storybook requirements, and v2…