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/sammcj/agentic-coding/tmux-clinpx skills add sammcj/agentic-coding --skill tmux-cligit clone --depth 1 https://github.com/sammcj/agentic-codingWhat 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 | $0.00912 |
| Opus 5 | $0.00024 | $0.00456 |
| Sonnet 5 | $0.00010 | $0.00182 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
tmux-cli 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tmux-cli
Instructions
- Use the
tmux-clicommand to communicate with other CLI Agents or Scripts in other tmux panes. Dotmux-cli --helpto see how to use it!- This command depends on installing the
claude-code-tools. If you get an error indicating that the command is not available, ask the user to install it using:uv tool install claude-code-tools. - When using tmux-cli to connect to remote machines you must run it outside the sandbox (the tmux socket is outside the sandbox's allowed paths, and the pane's
sshneeds the environment's SSH auth). A sandboxedcapturereturns empty. Allow-listtmux-clionce to avoid repeated approval prompts.
- This command depends on installing the
- When you are finished with all tasks that you need tmux-cli for clean up the session.
Remote SSH hosts (default pattern)
When you need to run more than one command on a remote host over SSH, do NOT issue repeated one-off ssh host 'cmd' calls - each re-authenticates and needs its own approval. Open ONE persistent session and drive it. This is the default for any multi-command remote work.
- Reuse an existing session rather than spawning a new one each task (windows accumulate otherwise): check
tmux-cli status/tmux-cli list_panes, reuse its pane if healthy, and onlytmux-cli launch "zsh"if none exists. Note the returned pane id. - Arm auto-cleanup on the pane BEFORE connecting, so nothing lingers if the task is abandoned:
- Idle timeout:
export TMOUT=1800in the launched zsh (self-exits after 30 min idle at a prompt). - Hard cap watchdog (zsh):
( sleep 5400 && tmux kill-session -t remote-cli-session ) &!- kills the whole session after 90 min regardless of activity. tmux-cli's remote session is namedremote-cli-sessionon the default socket, so rawtmuxcan target it.&!backgrounds and disowns so it survives the shell exiting.
- Idle timeout:
- Connect with keepalive so a dropped link tears itself down:
ssh -o ServerAliveInterval=60 -o ServerAliveCountMax=3 -o StrictHostKeyChecking=no user@host. - After connecting, set the same idle timeout on the remote shell (busybox
ashandbashboth honour it):export TMOUT=1800. - Run work with
send+wait_idle+capture. Only the pane'ssshuses the network / SSH auth; tmux-cli itself only talks to the local tmux socket. - Tear it down explicitly when done:
tmux-cli cleanupkills the managed session;tmux-cli kill --pane=<id>kills a single pane. Do not leave idle sessions behind - the timeouts above are a backstop, not a substitute for cleanup.
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 · 55 lines · 48 tokens per session scan A c07f78ce899f
tmux-cli is a skill published in the GitHub repository sammcj/agentic-coding (158 stars, last pushed 8d ago), licensed Apache-2.0. It adds 48 tokens to every session and 912 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
ilya-sutskever
Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na OpenAI, superinteligência segura.
yann-lecun
Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018.
shopify-apps
Expert patterns for Shopify app development including Remix/React Router apps, embedded apps with App Bridge, webhook handling, GraphQL Admin API, Polaris components, billing, and app extensions.
yann-lecun-debate
Sub-skill de debates e posições de Yann LeCun. Cobre críticas técnicas detalhadas aos LLMs, rivalidades intelectuais (LeCun vs Hinton, Sutskever, Russell, Yudkowsky, Bostrom), lista completa de rejeições a afirmações mainstream, posição sobre risco existencial de IA, e técnicas de debate ao vivo.
context-guardian
Guardiao de contexto que preserva dados criticos antes da compactacao automatica. Snapshots, verificacao de integridade e zero perda de informacao.
llm-structured-output
Get reliable JSON, enums, and typed objects from LLMs using responseformat, tooluse, and schema-constrained decoding across OpenAI, Anthropic, and Google APIs.