Borrowing it
Nothing to install: this file belongs to mindroom-ai/mindroom. 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/mindroom-ai/mindroom/main/.claude/skills/agent-cli-tmux-supervision/SKILL.mdgit clone --depth 1 https://github.com/mindroom-ai/mindroomWrote 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/mindroom-ai/mindroom/agent-cli-tmux-supervision)<a href="https://agentmods.dev/skills/mindroom-ai/mindroom/agent-cli-tmux-supervision"><img src="https://agentmods.dev/badge/skills/mindroom-ai/mindroom/agent-cli-tmux-supervision.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.01622 |
| Opus 5 | $0.00030 | $0.00811 |
| Sonnet 5 | $0.00012 | $0.00324 |
| Haiku 4.5 | $0.00006 | $0.00162 |
Grade A, and why
agent-cli-tmux-supervision 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 9d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent CLI + tmux Supervision
Use this skill when you are supervising parallel Codex branches launched with agent-cli dev new ... --tmux-session ....
This is not just a launch guide. It is the full supervision protocol for getting from spawned worktree to reviewed PR without letting agents stop early.
When to use
Use this skill when:
- multiple Codex agents are working in separate
agent-cliworktrees - each branch needs active tmux supervision instead of fire-and-forget delegation
- you need repeated review loops before considering a PR done
- you need to prove that review fixes are pushed, not just described
Do not use this skill when:
- there is only one local branch and no tmux-supervised sub-agents
- the work is small enough to complete directly in the current session
Core launch pattern
Launch each branch with an explicit base, Codex as the agent, a dedicated tmux session, and a prompt file.
agent-cli dev new <branch-name> \
--from origin/main \
--agent codex \
--tmux-session <session-name> \
--prompt-file <prompt-file>
Use a feature branch as --from only when the prompt explicitly depends on unmerged branch work.
What the agent actually reads
The original prompt file path does not have to exist inside the spawned worktree.
agent-cli copies the prompt into the worktree as .claude/TASK-*.md.
When telling an agent to reread its instructions, always point it at the local .claude/TASK-*.md file, not the original prompt path from the main repo.
Known environment caveat
If uv sync --all-extras fails during setup but the tmux session still launches, treat that as a setup caveat, not an automatic launch failure.
In this repo, a known example is python-olm failing to build while Codex still starts successfully in tmux.
Sending messages reliably
Do not trust one combined tmux send-keys ... Enter command.
The reliable pattern is:
tmux send-keys -t <session> 'your message here'
tmux send-keys -t <session> Enter
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.
- 9d ago First seen · 228 lines · 61 tokens per session scan A 4bf60416c426
agent-cli-tmux-supervision is a skill published in the GitHub repository mindroom-ai/mindroom (267 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 1,622 once invoked, about $0.0003 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…