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.
git clone --depth 1 https://github.com/sfc-gh-eraigosa/dotfilesWrote 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/commands/sfc-gh-eraigosa/dotfiles/tmux-agent)<a href="https://agentmods.dev/commands/sfc-gh-eraigosa/dotfiles/tmux-agent"><img src="https://agentmods.dev/badge/commands/sfc-gh-eraigosa/dotfiles/tmux-agent/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/commands/sfc-gh-eraigosa/dotfiles/tmux-agent"><img src="https://agentmods.dev/badge/commands/sfc-gh-eraigosa/dotfiles/tmux-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00019 | $0.00297 |
| Opus 5 | $0.00010 | $0.00148 |
| Sonnet 5 | $0.00004 | $0.00059 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
tmux-agent 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.
What it actually says
Delegate or inspect work running in isolated tmux-mgr agent sessions.
Currently running agents
!tmux-mgr agent list 2>/dev/null || echo "no agents running"
Arguments: $ARGUMENTS
Parse the arguments to decide intent:
start <name> <task description...>— spawn a new agent in an isolated git worktree:tmux-mgr agent start <name> --task-description "<task>"list— show all active agent sessions and their worktree paths.complete <session-id>— fan-in: readRESULT.mdfrom the agent's worktree and summarize.cleanup <session-id>— remove the worktree and tracking file (only after results are saved).capture <session-id>— inspect the live terminal of a running agent.
If the user gave a free-form task without a verb, default to start with an auto-generated name.
Per the tmux skill: prefer agent delegation for any task that is parallelizable, repository-isolated, or expected to take more than a few minutes. Sub-agents MUST write RESULT.md before being cleaned up.
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 · 26 lines · 19 tokens per session scan A 930fc16f99a0
tmux-agent is a command published in the GitHub repository sfc-gh-eraigosa/dotfiles (46 stars, last pushed today), licensed Apache-2.0. It adds 19 tokens to every session and 297 once invoked, about $0.0001 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 commands, from other repositories
commit
Follow the Commit messages rule in the repository AGENTS.md when present; otherwise use the Conventional Commits 1.0.0 summary below.
create-pr
Rebase from the latest origin/main, squash the commits from it, and then create a PR on github with intelligent commit messages based on staged changes. Invoke with /create-pr.
pr-review
Intelligent PR code review with dynamic agent allocation based on change types.
scan-commit
Automatically scan the repository for unstaged/untracked changes, group them into logical commits using hunk-level analysis, stage and commit them following Conventional Commits. Invoke with /scan-commit.
smart-commit
Analyze staged changes and split them into multiple logical commits following Conventional Commits. Invoke with /smart-commit.
gen-commit-msg
Generate intelligent commit messages based on staged changes. Invoke with /gen-commit-msg.