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 commands/raine/workmux/last-donegit clone --depth 1 https://github.com/raine/workmuxWrote 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/raine/workmux/last-done)<a href="https://agentmods.dev/commands/raine/workmux/last-done"><img src="https://agentmods.dev/badge/commands/raine/workmux/last-done.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.00318 |
| Opus 5 | $0.00005 | $0.00159 |
| Sonnet 5 | $0.00002 | $0.00064 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
last-done 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 4d 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
Switches to the agent that most recently completed its task or is waiting for user input. Repeated invocations cycle through all done/waiting agents in reverse chronological order (most recent first). The cycle resets when a new agent finishes, so you always see the latest first.
This is a hidden command (not shown in --help), typically invoked via a tmux keybinding.
workmux last-done
How it works
- Finds all agents with "done" or "waiting" status.
- Sorts them by most recent status change first.
- Switches to the most recent one.
- On repeated invocations, advances to the next oldest agent in the list.
- When a new agent finishes (the most recent timestamp changes), the cycle resets back to the newest.
Tmux keybinding
Add to ~/.tmux.conf for quick access:
bind l run-shell "workmux last-done"
Then press prefix + l to jump to the last completed or waiting agent. Press again to cycle to the next oldest.
Examples
# Jump to the most recently completed/waiting agent
workmux last-done
# Press again to cycle to the next oldest
workmux last-done
Related
- Status tracking explains how agent status is detected and displayed
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.
- 4d ago First seen · 45 lines · 9 tokens per session scan A 8da52122e298
last-done is a command published in the GitHub repository raine/workmux (2,365 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 318 once invoked, about $0.0000 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.