Borrowing it
Nothing to install: this file belongs to GGPrompts/TFE. 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/GGPrompts/TFE/main/.claude/commands/watch-tmux.mdgit clone --depth 1 https://github.com/GGPrompts/TFEWrote 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/ggprompts/tfe/watch-tmux)<a href="https://agentmods.dev/commands/ggprompts/tfe/watch-tmux"><img src="https://agentmods.dev/badge/commands/ggprompts/tfe/watch-tmux.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 5.1 | $0.00012 | $0.01427 |
| Opus 5 | $0.00006 | $0.00714 |
| Sonnet 5 | $0.00002 | $0.00285 |
| Haiku 4.5 | $0.00001 | $0.00143 |
Grade A, and why
watch-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 8d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch TFE in Tmux Session
You are monitoring TFE running in a tmux session, giving you visibility into the exact visual output the user sees.
Your Task
Use Desktop Commander's execute_command tool to monitor a tmux session running TFE.
Step 1: Identify the Session
Ask the user:
- "What's your tmux session name?" (e.g., "tfe-dev", "0", "main")
- Or detect automatically with:
tmux list-sessions
Step 2: Verify and Identify the Pane
# List all sessions
tmux list-sessions
# List windows in the session
tmux list-windows -t SESSION_NAME
# List panes in a window
tmux list-panes -t SESSION_NAME:0
# Get pane details
tmux display-message -t SESSION_NAME -p '#{session_name}:#{window_index}.#{pane_index}'
Step 3: Capture Initial State
# Capture last 100 lines from the pane
tmux capture-pane -t SESSION_NAME -p -S -100
# For specific window/pane:
tmux capture-pane -t SESSION_NAME:WINDOW.PANE -p -S -100
Parse the output for:
- Current directory TFE is browsing
- Files visible in the list
- Preview content (if in preview mode)
- Any error messages or panics
- Bubbletea rendering artifacts
- Current display mode (list/grid/detail/tree)
Step 4: Continuous Monitoring
Every 15-20 seconds (or when user asks), capture fresh output:
# Get latest 50 lines
tmux capture-pane -t SESSION_NAME -p -S -50
# Compare with previous capture
# Alert on changes:
# - New errors appeared
# - TFE crashed (pane shows shell prompt)
# - Directory changed
# - Different file selected
Step 5: Parse TFE's TUI Output
Look for:
- Title bar: Shows current path
- File list: What files are visible
- Status bar: Current mode, file count
- Preview pane: What file content is shown
- Error indicators:
- Go panic stack traces
- "panic: runtime error"
- "fatal error:"
- Bubbletea crash messages
Example parsing:
Top line: /home/matt/projects/TFE
File list: Contains "main.go", "types.go", etc.
Preview: Showing README.md content
Status: Detail mode, 15 files
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.
- 8d ago First seen · 217 lines · 12 tokens per session scan A 204f7ab6b72d
watch-tmux is a command published in the GitHub repository GGPrompts/TFE (20 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 1,427 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
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.