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/ttttmr/pi-tmux-task/old-skillnpx skills add ttttmr/pi-tmux-task --skill old-skillgit clone --depth 1 https://github.com/ttttmr/pi-tmux-taskWrote 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/ttttmr/pi-tmux-task/old-skill)<a href="https://agentmods.dev/skills/ttttmr/pi-tmux-task/old-skill"><img src="https://agentmods.dev/badge/skills/ttttmr/pi-tmux-task/old-skill.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 | $0.00062 | $0.01194 |
| Opus 5 | $0.00031 | $0.00597 |
| Sonnet 5 | $0.00012 | $0.00239 |
| Haiku 4.5 | $0.00006 | $0.00119 |
Grade A, and why
tmux-task-manager 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 6d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tmux Task Manager
Use this skill for any project task that should not block the main line of work.
Typical cases:
- dev servers
- backend services
- watch mode commands
- log tailing / observation
- long scans or crawls
- polling / monitoring loops
- delayed or scheduled shell tasks
- parallel subtasks you want to keep alive
Do not use tmux for short one-shot commands when you need the output immediately in the current turn.
Rules
- Reuse the shared project tmux session in
$PI_TMUX_SESSION. - If
$PI_TMUX_SESSIONis missing, compute it with./tmux-session-name.sh. - Use one tmux window per logical task.
- Give each task a short, descriptive window name.
- Preferred names:
web,api,worker,logs,watch,scan,tests,build. - Avoid long names, timestamps, random suffixes, and vague names like
taskormisc. - When rerunning the same task intentionally, replace the old same-name window.
- Once a window exists, prefer window id (
@12) for follow-up operations. - Notifications mention both id and name, e.g.
@12 (web).
Session bootstrap
Prefer the injected value from the extension:
if [[ -z "${PI_TMUX_SESSION:-}" ]]; then
PI_TMUX_SESSION="$(./tmux-session-name.sh)"
export PI_TMUX_SESSION
fi
Ensure the shared session exists:
tmux has-session -t "$PI_TMUX_SESSION" 2>/dev/null || \
tmux new-session -d -s "$PI_TMUX_SESSION" -n shell
Standard start / replace flow
TASK_NAME=web
EXISTING_WINDOW_ID="$({ tmux list-windows -t "$PI_TMUX_SESSION" -F '#{window_id}\t#{window_name}' || true; } \
| awk -F $'\t' -v name="$TASK_NAME" '$2==name { print $1; exit }')"
if [[ -n "$EXISTING_WINDOW_ID" ]]; then
tmux kill-window -t "$EXISTING_WINDOW_ID"
fi
tmux new-window -t "$PI_TMUX_SESSION" -n "$TASK_NAME" \
"bash -lc 'cd \"$PWD\" && npm run dev'"
WINDOW_ID="$({ tmux list-windows -t "$PI_TMUX_SESSION" -F '#{window_id}\t#{window_name}' || true; } \
| awk -F $'\t' -v name="$TASK_NAME" '$2==name { print $1; exit }')"
if [[ -n "$WINDOW_ID" ]]; then
tmux setw -t "$WINDOW_ID" remain-on-exit on
fi
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.
- 6d ago First seen · 137 lines · 62 tokens per session scan A 70ed02cdf34e
tmux-task-manager is a skill published in the GitHub repository ttttmr/pi-tmux-task (5 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 1,194 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.