Borrowing it
Nothing to install: this file belongs to QiuwenZheng/interminal. 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/QiuwenZheng/interminal/main/.agents/skills/zellij/SKILL.mdgit clone --depth 1 https://github.com/QiuwenZheng/interminalWrote 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/qiuwenzheng/interminal/zellij)<a href="https://agentmods.dev/skills/qiuwenzheng/interminal/zellij"><img src="https://agentmods.dev/badge/skills/qiuwenzheng/interminal/zellij/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/skills/qiuwenzheng/interminal/zellij"><img src="https://agentmods.dev/badge/skills/qiuwenzheng/interminal/zellij.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 | $0.00028 | $0.00646 |
| Opus 5 | $0.00014 | $0.00323 |
| Sonnet 5 | $0.00006 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
zellij 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 11d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zellij: Persistent Terminal Workflows
When executing terminal commands via an MCP or a stateless runner, each execute call runs in an isolated channel. State (like cd /path, export VAR=1, or active virtual environments) does not persist to the next call.
To solve this, use Zellij, a terminal multiplexer. By starting a Zellij daemon, you can maintain persistent state and drive it programmatically via its CLI (zellij action).
1. Starting a Session
Do NOT try to background the TUI with & (e.g., zellij &). It will crash during TTY initialization. Instead, start it in the foreground and let the execution timeout (or return a "partial" status). The daemon will fork safely.
# Start a named session (requires TERM to be set)
execute("TERM=xterm-256color zellij --session mysession", total_timeout=4)
Note: Ignore or abandon the partial channel returned. The daemon survives in the background.
2. Driving the Session via CLI
Once the session is running, you can interact with it completely statelessly using zellij action. You can chain these with && for efficiency.
Typing and Running Commands
Use write-chars to type text into the active pane, followed by send-keys Enter to execute it. This is superior to new-pane -- cmd because it preserves shell built-ins, pipes, and variables.
execute("zellij -s mysession action write-chars 'cd /var/log && ls -la' && zellij -s mysession action send-keys Enter")
Reading Output
Do not use raw channel output (which contains messy ANSI/TUI drawing characters). Instead, ask Zellij to dump the clean screen content:
# Dump the current viewport
execute("zellij -s mysession action dump-screen")
# Dump with scrollback history
execute("zellij -s mysession action dump-screen --full")
3. Advanced Window Management
You can manipulate panes and tabs programmatically.
# Open a new pane or tab
execute("zellij -s mysession action new-pane")
execute("zellij -s mysession action new-tab")
# List panes/tabs (Useful for finding IDs)
execute("zellij -s mysession action list-panes")
execute("zellij -s mysession action list-tabs")
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.
- 11d ago First seen · 70 lines · 28 tokens per session scan A 52a745bca46c
zellij is a skill published in the GitHub repository QiuwenZheng/interminal (3 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 646 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 2026-08-31.
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…
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.