self-command: Instructions file for Gemini CLI

GEMINI.md

self-command GEMINI.md is an instructions file for Gemini CLI from stevenAthompson/self-command. It costs 1,526 tokens per session, scanned A, original, MIT.

Instructions for a Gemini CLI extension that lets the agent control its interface through tmux, a terminal multiplexer. It covers sending commands, waiting for tasks, and watching log files.

In plain words
What is it for?
Sending Gemini CLI commands, waiting for scheduled wake-ups, monitoring files, and managing the agent's terminal workspace.
Why use it?
It gives the agent a defined way to operate Gemini CLI and monitor longer-running work from the terminal.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions Gemini CLI.

This is stevenAthompson/self-command's own configuration. It tells Gemini CLI how to work on self-command itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything self-command configures →

Reuse

Borrowing it

Nothing to install: this file belongs to stevenAthompson/self-command. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/stevenAthompson/self-command/master/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/stevenAthompson/self-command

Made for: Gemini CLI.

Wrote 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.

agentmods badge for self-command GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/stevenathompson/self-command/gemini-md/github.svg)](https://agentmods.dev/instructions/stevenathompson/self-command/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/stevenathompson/self-command/gemini-md"><img src="https://agentmods.dev/badge/instructions/stevenathompson/self-command/gemini-md/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.

agentmods 80×15 button for self-command GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/stevenathompson/self-command/gemini-md"><img src="https://agentmods.dev/badge/instructions/stevenathompson/self-command/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,526 This file is loaded in full into every session.
When invoked 1,526 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01526 $0.01526
Opus 5.5 $0.00610 $0.00610
Sonnet 5.5 $0.00305 $0.00305
Haiku 4.5 $0.00153 $0.00153

Measured 2mo ago against content hash af62ba04807a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

self-command GEMINI.md 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 2mo 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.

GEMINI.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self Command Extension

This extension provides tools that allow the Gemini CLI agent to control its own interface via tmux, wait for tasks, monitor files, and manage the workspace.

Tools

1. self_command

Executes a Gemini CLI command programmatically.

Usage

Use this tool when you need to execute a Gemini CLI command, such as running a specific /command, listing files, or triggering other agent actions.

Tool Signature

self_command({
  command: string; // The command to send to Gemini (e.g., "/compress", "/help").
});

Response Returns a text message confirming the task has started, including a unique Request ID (e.g., [A1B2]). This ID will also appear in the completion notification.

Example

// To ask for help
self_command({ command: "/help" });

CRITICAL INSTRUCTION You MUST yield your turn immediately after calling this tool. Do not attempt to perform other actions.


2. gemini_sleep

Sleeps for a specified duration and then sends a wake-up notification.

Usage

Use this tool to pause execution while waiting for a task that you know will take a specific amount of time.

Single Active Sleep Policy: Only ONE sleep task can be active at a time. If you request a new sleep while one is already running, the system will choose the shorter duration:

  • If the new sleep ends sooner than the current one, the current sleep is cancelled and replaced by the new, shorter one.
  • If the new sleep ends later, the request is ignored, and the existing shorter sleep continues.

Recurring Sleep: You can set recurring: true to be woken up periodically (e.g., for monitoring).

  • Constraint: Recurring sleep requires a minimum interval of 3600 seconds (1 hour).

Tool Signature

gemini_sleep({
  seconds: number; // Number of seconds to sleep (or interval if recurring).
  recurring?: boolean; // Optional: If true, wakes repeatedly. Min 3600s.
});

CRITICAL INSTRUCTION You MUST yield your turn immediately after calling this tool.

Read the full file on GitHub · 233 lines

Changes

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.

  1. 2mo ago First seen · 233 lines · 1,526 tokens per session scan A af62ba04807a

Subscribe to this mod's changes

self-command GEMINI.md is an instructions file published in the GitHub repository stevenAthompson/self-command (29 stars, last pushed 7mo ago), licensed MIT. It adds 1,526 tokens to every session, about $0.0061 per session on Opus 5.5. 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.

Related

self-command GEMINI.md compared with instructions from other repositories

self-command GEMINI.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
self-command GEMINI.mdstevenAthompson/self-commandInstructions file297mo agoMITA1,526Gemini CLI
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode