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.
curl -O https://raw.githubusercontent.com/stevenAthompson/self-command/master/GEMINI.mdgit clone --depth 1 https://github.com/stevenAthompson/self-commandWrote 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/instructions/stevenathompson/self-command/gemini-md)<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.
<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>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 | $0.01526 | $0.01526 |
| Opus 5.5 | $0.00610 | $0.00610 |
| Sonnet 5.5 | $0.00305 | $0.00305 |
| Haiku 4.5 | $0.00153 | $0.00153 |
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.
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.
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.
- 2mo ago First seen · 233 lines · 1,526 tokens per session scan A af62ba04807a
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.
self-command GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| self-command GEMINI.mdstevenAthompson/self-command | Instructions file | 29 | 7mo ago | MIT | A | 1,526 | Gemini CLI |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |