Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/saski/arnestonpx agentmods add commands/saski/arnesto/install-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/commands/saski/arnesto/install-command)<a href="https://agentmods.dev/commands/saski/arnesto/install-command"><img src="https://agentmods.dev/badge/commands/saski/arnesto/install-command/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/commands/saski/arnesto/install-command"><img src="https://agentmods.dev/badge/commands/saski/arnesto/install-command.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 | $0.00000 | $0.05270 |
| Opus 5.5 | $0.00000 | $0.02108 |
| Sonnet 5.5 | $0.00000 | $0.01054 |
| Haiku 4.5 | $0.00000 | $0.00527 |
Grade A, and why
install-command 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 1mo 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 — 757 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install Command
Command: /install-command [template-name]
Installs and customizes command templates for your specific repository. Run without arguments to see available templates.
What This Command Does
This command helps you adapt generic command templates to your specific repository:
- Lists available templates (if no template specified)
- Asks customization questions about your repo
- Generates a customized version with repo-specific details
- Saves the command to your local
.cursor/commands/directory - Validates the installation and confirms it's ready to use
Usage
List Available Templates
Run without arguments to see what's available:
/install-command
This will scan /Users/[username]/work/cursor-prompts/templates/ and show:
- Template name
- Description
- What it does
- Prerequisites
Install a Specific Template
/install-command review-pr
Available Templates
The command will scan the templates directory and display available templates with their descriptions. Templates should include metadata at the top:
<!--
template-name: review-pr
description: Interactive PR review workflow with AI assistance
languages: all
requires: gh CLI, git
-->
Workflow Steps
When No Template Specified (List Mode)
1. Scan /Users/[username]/work/cursor-prompts/templates/
2. Read each .md file
3. Extract metadata or first description
4. Display formatted list:
=== Available Command Templates ===
📝 review-pr
Interactive PR review workflow with AI assistance
Features:
- Checkout and analyze PR changes
- Interactive walkthrough of all files
- Post comments via GitHub CLI
- Track review metrics
- Optional fix implementation
Prerequisites: gh CLI, git
Languages: All
Install: /install-command review-pr
[Additional templates listed here]
===================================
Which template would you like to install? [name or 'cancel']
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.
- 1mo ago First seen · 757 lines · 0 tokens per session scan A ff5712cf6d6f
install-command is a command published in the GitHub repository saski/arnesto (5 stars, last pushed yesterday), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 5,270 tokens. 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 commands, from other repositories
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
handoff
Export a Waybill Bundle by default, or import one when requested.
aitask-explore
Explore the codebase interactively, then create a task for implementation.
aitask-refresh-code-models
Research latest AI code agent models via web and update models.json configuration files.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.