Scripts AGENTS.md

A set of repository instructions for Windows automation scripts written in AutoHotkey v2, a scripting language for controlling windows, keyboards, and other desktop actions. It explains the project layout, documentation, testing, and validation rules.

In plain words
What is it for?
Use it when adding, changing, testing, formatting, or documenting AutoHotkey scripts and shared helpers in this Windows 10/11 project.
Why use it?
It gives coding agents a reliable source of project-specific rules and keeps related guidance files consistent. This helps prevent using the wrong AutoHotkey version or overlooking the repository’s checks and documentation.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/ven0m0/scripts/agents-md
Clone the repo
git clone --depth 1 https://github.com/Ven0m0/Scripts

Made for: Codex, OpenCode.

Per session 963 This file is loaded in full into every session.
When invoked 963 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00963 $0.00963
Opus 5 $0.00481 $0.00481
Sonnet 5 $0.00193 $0.00193
Haiku 4.5 $0.00096 $0.00096

Measured yesterday against content hash 6f200e734911, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Scripts AGENTS.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 yesterday.

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.

AGENTS.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Canonical AI guidance for this repository. CLAUDE.md must remain a symlink to this file.

Repository snapshot

  • Project: Windows gaming and utility automation scripts
  • Primary language: AutoHotkey v2, exclusively (ahk/, Lib/)
  • Platform: Windows 10/11 for runtime and meaningful validation
  • Canonical user docs: README.md, EXAMPLES.md, directory READMEs

How to use this guide

  • Treat this file as the detailed, shared source of truth for AI assistants.
  • Keep .github/copilot-instructions.md shorter and reference this file instead of duplicating large sections.
  • Keep guidance repo-specific; remove version counts, file counts, and other details that drift quickly.

Repository map

ahk/                    AutoHotkey v2 scripts
Lib/                    Shared v2 helpers (`AHK_Common`, `WindowManager`)
tests/                  Standalone test scripts
.claude/rules/          Language rulesets (AutoHotkey, PowerShell) auto-loaded as project context
.github/workflows/      CI definitions; `ahk-lint-format-compile.yml` is the main AHK validation workflow

Core rules

  1. AHK v2 only. Every .ahk file in this repo targets v2; no v1 command syntax anywhere.
  2. Reuse shared helpers before adding new logic. Check Lib/ first for initialization, fullscreen, and window behavior.
  3. Be careful with shared libraries. Changes in Lib/ can affect many scripts; inspect consumers before editing and test representative dependents.
  4. Respect Windows-oriented formatting rules.
    • .ahk, .ps1, .cmd, .bat: CRLF, UTF-8, 4 spaces
    • .md, .json, .yml, .yaml: LF
    • Follow .editorconfig and .gitattributes when they differ from editor defaults.
  5. Avoid hardcoded user-specific paths. Prefer A_ScriptDir, A_MyDocuments, %AppData%, and environment-aware logic.
  6. Preserve low-latency behavior. Gaming and automation scripts keep InitScript() or equivalent performance settings unless the task documents an explicit exception.
  7. Keep documentation synchronized by design. Put durable repo-wide rules here; keep shorter tool-entry docs concise and linked back here.

Read the full file on GitHub · 81 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. yesterday First seen · 81 lines · 963 tokens per session scan A 6f200e734911

Subscribe to this mod's changes

Scripts AGENTS.md is an instructions file published in the GitHub repository Ven0m0/Scripts (10 stars, last pushed 14d ago), licensed MIT. It adds 963 tokens to every session, about $0.0048 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.

Related

Other instructions, from other repositories