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.
npx agentmods add instructions/ven0m0/scripts/agents-mdgit clone --depth 1 https://github.com/Ven0m0/ScriptsWhat 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 | $0.00963 | $0.00963 |
| Opus 5 | $0.00481 | $0.00481 |
| Sonnet 5 | $0.00193 | $0.00193 |
| Haiku 4.5 | $0.00096 | $0.00096 |
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.
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.mdmust 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.mdshorter 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
- AHK v2 only. Every
.ahkfile in this repo targets v2; no v1 command syntax anywhere. - Reuse shared helpers before adding new logic. Check
Lib/first for initialization, fullscreen, and window behavior. - Be careful with shared libraries. Changes in
Lib/can affect many scripts; inspect consumers before editing and test representative dependents. - Respect Windows-oriented formatting rules.
.ahk,.ps1,.cmd,.bat: CRLF, UTF-8, 4 spaces.md,.json,.yml,.yaml: LF- Follow
.editorconfigand.gitattributeswhen they differ from editor defaults.
- Avoid hardcoded user-specific paths. Prefer
A_ScriptDir,A_MyDocuments,%AppData%, and environment-aware logic. - Preserve low-latency behavior. Gaming and automation scripts keep
InitScript()or equivalent performance settings unless the task documents an explicit exception. - Keep documentation synchronized by design. Put durable repo-wide rules here; keep shorter tool-entry docs concise and linked back here.
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.
- yesterday First seen · 81 lines · 963 tokens per session scan A 6f200e734911
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.
Other instructions, from other repositories
CapsLockX CLAUDE.md
Claude Code instructions for snolab/CapsLockX, covering capslockx – claude instructions, project overview, architecture, hotkey map (hold capslock or space as trigger) and build (macos).
CapsLockX AGENTS.md
AGENTS.md instructions for snolab/CapsLockX, covering capslockx – codex instructions, project overview, architecture, hotkey map (hold capslock or space as trigger) and build (macos).
aws-hpc-recipes AGENTS.md
AGENTS.md instructions for aws-samples/aws-hpc-recipes, covering aws hpc recipes, what this repository is, read this before you change anything, repository map and deep documentation.
aws-hpc-recipes CLAUDE.md
Claude Code instructions for aws-samples/aws-hpc-recipes, a project described as: Contains example recipes that demonstrate how to build HPC systems using AWS services and solutions.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).