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 skills add tim0-12432/HotkeylessAHK-mcp-skill --skill hotkeyless-ahk-invokegit clone --depth 1 https://github.com/tim0-12432/HotkeylessAHK-mcp-skillWrote 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/skills/tim0-12432/hotkeylessahk-mcp-skill/hotkeyless-ahk-invoke)<a href="https://agentmods.dev/skills/tim0-12432/hotkeylessahk-mcp-skill/hotkeyless-ahk-invoke"><img src="https://agentmods.dev/badge/skills/tim0-12432/hotkeylessahk-mcp-skill/hotkeyless-ahk-invoke/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/skills/tim0-12432/hotkeylessahk-mcp-skill/hotkeyless-ahk-invoke"><img src="https://agentmods.dev/badge/skills/tim0-12432/hotkeylessahk-mcp-skill/hotkeyless-ahk-invoke.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 | $0.00069 | $0.00551 |
| Opus 5 | $0.00034 | $0.00275 |
| Sonnet 5 | $0.00014 | $0.00110 |
| Haiku 4.5 | $0.00007 | $0.00055 |
Grade A, and why
hotkeyless-ahk-invoke scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:42800/list How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hotkeyless AHK – Invoke Commands
Send commands to the Hotkeyless AHK HTTP server to control the user's desktop.
Prerequisites
You must know the available commands before invoking anything. If you haven't already, use the hotkeyless-ahk-discovering skill first:
curl -s http://localhost:42800/list
Only invoke commands that appear in the /list response.
Invoking a command
Without parameters
curl -s http://localhost:42800/send/<command>
Example:
curl -s http://localhost:42800/send/OpenBrowser
With parameters
Pass parameters as query string values separated by ?:
curl -s http://localhost:42800/send/<command>?param1?param2
Example:
curl -s http://localhost:42800/send/MoveMouse?500?300
Note: Parameters are separated by
?, not&. This is specific to Hotkeyless AHK.
Response handling
| Response | Meaning | Action |
|---|---|---|
success |
Command was forwarded to AHK | Confirm to user |
failure |
No AHK subscriber or command not found | Check if AHK script is running |
If you receive failure:
- Tell the user the AHK subscriber may not be running
- Suggest they check that the Hotkeyless AHK AutoHotkey script is active
- Do not retry more than once
Configuration
- Default URL:
http://localhost:42800 - The user may specify a different host or port
Rules
- Never guess command names. Only use commands from
/list. - Never invoke
killunless the user explicitly asks to shut down the Hotkeyless AHK server. - Ask before bulk actions. If a task requires more than 5 sequential commands (e.g. gameplay automation), confirm the plan with the user first.
- No feedback loop. You cannot see the screen. If you need visual confirmation of results, tell the user or suggest a screenshot MCP 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.
- 11d ago First seen · 74 lines · 69 tokens per session scan A 5e1c3ebc33ba
hotkeyless-ahk-invoke is a skill published in the GitHub repository tim0-12432/HotkeylessAHK-mcp-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 551 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hevy-cli
Manage Hevy workouts from the terminal: read and summarize training data, search exercise templates, and create or update workouts, routines, exercises, folders, or body measurements.
help-flow
Help about Rosetta: explains capabilities and usage.
external-lib-flow
Workflow for onboarding an external private library so AI can use it without source access.
memora
Use when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.
coding-flow
Light coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.
adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.