A procedure for sending a message to the imp3 chat, a live public chat room built into an Amiga music player, through a local computer-control interface.

Use it to find the correct Amiga, confirm that imp3 is running, and post a requested message to the public chat.

It reduces mistakes when choosing a machine, controlling the chat window, or posting from multiple machines that share one identity.

How thomas-luebker/amimcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to thomas-luebker/amimcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/thomas-luebker/amimcp/master/.claude/skills/imp3-post/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/thomas-luebker/amimcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/thomas-luebker/amimcp/imp3-post/github.svg)](https://agentmods.dev/skills/thomas-luebker/amimcp/imp3-post)

Your own site

<a href="https://agentmods.dev/skills/thomas-luebker/amimcp/imp3-post"><img src="https://agentmods.dev/badge/skills/thomas-luebker/amimcp/imp3-post/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/thomas-luebker/amimcp/imp3-post"><img src="https://agentmods.dev/badge/skills/thomas-luebker/amimcp/imp3-post.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,189 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.01189
Opus 5.5	$0.00025	$0.00476
Sonnet 5.5	$0.00012	$0.00238
Haiku 4.5	$0.00006	$0.00119

Measured 1mo ago against content hash b5c493b0d0bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

imp3-post 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.

The scan reads SKILL.md. This mod also ships 1 executable file (post_to_imp3.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/imp3-post/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Posting to the imp3 chat

imp3 is "Infinity Music Player v3.472 by Juen" — an MP3 player with a built-in community chat used by the Amiga scene (yelworC, juen, FTA, djbase, konsolendoc and ~40 others). Posting into it means typing into a live public room full of real people. Everything below exists to keep that from going wrong.

You do not need impsend for this. amiagent 0.11.0+ opens a local ARexx port called AMIAGENT whose ACTIVATEWINDOW / ENTERTEXT / KEY commands drive the chat window directly.

Before you start

Find a machine that has imp3 running. Not every fleet machine does, and the answer changes between sessions. A chat window is the proof:
```
wins = [l for l in a.ui_tree().split("\n") if l.startswith("W ")]
chat = [w for w in wins if "CHAT --" in w]
```
Status will not show imp3 — it is Workbench-started, so it has no CLI number. Only the window list tells you.
All fleet machines share one identity (S:imp3.reg), so they all connect as nick lokiist. Two clients online at once kick each other off. If imp3 is up on more than one machine, post from the one the user named and leave the rest alone.

The procedure

post_to_imp3.py in this directory does it; it is deliberately two-phase.

post_to_imp3.py --check                  is imp3 up, and where is its window
post_to_imp3.py --stage "first line"     type it WITHOUT sending; screenshot it
post_to_imp3.py --send "l2" "l3" ...     send the staged line, then the rest

By hand it is:

a.arexx("address AMIAGENT\n'ACTIVATEWINDOW \"CHAT --*\"'\n")
a.arexx("address AMIAGENT\n'ENTERTEXT \"your line\"'\n")
a.arexx("address AMIAGENT\n'KEY \"enter\"'\n")

One line per message, about 1.5 s apart so the client keeps up.

The rule that matters: check before it is public

The A4000 runs a German keymap. ENTERTEXT types through the Amiga's own keymap, so |, /, : and umlauts do come out right — but verify it rather than assume, because a mangled line cannot be unsent.

Read the full file on GitHub · 105 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

post_to_imp3.py 4.2 KB runs code

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.

1mo ago First seen · 105 lines · 62 tokens per session scan A b5c493b0d0bc

Subscribe to this mod's changes

imp3-post is a skill published in the GitHub repository thomas-luebker/amimcp (26 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 1,189 once invoked, about $0.0002 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 2026-10-01.

Creative and media

imp3-post next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
imp3-postthomas-luebker/amimcp	Skill	26	yesterday	Apache-2.0	A	62	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

amimcp: Skill for Claude Code