Borrowing it
Nothing to install: this file belongs to gug007/lpm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gug007/lpm/main/.claude/skills/short-publish/SKILL.mdgit clone --depth 1 https://github.com/gug007/lpmWrote 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/gug007/lpm/short-publish)<a href="https://agentmods.dev/skills/gug007/lpm/short-publish"><img src="https://agentmods.dev/badge/skills/gug007/lpm/short-publish/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/gug007/lpm/short-publish"><img src="https://agentmods.dev/badge/skills/gug007/lpm/short-publish.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 | $0.00120 | $0.03119 |
| Opus 5.5 | $0.00048 | $0.01248 |
| Sonnet 5.5 | $0.00024 | $0.00624 |
| Haiku 4.5 | $0.00012 | $0.00312 |
Grade A, and why
short-publish 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post a vertical lesson to YouTube Shorts and TikTok at the same time.
- scope: both platforms unless the user names one. A platform whose ledger already lists the slug is skipped unless the user asked for a repost.
- run
node scripts/prepare.js <slug> <scratchpad-dir> [--full-lesson <youtu.be link>]first. It copies the MP4 (named after the title, because Studio pre-fills the title from the file name) andcover.jpginto the scratchpad, shrinks a master over 10,000,000 bytes to a two-pass H.264 copy (the master stays in the lesson folder), and prints the title, the TikTok caption and the YouTube description. It warns about a wrong size, a clip over 3 minutes (not a Short), a title the file name could not carry (retype it), an over-long caption, more than 5 hashtags, an@, and a slug already in either ledger.--full-lessonis the long YouTube lesson on the same topic (Studio → Content → Videos); leave it out when there is none. - shared text: the caption is the first paragraph of
post.txt, then at most 5 hashtags (TikTok's cap; a 6th and later lose their#; whenpost.txthas more, keep the topic tags and#lpm). Brand stays lowercaselpm. No@. No next-video teaser. YouTube gets the same caption and hashtags plus the lpm line and link that prepare.js adds.
Running both at once
The two tracks use different tools that do not share state: YouTube goes through the Claude in Chrome MCP, which drives the tab through the extension and needs no OS focus; TikTok goes through computer use on iPhone Mirroring, which moves the real pointer in the frontmost app. Work both yourself, without subagents: put the next step of each track in the same message as two parallel tool calls (a browser_batch beside a computer_batch), read both results, and send the next pair. Start with YouTube's file_upload so the video processes on YouTube's side while the phone steps run.
- both platforms publish as soon as their forms are done and checked; neither waits for the user's OK (user rule 2026-09-30: "post it without asking").
- computer use "in use by another Claude session": end that session without asking (user rule 2026-09-30).
~/.claude/computer-use.locknames itspid;kill <pid>, check the lock is gone, thenrequest_accessagain. - a blocked track does not stop the other: when computer use is still unavailable (access denied) or the Chrome extension is not connected, finish the other platform and tell the user which one is left. Never move TikTok to the Chrome path on your own (the daily-short automation is the one exception: see below).
- each track was verified on its own (2026-09-25: two Shorts, two TikTok posts). The first parallel run is new: write what broke into the
tiktok-uploadandyoutube-uploadmemories.
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.
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 Changed be0dcb18c78a
- 23d ago First seen · 62 lines · 120 tokens per session scan A bd18eff6fad4
short-publish is a skill published in the GitHub repository gug007/lpm (145 stars, last pushed today), licensed MIT. It adds 120 tokens to every session and 3,119 once invoked, about $0.0005 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.
Other skills, from other repositories
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
tui-migrate-setup
Migrates the supported subset of an existing Warp GUI setup into Warp Agent CLI without exposing credentials or application state. Use in Warp Agent CLI when a user wants to copy or move compatible settings or global file-based MCP servers from the desktop app, set up Warp Agent CLI from an existing GUI installation…
blueprint-cloudflare-scaffold
Lay out a Worker with D1 and static Vue assets, with tests that run inside the Workers runtime.