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 Charlesmpc/by2kb --skill short-abstractgit clone --depth 1 https://github.com/Charlesmpc/by2kbWrote 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/charlesmpc/by2kb/short-abstract)<a href="https://agentmods.dev/skills/charlesmpc/by2kb/short-abstract"><img src="https://agentmods.dev/badge/skills/charlesmpc/by2kb/short-abstract/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/charlesmpc/by2kb/short-abstract"><img src="https://agentmods.dev/badge/skills/charlesmpc/by2kb/short-abstract.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 | $0.00018 | $0.00264 |
| Opus 5 | $0.00009 | $0.00132 |
| Sonnet 5 | $0.00004 | $0.00053 |
| Haiku 4.5 | $0.00002 | $0.00026 |
Grade A, and why
short-video-abstract 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 10d 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.
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.
What it actually says
Short video abstract
Goal
Help the reader decide in under a minute whether the full study notes or source video are worth their time.
Rules
- Write in the transcript's primary language unless the source metadata strongly indicates another language.
- Stay grounded in the transcript. Do not add background facts or infer claims that the speaker did not make.
- Keep the entire response concise: roughly 120–200 Chinese characters or 80–140 English words.
- Do not reproduce the transcript or create a detailed chapter list.
- If the transcript is incomplete or low quality, say so in one short warning.
Output
Produce exactly these sections:
# 一句话摘要/# One-sentence abstract— the topic and central conclusion.## 你会得到什么/## What you will learn— 2–4 concrete bullets.## 是否值得深入/## Is it worth going deeper?— who benefits, what prior interest is assumed, and the strongest reason to continue or skip.
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.
- 10d ago First seen · 34 lines · 18 tokens per session scan A 59c5cb4fcada
short-video-abstract is a skill published in the GitHub repository Charlesmpc/by2kb (6 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 264 once invoked, about $0.0001 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 skills, from other repositories
obsidian-setup-consultant
Use this skill whenever the user wants to install, configure, migrate, design, or connect Obsidian as a second brain, knowledge base, cloud-synced vault, or AI/Hermes-readable memory. It is especially important when the user asks for an Obsidian setup prompt, vault architecture, folder structure, plugin…
solomd
Read, search, edit, and version-control any folder of Markdown notes via the SoloMD MCP server. 13 tools including AutoGit per-note history, semantic search, and write-with-sandbox via an accept/reject branch. Includes 11 starter agent recipes (weekly review, todo extract, link suggester, …).
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
youtube-fetcher
Retrieve YouTube transcripts and subtitles, summarize or analyze what was said, or save an Obsidian-ready Markdown knowledge-base note with captions, creator metadata, chapters, language, and source provenance. Use for a YouTube URL or video ID when the request needs spoken content or an archival note. A bare YouTube…
larksnap-fetch
A bridge for downloading Feishu/Lark documents or ordinary webpages into local files, with options such as Markdown, HTML, or PDF. Feishu, also called Lark, is a workplace collaboration platform.
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.