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 skills/localplugins/plugins/channel-formatsnpx skills add localplugins/plugins --skill channel-formatsgit clone --depth 1 https://github.com/localplugins/pluginsWhat 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 | $0.00075 | $0.01175 |
| Opus 5 | $0.00037 | $0.00588 |
| Sonnet 5 | $0.00015 | $0.00235 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
channel-formats 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Channel Formats
Overview
Channel Formats adapts a single source into the shape each platform expects, then hands the draft to the brand layer. Format is the container; brand voice is the content.
Every channel has its own limits and conventions: a LinkedIn post is not an X thread, and a YouTube description is not an Instagram caption.
This skill reads the spec for the requested channel from the plugin's bundled channels/<id>.md files, drafts to that spec, and enforces the length limit.
It is instruction-driven and writes ready-to-paste files, with no accounts, keys, or network access.
Prerequisites
- The source content to adapt (a file path or pasted text) and one or more target channels.
- The bundled channel specs, which ship inside this skill at
channels/. The skill uses Glob and Read to load the right spec and Write to save each derivative. - An active brand profile so the
brand-voiceskill can run on top; if none exists, the caller is pointed to/brand-setup.
Channels (canonical IDs)
The channel ID is also the output filename (for example linkedin.md).
linkedin— professional single post — channels/linkedin.mdx-thread— multi-post thread — channels/x-thread.mdnewsletter— email newsletter section — channels/newsletter.mdinstagram— caption plus hashtags — channels/instagram.mdyoutube— description with timestamped chapters — channels/youtube.mdshort-video— TikTok, Reels, or Shorts script — channels/short-video.mdblog— short post or excerpt — channels/blog.md
Instructions
- Identify the target channel by its canonical ID from the list above.
- Read that channel's spec in
channels/<id>.md— each spec defines Format, Length, Structure, Do, and Avoid. - Draft the derivative to the spec, mapping the source's core message onto that channel's hook and structure.
- Check the character or word count and enforce the channel's limit; trim or split as the spec requires.
- Run the
brand-voiceself-check so the draft obeys the brand's tone, glossary, and compliance rules. - For localized copy, re-fit after transcreation because text expands or contracts across languages.
- Write one file per derivative, named after the channel ID.
What ships with it
9 files 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 First seen · 100 lines · 75 tokens per session scan A 6cb892209d45
channel-formats is a skill published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,175 once invoked, about $0.0004 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
Article Repurposer
Takes a long-form article and repurposes it into multiple formats: tweet thread, LinkedIn post, TL;DR, and key quotes.
code-to-content
Use when transforming a codebase into developer content. Activates for: Blog posts, tutorials, or technical documentation about code README, changelog, release notes, or API docs generation Twitter/X threads, LinkedIn posts about technical work Conference talk proposals (CFP) or newsletter content Build-in-public…
linkedin-post-creator
LinkedIn专业内容创作工具，根据主题和受众生成高质量LinkedIn帖子，优化专业表达和互动率.
viral-post-creator
病毒式社交媒体帖子生成器，分析热门趋势并创作高传播潜力的多平台内容.
Chinese Market Content Engineer
Generate, localize, and optimize content for Chinese digital platforms (微信公众号, 小红书, 抖音, 知乎, B站) with cultural nuance and platform-specific best practices.
Xiaohongshu Content Strategist
Create viral Xiaohongshu (小红书) content that ranks in search and gets saves. Bilingual Chinese/English, platform-native style, trending format awareness.