social-crosspost

social-crosspost is a skill for Claude Code from inklate/social-skills. It costs 166 tokens per session (1,381 once invoked), scanned A, original, MIT.

A writing guide that turns one source, such as a web page, article, announcement, or idea, into separate social-media drafts. Each draft is adapted for LinkedIn, X, Instagram, Facebook, Threads, Bluesky, or Mastodon.

In plain words
What is it for?
Use it to promote an article, announcement, story, or idea on multiple platforms with different lengths, tones, structures, hashtags, and calls to action.
Why use it?
It avoids copying the same caption everywhere when each platform has different reading habits and format expectations. It also helps keep one central message consistent across several drafts.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the social-skills plugin — 14 skills shipped together

Good fit Use it to promote an article, announcement, story, or idea on multiple platforms with different lengths, tones, structures, hashtags, and calls to action.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/inklate/social-skills/social-crosspost
Install

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.

Any agent
npx skills add inklate/social-skills --skill social-crosspost
Clone the repo
git clone --depth 1 https://github.com/inklate/social-skills

Made for: Claude Code.

Or install social-skills, the plugin that ships this one along with the rest of its 14 skills.

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.

agentmods badge for social-crosspost

README.md
[![agentmods](https://agentmods.dev/badge/skills/inklate/social-skills/social-crosspost/github.svg)](https://agentmods.dev/skills/inklate/social-skills/social-crosspost)
Your own site
<a href="https://agentmods.dev/skills/inklate/social-skills/social-crosspost"><img src="https://agentmods.dev/badge/skills/inklate/social-skills/social-crosspost/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.

agentmods 80×15 button for social-crosspost

Your own site · 80×15
<a href="https://agentmods.dev/skills/inklate/social-skills/social-crosspost"><img src="https://agentmods.dev/badge/skills/inklate/social-skills/social-crosspost.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 166 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,381 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00166 $0.01381
Opus 5 $0.00083 $0.00691
Sonnet 5 $0.00033 $0.00276
Haiku 4.5 $0.00017 $0.00138

Measured 12d ago against content hash feae2935ed4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

social-crosspost 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 12d 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.

skills/social-crosspost/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Given one source — a URL, pasted text, or a raw idea — produce a native draft per platform, each shaped for how that platform actually reads, with a one-line rationale per draft.

Context

Read social-context.md (also check .agents/social-context.md) before drafting. You need:

  • Brand voice: register, person ("I" vs "we"), emoji policy, banned phrases
  • Audience per platform, if specified — the LinkedIn reader and the Bluesky reader are rarely the same person
  • ## Platforms: the default platform list when the user does not name targets
  • The Never list: red lines to keep out of every draft, since one message goes to many public feeds

If the file is missing, offer to run the social-context skill first — but do not block. Ask two or three quick questions inline (Which platforms? Personal voice or company voice? Anything off-limits?) and proceed.

Workflow

  1. Ingest the source. Fetch the URL or read the pasted text in full — the best social material is often a buried aside, not the headline. If it is only an idea, ask one clarifying question at most, then work with what you have.
  2. Extract the ONE core claim plus 2–3 supporting points. Write these down and show them before drafting. Every platform draft argues the same claim; what varies is how. If you cannot state the claim in one sentence, the source is not ready — say so and propose the sharpest available angle. Also harvest the receipts: any number, quote, or before/after in the source, because those survive adaptation better than prose.
  3. Confirm target platforms. Use the user's list if given; otherwise default to ## Platforms from social-context; otherwise ask. Do not silently produce all seven — an unwanted Mastodon draft is noise, not thoroughness.
  4. Draft each platform natively, from the claim — not from another draft. These are siblings, not truncations of each other. Load references/platform-rules.md and draft each target to its length, structure, hashtag, and link rules there. Keep the receipts (numbers, quotes, before/after) — they survive adaptation better than prose — and give every platform its own hook, since reusing one first line wastes the variable that matters most.
  5. Write the per-draft rationale. One line under each draft: what you changed for this platform and why ("compressed to the stat because X rewards one sharp number", "led with the customer story because LinkedIn's fold buries anything slower"). The rationale teaches the user the platform, not just this post.
  6. Voice-check the set. Read all drafts in a row and hold them to three tests:
    • Same person, different rooms — if any draft could not have been written by the voice in social-context, revise it.
    • No verbatim repeats — kill any phrase that appears word-for-word in three or more drafts; siblings, not clones.
    • Claim intact — every draft still argues the core claim from step 2; a draft that drifted into a different point gets rewritten, not kept.
  7. Check every draft against its platform rules. Using references/platform-rules.md, verify each draft on every axis — length, structure, hashtags, links — and fix violations: count characters on X, Threads, Bluesky, and Mastodon and trim to fit by cutting the weakest middle clause, never by amputating the ending. Screen every draft against the Never list too.
  8. Flag gaps honestly. If a platform is a poor fit for this story (a B2B pricing memo on Instagram), include the draft but say so in its rationale rather than forcing false enthusiasm — the user may still want it, but they should not be surprised when it underperforms.

Read the full file on GitHub · 76 lines

Files

What ships with it

2 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.

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.

  1. 12d ago First seen · 76 lines · 166 tokens per session scan A feae2935ed4d

Subscribe to this mod's changes

social-crosspost is a skill published in the GitHub repository inklate/social-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 166 tokens to every session and 1,381 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens