A tool that adapts LinkedIn posts for X (formerly Twitter), including text, images, and videos, then publishes them through X's API.

Use it to cross-post a LinkedIn update, shorten its text, attach supported media, or turn it into an X thread.

It removes the need to rewrite longer LinkedIn content to fit X's shorter post limits or upload media separately. It requires X developer credentials with permission to publish.

post-to-x — Skill for Claude Code and Codex by floomhq

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 floomhq/moto --skill post-to-x

Clone the repo

git clone --depth 1 https://github.com/floomhq/moto

Made for: Claude Code, Codex.

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/floomhq/moto/post-to-x/github.svg)](https://agentmods.dev/skills/floomhq/moto/post-to-x)

Your own site

<a href="https://agentmods.dev/skills/floomhq/moto/post-to-x"><img src="https://agentmods.dev/badge/skills/floomhq/moto/post-to-x/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/floomhq/moto/post-to-x"><img src="https://agentmods.dev/badge/skills/floomhq/moto/post-to-x.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,201 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	$0.00083	$0.01201
Opus 5	$0.00042	$0.00600
Sonnet 5	$0.00017	$0.00240
Haiku 4.5	$0.00008	$0.00120

Measured 10d ago against content hash 1776ee84936d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

post-to-x 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.

claude/skills/post-to-x/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Post to X (Twitter)

Cross-post LinkedIn content to X, adapting text and attaching media.

Prerequisites

X API credentials must be set in ~/.claude/skills/post-to-x/.env:

X_API_KEY=your_api_key
X_API_SECRET=your_api_secret
X_ACCESS_TOKEN=your_access_token
X_ACCESS_TOKEN_SECRET=your_access_token_secret

These come from the X Developer Portal (developer.x.com). You need a project with "Read and Write" permissions. The access token must be generated with read+write scope.

Workflow

Step 1: Find the LinkedIn post content

Look for the post text in the current directory or the directory the user references:

post-copy-final.txt or post-copy*.txt for text
*.mp4, *.mov, *.webm for video
*.jpg, *.jpeg, *.png for images
thumbnail*.jpg, thumbnail*.png for thumbnail images

If the user provides text directly, use that instead.

Step 2: Adapt the text for X

LinkedIn posts are long-form. X has character limits:

280 characters for text-only posts
280 characters for posts with media (text portion)
Threads: up to 25 tweets, each 280 chars

Strategy:

Extract the core hook/message from the LinkedIn post
Create a concise X version (aim for 200-250 chars to leave room for links)
Remove LinkedIn-specific CTAs ("DM me", "Comment below")
Replace with X-appropriate CTAs if needed ("Link in replies", thread format)
Keep hashtags minimal (0-2 max, only if truly relevant)
No emojis unless the user explicitly requests them

If the post is too rich for a single tweet, propose a thread (2-4 tweets max).

Always show the adapted text to the user for approval before posting.

Step 3: Upload media (if any)

python3 ~/.claude/skills/post-to-x/scripts/post_to_x.py upload-media <file_path>

This returns a media_id to use in Step 4.

For video: the script handles chunked upload (INIT, APPEND, FINALIZE, STATUS polling). For images: simple upload.

Size limits:

Images: 5 MB (JPEG, PNG, GIF, WEBP)
Video: 512 MB, up to 2:20 duration (MP4 with H.264 video, AAC audio)
GIF: 15 MB

Read the full file on GitHub · 137 lines

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.

10d ago First seen · 137 lines · 83 tokens per session scan A 1776ee84936d

Subscribe to this mod's changes

post-to-x is a skill published in the GitHub repository floomhq/moto (32 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 1,201 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 2026-08-30.

Marketing and SEO agentic-coding agentic-work ai-agent ai-agents ai-coding anthropic

eval-agents

Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…

FlorianBruniaux/claude-code-ultimate-guide · 93 tokens

issue-triage

3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.

FlorianBruniaux/claude-code-ultimate-guide · 81 tokens

post-to-x