agentmods.dev

walter-social-media

walter-social-media is a skill for Claude Code, Codex from walterwritesai/walter-skills. It costs 45 tokens per session (329 once invoked), scanned A, original, MIT.

A writing assistant that turns source content into posts for X or Twitter, LinkedIn, Instagram, and Facebook. Each version follows the platform's specified length and writing style.

In plain words
What is it for?
Use it to create social posts or threads, preserve branded terms, and compare each platform's word or character count and detection score.
Why use it?
It avoids manually adapting one piece of content to four different social platforms.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 13repo 4mo ago A scan 45 tokens original MIT

Good fit Use it to create social posts or threads, preserve branded terms, and compare each platform's word or character count and detection score.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/walterwritesai/walter-skills/social-media
View source ↗ walterwritesai/walter-skills
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 walterwritesai/walter-skills --skill social-media
Clone the repo
git clone --depth 1 https://github.com/walterwritesai/walter-skills

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.

agentmods badge for walter-social-media

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/walterwritesai/walter-skills/social-media"><img src="https://agentmods.dev/badge/skills/walterwritesai/walter-skills/social-media.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 329 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 $0.00045 $0.00329
Opus 5.5 $0.00018 $0.00132
Sonnet 5.5 $0.00009 $0.00066
Haiku 4.5 $0.00005 $0.00033

Measured 2mo ago against content hash 35eaff2df112, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

walter-social-media 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 2mo 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-media/SKILL.md · 34 lines

What it actually says

Walter Social Media Manager

You repurpose content into platform-native social posts. Use Walter Writes AI tools automatically.

Platforms

  • X / Twitter: threads (7–10 posts, 280 char each) and standalone posts.
  • LinkedIn: 200–400 word posts with one clear takeaway.
  • Instagram: captions 100–200 words, no aggressive emoji use, save line breaks for visual rhythm.
  • Facebook: longer-form (300–500 words) with conversational hook.

Per-platform rules

  • X: number every post in a thread (1/, 2/, etc.). End the thread with an explicit "←" or CTA.
  • LinkedIn: open with a 1-line hook on its own paragraph. Use single line breaks between paragraphs.
  • Instagram: assume the first 125 chars are visible before "more" — earn the click.
  • Facebook: lean conversational, not listicle.

Default behavior

  • When given source content, generate all four formats unless told otherwise.
  • Humanize every output through Walter in balanced mode.
  • Show detection scores side-by-side.
  • Preserve any branded terms or product names exactly.

End-of-output

  • Print a 4-row table: platform, character/word count, detection score, ready-to-paste flag.
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. 2mo ago First seen · 34 lines · 45 tokens per session scan A 35eaff2df112

Subscribe to this mod's changes

walter-social-media is a skill published in the GitHub repository walterwritesai/walter-skills (13 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 329 once invoked, about $0.0002 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 2026-08-31.

Marketing and SEOWriting and docsai-detectionai-humanizerclaudeclaude-mcpclaude-skillscontent-marketing
Related

walter-social-media compared with skills from other repositories

walter-social-media next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
walter-social-mediawalterwritesai/walter-skillsSkill134mo agoMITA45Claude Code, Codex
scrapecreators-apiScrapeCreators/social-media-research-skillsSkill5.8k2mo agoMITA161Claude Code
outlier-post-finderScrapeCreators/social-media-research-skillsSkill5.8k2mo agoMITA60Claude Code
ad-library-teardownScrapeCreators/social-media-research-skillsSkill5.8k2mo agoMITA56Claude Code
comment-miningScrapeCreators/social-media-research-skillsSkill5.8k2mo agoMITA48Claude Code
competitor-social-researchScrapeCreators/social-media-research-skillsSkill5.8k2mo agoMITA49Claude Code
transcript-intelligenceScrapeCreators/social-media-research-skillsSkill5.8k2mo agoMITA62Claude Code