social-post-craft

social-post-craft is a skill for Claude Code from cbrock84/headcount. It costs 69 tokens per session (659 once invoked), scanned A, original, MIT.

A guide to writing and evaluating social media posts, from the opening line through the main idea, formatting, and final review.

In plain words
What is it for?
Use it to draft or rewrite posts, turn longer material into social content, improve hooks, and assess underperforming drafts.
Why use it?
It helps posts avoid weak openings, unclear structure, poor platform formatting, and ideas that are not ready to publish.

Skill for Claude Code

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

Part of the marketing plugin — 19 skills shipped together

Good fit Use it to draft or rewrite posts, turn longer material into social content, improve hooks, and assess underperforming drafts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cbrock84/headcount/social-post-craft
About the project

headcount is an organization of independently installable Claude Code plugins, each grouping skills for a department such as finance, security, or demand generation. Claude Code users install the departments they need and invoke their skills for specialized work; the catalogue entries are skills and related agent tooling from that organization.

cbrock84/headcount · 1,300 stars · on GitHub · cbrock84.github.io

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 cbrock84/headcount --skill social-post-craft
Clone the repo
git clone --depth 1 https://github.com/cbrock84/headcount

Made for: Claude Code.

Or install marketing, the plugin that ships this one along with the rest of its 19 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-post-craft

README.md
[![agentmods](https://agentmods.dev/badge/skills/cbrock84/headcount/social-post-craft.svg)](https://agentmods.dev/skills/cbrock84/headcount/social-post-craft)
Your own site
<a href="https://agentmods.dev/skills/cbrock84/headcount/social-post-craft"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/social-post-craft.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 659 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00069 $0.00659
Opus 5 $0.00034 $0.00329
Sonnet 5 $0.00014 $0.00132
Haiku 4.5 $0.00007 $0.00066

Measured 3d ago against content hash 071ec102e2be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

social-post-craft 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 3d 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.

plugins/marketing/skills/social-post-craft/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Social post craft

The hook decides everything

Most posts are lost in the first line, before any of the substance is reached. The opening has one job: make continuing feel more attractive than scrolling.

Openings that work:

  • A specific claim with a number — concrete beats clever.
  • A stated tension — two things the reader believes that cannot both be true.
  • A named mistake — especially one the reader is probably making.
  • An outcome, before the method — the result first, the how afterward.

Openings that do not: a question the reader can answer "no" to, a definition, throat-clearing about why the topic matters, and anything beginning "In today's world."

Write the hook last, after you know what the post actually says. Written first, it commits you to a post you have not thought through.

Structure

One idea. A post carrying two ideas gets remembered for neither.

Then: hook, the turn (why the obvious view is incomplete), the substance (specific, ideally first-hand), and the landing — a conclusion, not a request for engagement.

Cut the first two lines of your draft. They are almost always warm-up.

Formatting is not cosmetic

Line breaks control pace and determine what is visible before the "see more" fold. On every major platform, the visible portion is one to three lines — everything about whether the post is read is decided there.

Short paragraphs. One thought per line for emphasis. No walls. Emphasis carried by structure, since most platforms strip formatting.

Check before publishing

  • Is the first line strong enough alone, with no context?
  • Does it survive the fold — is the visible part a complete enough thought to earn expansion?
  • One idea, or two?
  • Is anything in it specific to you? A post anyone in your field could have written performs like it.
  • Would you send this to one person you respect? If not, do not send it to everyone.

A draft that fails these gets rewritten, not published with a caveat.

Tooling

Scheduling and publishing: Buffer, Hootsuite, Later, Sprout Social, Typefully, and similar. Native composers usually get better reach handling and newer formats first, so schedule what benefits from timing and post natively what benefits from features.

Read the full file on GitHub · 69 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.

  1. 3d ago First seen · 69 lines · 69 tokens per session scan A 071ec102e2be

Subscribe to this mod's changes

social-post-craft is a skill published in the GitHub repository cbrock84/headcount (1,300 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 659 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

save

Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.

XTSoftwareLabs/neatcontext-plugins · 49 tokens

mode

Show or set NeatContext routing to auto, ask, or manual for Codex, with an optional default shared with every other NeatContext host. Use only when the user explicitly invokes this skill or clearly asks to change routing behavior.

XTSoftwareLabs/neatcontext-plugins · 50 tokens

status

Report the NeatContext context and routing mode active in Codex, including missing-file or stale-routing warnings. Use when the user asks which context is connected or explicitly invokes this skill.

XTSoftwareLabs/neatcontext-plugins · 39 tokens

list

List the local NeatContext Contexts available to Codex. Use when the user asks what contexts exist, what can be connected, or explicitly invokes this skill.

XTSoftwareLabs/neatcontext-plugins · 35 tokens

build-oxpecker-web-app

Build or modify an Oxpecker web application in idiomatic F#, using endpoint routing, functional EndpointHandler and EndpointMiddleware composition, ASP.NET Core metadata, and focused endpoint tests.

gaelic-ghost/socket · 44 tokens

dns

This skill should be used when the user asks about "DNS", "domain resolution", "GeoDNS / geo routing", "latency-based routing", "weighted / failover routing", "Route 53 / Cloud DNS", an "A/CNAME/ALIAS record", "anycast", or "DNS TTL / propagation". It gives the global front door that maps a name to the right IP and…

proyecto26/system-design-skills · 131 tokens