social-draft

social-draft is a skill for Claude Code, Codex from Kevin-Liu-01/Agent-Machines. It costs 69 tokens per session (943 once invoked), scanned A, original, MIT.

A writing guide for turning one idea into platform-specific posts for X and LinkedIn. It uses the topic, claim, proof, goal, tone, and constraints to shape the draft.

In plain words
What is it for?
Use it to draft an X post, X thread, LinkedIn story, or LinkedIn list from raw material. It helps choose an opening, format, tone, and concise wording.
Why use it?
It helps avoid vague social posts and unsupported claims. It also removes the need to adapt the same idea manually for each platform.

Skill for Claude CodeCodex

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

Good fit Use it to draft an X post, X thread, LinkedIn story, or LinkedIn list from raw material. It helps choose an opening, format, tone, and concise wording.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kevin-liu-01/agent-machines/social-draft
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 Kevin-Liu-01/Agent-Machines --skill social-draft
Clone the repo
git clone --depth 1 https://github.com/Kevin-Liu-01/Agent-Machines

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 social-draft

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/social-draft/github.svg)](https://agentmods.dev/skills/kevin-liu-01/agent-machines/social-draft)
Your own site
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/social-draft"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/social-draft/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-draft

Your own site · 80×15
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/social-draft"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/social-draft.svg" alt="Reviewed on agentmods" width="80" 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 943 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 $0.00943
Opus 5 $0.00034 $0.00472
Sonnet 5 $0.00014 $0.00189
Haiku 4.5 $0.00007 $0.00094

Measured 9d ago against content hash 86a8f156f438, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

social-draft 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 9d 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.

knowledge/skills/social-draft/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 Draft

Input Contract

Minimum viable draft input is not "write about X." It is: topic, claim, proof, why it matters, goal, tone, constraints. If proof is missing, do not invent it. Use qualitative specificity or clearly marked placeholders.

Drafting Workflow

  1. Distill the idea into one claim
  2. Find the strongest proof block
  3. Decide: teach, reveal, provoke, or reflect
  4. Pick format (X single post, X thread, LinkedIn story, LinkedIn list)
  5. Write the opening first
  6. Remove every sentence that sounds generic when detached from the proof

X Rules

Good X posts: stop the scroll in line one, compress one idea hard, sound current and alive, create curiosity without bait.

Preferred openings: specific result (I shipped X in Y), contrarian take (Most people get X wrong), build tension (The weirdest part of building X was not Y), field note (Watching X happen live changed my view on Y).

Format: target under 140 characters for single posts, under 110 for sharp takes. Thread only when genuinely needed. Links in reply, not main post. One emoji max. Close with a clean question, challenge, or takeaway.

Avoid: "Thoughts?", "Agree?", "Like and repost."

LinkedIn Rules

Good LinkedIn posts: win the first two lines, feel conversational but professional, tell one coherent story, translate detail into a lesson.

Structures: Story (hook -> event -> change -> lesson -> close), Contrarian (claim -> why common wisdom fails -> evidence -> better framing), List (hook -> numbered points -> synthesis), Lesson learned (I used to think X. Now I think Y.).

Format: paragraphs 1-2 sentences, under 1300 characters unless depth helps, line breaks aggressively, 3-5 hashtags max at bottom only.

Tone Modes

Casual: tighter sentences, lighter language, more immediacy. Avoid slang that hurts credibility.

Professional: clean sentences, explicit lessons. Avoid consulting voice and over-hedging.

Thought-leader: sharper framing, stronger claims, broader implication. Avoid prophecy without proof.

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. 9d ago First seen · 69 lines · 69 tokens per session scan A 86a8f156f438

Subscribe to this mod's changes

social-draft is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 943 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