social-media-drafting

A skill for writing social-media drafts, including posts, threads, replies, captions, and updates, with audience, safety, and privacy checks.

In plain words
What is it for?
Use it for LinkedIn posts, X-style threads, community updates, launch announcements, replies, and captions, including shorter or differently toned versions.
Why use it?
It helps turn verified information into suitable public writing while keeping publication under explicit human approval.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/codeinfinity1/stram/social-media-drafting
Any agent
npx skills add CodeInfinity1/Stram --skill social-media-drafting
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 528 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.00528
Opus 5 $0.00018 $0.00264
Sonnet 5 $0.00007 $0.00106
Haiku 4.5 $0.00004 $0.00053

Measured 3d ago against content hash c8df2822ad2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

social-media-drafting 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.

skills/communications/social-media-drafting/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Social Media Drafting

Purpose

Help the user write social content without turning the assistant into an uncontrolled broadcaster. This skill creates drafts, variants, and review notes while keeping posting behind explicit approval and native tool support.

When To Use

Use for LinkedIn posts, X/Twitter-style threads, community updates, launch posts, replies, captions, or public-facing short content.

Inputs And Evidence

  • Platform, audience, intent, source facts, desired tone, and length.
  • Links, screenshots, product details, or announcement facts.
  • Risk constraints: privacy, policy, legal, competitive, or safety.
  • Native channel or browser posting support if requested.

Tool Map

  • writing_draft_create
  • writing_draft_inspect
  • write_note
  • memory_write
  • read_file
  • browser_live_open
  • browser_live_observe
  • channel_message_prepare
  • message-approval-policy

Workflow

  1. Identify platform norms and audience.
  2. Extract verified facts and decide what should stay private.
  3. Draft one strong version and optional shorter/warmer/more formal variants.
  4. Avoid unsupported claims, protected lyrics, private data, and impersonation.
  5. Save reusable drafts with writing_draft_create when requested.
  6. Do not post automatically; use native browser/channel actions only after explicit approval.

Native Implementation Boundaries

  • Do not use external reference X/Twitter utilities, external reference social plugins, or third-party posting scripts as implementation.
  • If a native social API adapter does not exist, provide drafts or use approved browser control as a user-directed path.

Safety And Approval

  • Public posts need review before publication.
  • Do not imitate a real person's private voice without user-provided context and permission.
  • Do not disclose confidential roadmap, keys, addresses, or private conversations.

Verification

  • Confirm whether output is a draft, saved note, prepared message, or posted artifact.
  • Posting requires a native tool result proving success.
  • Check factual claims against provided evidence.

Read the full file on GitHub · 71 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 · 71 lines · 36 tokens per session scan A c8df2822ad2a

Subscribe to this mod's changes

social-media-drafting is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 23d ago), licensed MIT. It adds 36 tokens to every session and 528 once invoked, about $0.0002 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.