platform-reference

platform-reference is a skill for Claude Code, Codex from azeemkafridi/bulkpublish-api. It costs 36 tokens per session (4,013 once invoked), scanned A, original, MIT.

A reference guide for creating posts on 15 social platforms, including each platform’s post types, media rules, required fields, and text limits.

In plain words
What is it for?
It helps prepare platform-specific content for services such as YouTube, TikTok, Pinterest, Instagram, Facebook, Bluesky, Threads, and Mastodon.
Why use it?
It prevents posts from being rejected because they use the wrong format, missing fields, unsupported media, or too much text.

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/azeemkafridi/bulkpublish-api/platform-reference
Any agent
npx skills add azeemkafridi/bulkpublish-api --skill platform-reference
Clone the repo
git clone --depth 1 https://github.com/azeemkafridi/bulkpublish-api

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 platform-reference

README.md
[![agentmods](https://agentmods.dev/badge/skills/azeemkafridi/bulkpublish-api/platform-reference.svg)](https://agentmods.dev/skills/azeemkafridi/bulkpublish-api/platform-reference)
Your own site
<a href="https://agentmods.dev/skills/azeemkafridi/bulkpublish-api/platform-reference"><img src="https://agentmods.dev/badge/skills/azeemkafridi/bulkpublish-api/platform-reference.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,013 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 $0.04013
Opus 5 $0.00018 $0.02006
Sonnet 5 $0.00007 $0.00803
Haiku 4.5 $0.00004 $0.00401

Measured 3d ago against content hash 2122d1b95d9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

platform-reference 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/bulkpublish/skills/platform-reference/SKILL.md · 411 lines

How it starts

The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BulkPublish — Platform Reference

Quick Rules

  • YouTube & TikTok require video — NEVER include them for image-only posts
  • Pinterest requires a title — set platformSpecific.pinterest.title
  • YouTube requires a title — set platformSpecific.youtube.title
  • Instagram defaults to feed_photo — set postTypeOverrides.instagram for video content
  • Use platformContent for shorter text on platforms with low char limits (Bluesky 300, Pinterest/Threads/Mastodon 500)

Facebook

Field Value
Platform key facebook
Char limit 63,206
Title required No

Post types:

Type Media Notes
post (default) 0-10 images OR 0-1 video Text-only OK. No mixing images+video
reel 1 video required Vertical short-form video
story 1 image OR 1 video required Disappears after 24h

Media specs: Image max 10MB (jpg/png/gif/webp). Video max 2GB (mp4/mov).

platformSpecific options: linkPreview.url


Instagram

Field Value
Platform key instagram
Char limit 2,200
Title required No
Account type Business or Creator (personal rejected)

Post types:

Type Media Notes
feed_photo (default) 1 image required Single photo post
feed_video 1 video required Single video post
reel 1 video required Short-form video, 9:16 recommended
story 1 image OR 1 video required Disappears after 24h
carousel 2-10 images/videos required Mixed media OK

Media specs: Image max 8MB (jpg/jpeg only). Video max 1GB (mp4/mov).

platformSpecific options:

  • collaborators — string or array of collaborator usernames
  • trialReel — boolean, trial reel (graduates based on performance)
  • thumbnailTimestamp — number (seconds), video thumbnail offset

IMPORTANT: If you have video and don't set postTypeOverrides.instagram, it defaults to feed_photo and FAILS. Always set to reel or feed_video for video.

Read the full file on GitHub · 411 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 · 411 lines · 36 tokens per session scan A 2122d1b95d9b

Subscribe to this mod's changes

platform-reference is a skill published in the GitHub repository azeemkafridi/bulkpublish-api (1 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 4,013 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.