social-campaign

social-campaign is a skill for Claude Code, Codex from tang-vu/social-posting-skills. It costs 30 tokens per session (1,118 once invoked), scanned A, original, MIT.

A workflow for turning one source item, such as a release note, README, or changelog, into adapted social-media posts and draft content. A person reviews and approves the content before it is published.

In plain words
What is it for?
Use it to create a campaign from a project update, adapt content for different platforms, preview and edit the results, approve selected items, publish them, or export them as drafts.
Why use it?
It removes the need to rewrite the same announcement separately for each platform. It keeps publishing behind a human approval step and can also export drafts instead of publishing them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to create a campaign from a project update, adapt content for different platforms, preview and edit the results, approve selected items, publish them, or export them as drafts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tang-vu/social-posting-skills/social-campaign
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 tang-vu/social-posting-skills --skill social-campaign
Clone the repo
git clone --depth 1 https://github.com/tang-vu/social-posting-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 social-campaign

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tang-vu/social-posting-skills/social-campaign"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/social-campaign.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,118 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 $0.00030 $0.01118
Opus 5.5 $0.00012 $0.00447
Sonnet 5 $0.00006 $0.00224
Haiku 4.5 $0.00003 $0.00112

Measured 6d ago against content hash 38be04a8f0e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-26, from the pricing page.

Security

Grade A, and why

social-campaign 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 6d 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.

.agents/skills/social-campaign/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Social Campaign

Turn ONE source artifact into a safe, reviewable, platform-native distribution campaign. You are the content intelligence; the social-posting-skills CLI is the deterministic plumbing (validation, approval, receipts, drafts, publishing modes). The human approves before anything is published.

Pipeline

Source → Campaign intent → Content graph → Platform adaptations
→ Preview → Human approval → Publish or export draft → Observe → Learnings

Commands (use the CLI; do not hand-roll files)

npx social-posting-skills campaign create --source <artifact> [--preset oss-launch]
npx social-posting-skills campaign graph   <id>          # see the content graph
npx social-posting-skills campaign set-node <id> --id <node> --value "<text>"
npx social-posting-skills campaign adapt   <id>          # regenerate scaffolds
npx social-posting-skills campaign preview <id>          # THE approval package
npx social-posting-skills campaign approve <id> --items a,b | --all
npx social-posting-skills campaign publish <id> [--items a,b] [--mode ...]
npx social-posting-skills campaign export  <id>          # draft packages
npx social-posting-skills campaign record  <id> --item <i> (--url|--failed|--unknown|--partial)
npx social-posting-skills campaign observe <id> --url <u> --views n --likes n
npx social-posting-skills campaign learn   <id> --text "<lesson>" [--inferred]

Or the same operations as MCP tools (social-posting-skills mcp).

Your job at each step

  1. Source — accept README, CHANGELOG, release notes, blog post, URL, owner/repo@tag, npm:pkg, git:<range>, or pasted text. Never fetch private/authenticated URLs; the fetcher refuses private hosts anyway.

  2. Intent — ask if unclear: goal (launch/explain/milestone), audience, key message, disclosures ("I built this", "Open source", "Sponsored"). A campaign is not "post this everywhere" — pick platforms deliberately.

  3. Content graph — THIS IS WHERE QUALITY LIVES. The CLI extracts a scaffold graph (core-claim, context, proof, technical, demo, cta, links). Refine every extracted node: sharpen the claim, pick the 3 best proofs, keep ONE fact layer — every platform renders from this same graph, so fix facts once, not twelve times.

Read the full file on GitHub · 94 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 94 lines · 30 tokens per session scan A 38be04a8f0e8

Subscribe to this mod's changes

social-campaign is a skill published in the GitHub repository tang-vu/social-posting-skills (9 stars, last pushed 5d ago), licensed MIT. It adds 30 tokens to every session and 1,118 once invoked, about $0.0001 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 2026-09-20.