socials-connect

socials-connect is a skill for Claude Code from aryaminus/socials-assistant. It costs 68 tokens per session (789 once invoked), scanned A, original, MIT.

A guided account-connection workflow for linking TikTok, Instagram, Facebook, and YouTube to a social-media analytics vault through official OAuth, a permission system for account access.

In plain words
What is it for?
It helps set up the analytics vault, connect accounts, repair connections, store developer-app credentials, and establish the TikTok Studio CSV routine.
Why use it?
It removes the need to manage each platform connection separately and helps identify missing app credentials or expired links.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the socials-assistant plugin — 6 skills, 1 MCP server shipped together

Good fit It helps set up the analytics vault, connect accounts, repair connections, store developer-app credentials, and establish the TikTok Studio CSV routine.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aryaminus/socials-assistant/socials-connect
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 aryaminus/socials-assistant --skill socials-connect
Clone the repo
git clone --depth 1 https://github.com/aryaminus/socials-assistant

Made for: Claude Code.

Or install socials-assistant, the plugin that ships this one along with the rest of its 6 skills, 1 MCP server.

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 socials-connect

README.md
[![agentmods](https://agentmods.dev/badge/skills/aryaminus/socials-assistant/socials-connect/github.svg)](https://agentmods.dev/skills/aryaminus/socials-assistant/socials-connect)
Your own site
<a href="https://agentmods.dev/skills/aryaminus/socials-assistant/socials-connect"><img src="https://agentmods.dev/badge/skills/aryaminus/socials-assistant/socials-connect/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 socials-connect

Your own site · 80×15
<a href="https://agentmods.dev/skills/aryaminus/socials-assistant/socials-connect"><img src="https://agentmods.dev/badge/skills/aryaminus/socials-assistant/socials-connect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 789 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 $0.00068 $0.00789
Opus 5 $0.00034 $0.00394
Sonnet 5 $0.00014 $0.00158
Haiku 4.5 $0.00007 $0.00079

Measured 8d ago against content hash e535c1bb6569, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

socials-connect 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 8d 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/socials-connect/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

socials-connect — guided onboarding

Goal: all of the user's platforms connected to the socials-mcp vault through official OAuth flows, plus the weekly TikTok Studio CSV habit for Studio-only data. The agent drives every step; the human only approves browser consent screens.

Prerequisites check

  1. Call socials-mcp:connection_status. Skip any platform already ok: true.
  2. If a connect tool returns missing_app_credentials, walk the user through the matching guide (repo docs/):
    • YouTube → docs/onboarding-google.md (Google Cloud project, 3 APIs, OAuth desktop client)
    • Instagram + Facebook → docs/onboarding-meta.md (Meta app; IG Business/Creator account linked to a FB Page)
    • TikTok → docs/onboarding-tiktok.md (TikTok developer app, Login Kit scopes)
  3. Have them store credentials (they paste; never ask them to email or DM secrets): socials-mcp config set googleClientId <id> — or env vars (see AGENTS.md).

Connect flow (per platform)

  1. Tell the user: "A consent screen will open — approve it and come back."
  2. Call socials-mcp:connect_youtube / socials-mcp:connect_meta / socials-mcp:connect_tiktok. Each replies immediately: ✅ done, or ⏳ pending with the consent URL in the server log.
  3. After they finish in the browser, call socials-mcp:connection_status to confirm ok: true.
  4. connect_meta connects Instagram AND Facebook in one flow.

First data pull

  1. Call socials-mcp:snapshot (default 28-day lookback). Report per-platform row counts.
  2. For TikTok depth: ask for their weekly TikTok Studio export (Studio → Analytics → export video-stats CSV), then call socials-mcp:import_tiktok_csv with the path. Explain why: retention, traffic sources, search terms, and follower-hours are Studio-only — no official API exposes them; CSV is the compliant path.
  3. Verify with socials-mcp:top_content (days: 7).

Finish: build the creator profile

After the first snapshot, offer to build the tuning profile (socials-mcp:profile_get → if empty): auto-fill audience_summary from socials-mcp:audience_overview and content_series from socials-mcp:top_content patterns, then ask only the 4 human-only questions — niche, tone, goals, rate floor — and save with socials-mcp:profile_set. This is what makes every other skill sound like it knows the creator.

Read the full file on GitHub · 49 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. 8d ago First seen · 49 lines · 68 tokens per session scan A e535c1bb6569

Subscribe to this mod's changes

socials-connect is a skill published in the GitHub repository aryaminus/socials-assistant (0 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 789 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 2026-08-31.