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.
npx skills add aryaminus/socials-assistant --skill socials-connectgit clone --depth 1 https://github.com/aryaminus/socials-assistantWrote 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.
[](https://agentmods.dev/skills/aryaminus/socials-assistant/socials-connect)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Call
socials-mcp:connection_status. Skip any platform alreadyok: true. - If a connect tool returns
missing_app_credentials, walk the user through the matching guide (repodocs/):- 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)
- YouTube →
- 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)
- Tell the user: "A consent screen will open — approve it and come back."
- 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. - After they finish in the browser, call
socials-mcp:connection_statusto confirmok: true. connect_metaconnects Instagram AND Facebook in one flow.
First data pull
- Call
socials-mcp:snapshot(default 28-day lookback). Report per-platform row counts. - For TikTok depth: ask for their weekly TikTok Studio export (Studio → Analytics → export video-stats CSV), then call
socials-mcp:import_tiktok_csvwith 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. - 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.
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.
- 8d ago First seen · 49 lines · 68 tokens per session scan A e535c1bb6569
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.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
grounded-citations
Ground answers and documents in cited, verifiable sources.
hermes-agent-skill-authoring
Author in-repo SKILL.md files: frontmatter and structure.
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
flash-attention
Speed up long-sequence transformer training and inference.