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 kevinnft/ai-agent-skills --skill social-media-account-auditgit clone --depth 1 https://github.com/kevinnft/ai-agent-skillsWrote 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/kevinnft/ai-agent-skills/social-media-account-audit)<a href="https://agentmods.dev/skills/kevinnft/ai-agent-skills/social-media-account-audit"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/social-media-account-audit/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/kevinnft/ai-agent-skills/social-media-account-audit"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/social-media-account-audit.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 | $0.00033 | $0.02186 |
| Opus 5.5 | $0.00013 | $0.00874 |
| Sonnet 5.5 | $0.00007 | $0.00437 |
| Haiku 4.5 | $0.00003 | $0.00219 |
Grade A, and why
social-media-account-audit scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -L -A "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" \ How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Media Account Audit
When to Use
- User shares analytics screenshots (LIVE stats, dashboard data, engagement metrics)
- User asks "why is my account/LIVE performing badly?"
- User shares a TikTok/Instagram profile link for review
- User wants to compare past vs current performance
- User asks for growth strategy based on data
Workflow Overview
1. Scrape profile data (if link provided)
2. Extract metrics from screenshots (if provided)
3. Calculate health ratios
4. Diagnose root causes
5. Deliver actionable recommendations
Step 1: Scrape TikTok Profile Data
Fetch HTML
curl -s -L -A "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" \
"https://www.tiktok.com/@USERNAME" -o /tmp/tiktok_profile.html
Extract Basic Stats (grep approach — fast)
grep -oP '"uniqueId":"[^"]*"|"nickname":"[^"]*"|"signature":"[^"]*"|"followerCount":\d+|"followingCount":\d+|"heartCount":\d+|"videoCount":\d+|"verified":[a-z]+' /tmp/tiktok_profile.html
Extract Full Profile (Python — comprehensive)
import json, re
from datetime import datetime
with open('/tmp/tiktok_profile.html') as f:
html = f.read()
match = re.search(
r'<script id="__UNIVERSAL_DATA_FOR_REHYDRATION__"[^>]*>(.*?)</script>',
html, re.DOTALL
)
data = json.loads(match.group(1))
scope = data['__DEFAULT_SCOPE__']
user_info = scope['webapp.user-detail']['userInfo']
user = user_info['user']
stats = user_info['stats']
# Key fields
print(f"Username: @{user['uniqueId']}")
print(f"Bio: {user['signature']}")
print(f"Created: {datetime.fromtimestamp(int(user['createTime']))}")
print(f"Category: {user.get('commerceUserInfo', {}).get('category', 'N/A')}")
print(f"Commerce User: {user.get('commerceUserInfo', {}).get('commerceUser', False)}")
print(f"TT Seller: {user.get('ttSeller', False)}")
print(f"Verified: {user['verified']}")
print(f"Followers: {stats['followerCount']:,}")
print(f"Following: {stats['followingCount']:,}")
print(f"Likes: {stats['heartCount']:,}")
print(f"Videos: {stats['videoCount']}")
What ships with it
2 files 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.
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.
- 1mo ago First seen · 199 lines · 33 tokens per session scan A e81252626431
social-media-account-audit is a skill published in the GitHub repository kevinnft/ai-agent-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 2,186 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
social-commerce
Sync your catalog to Instagram, TikTok, and Facebook to enable shoppable posts and in-app checkout directly from your social content.
legal-issue-research
A systematic research assistant for Chinese law. It searches laws, regulations, judicial interpretations, guiding cases, and typical cases, then organizes the legal sources and how they relate.
infringement-triage-bossmann007
Infringement triage across trademark, copyright, patent, and trade secret — a flag list with the factors cutting each way, not a finding. Use when assessing whether someone is infringing your IP or whether you might be infringing theirs, when a knockoff or copycat surfaces, or when deciding whether a matter is worth…
takedown-bossmann007
Draft a notificação de retirada de conteúdo (Marco Civil), triage one you received, or draft a resposta/contranotificação. Use when asserting copyright under Lei 9.610/1998 through a Marco Civil notice with the fair-use-analog and good-faith gates, when an incoming notice needs triage into comply / contest / engage /…
paper-to-cn-patent
Convert finished research papers, figures, and author notes into Chinese invention patent application drafts. Use when Codex needs to rewrite a paper as a China invention patent, draft claims, abstract, specification sections, and figure descriptions, assess whether the source materials are sufficient for patent…
agency-legal-compliance-checker-2
Expert legal and compliance specialist ensuring business operations, data handling, and content creation comply with relevant laws, regulations, and industry standards across multiple jurisdictions.