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 brainbytes-dev/everything-claude-marketing --skill social-tiktokgit clone --depth 1 https://github.com/brainbytes-dev/everything-claude-marketingWrote 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/brainbytes-dev/everything-claude-marketing/social-tiktok)<a href="https://agentmods.dev/skills/brainbytes-dev/everything-claude-marketing/social-tiktok"><img src="https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/social-tiktok/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/brainbytes-dev/everything-claude-marketing/social-tiktok"><img src="https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/social-tiktok.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 | $0.00028 | $0.02799 |
| Opus 5.5 | $0.00011 | $0.01120 |
| Sonnet 5.5 | $0.00006 | $0.00560 |
| Haiku 4.5 | $0.00003 | $0.00280 |
Grade A, and why
social-tiktok 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 2mo 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TikTok Content Strategy
When to Activate
Use this skill when:
- Creating TikTok videos or content strategy
- Identifying and adapting trends for a brand or creator
- Writing hooks and scripts for TikTok content
- Building a TikTok presence from zero
- Integrating TikTok into a broader marketing strategy
- Advising on TikTok Shop and commerce features
First Questions
Before creating TikTok content, clarify:
- What is the account's niche or industry?
- Who is the target audience? (Age, interests, pain points)
- What is the primary goal? (Brand awareness, sales, community, traffic)
- Is the creator comfortable on camera, or is this faceless content?
- What resources are available? (Production quality, time, team)
- Is this a new account or established? (Current follower count, typical views)
- Is TikTok Shop relevant for this brand?
Core Rules
- The first 1-3 seconds determine everything. If you lose them in the hook, nothing else matters.
- Watch time is the algorithm's god metric. Completion rate and replay rate drive distribution.
- Native content wins. Polished, ad-looking content gets scrolled past. Raw, authentic, slightly imperfect content performs.
- Trends are accelerators, not strategies. Use trends to boost reach, but build a foundation of original content.
- Post volume matters early. When building, 1-3 posts per day teaches you what works faster.
- TikTok is a search engine for Gen Z. Keyword-optimize everything.
- Shares are the strongest signal. Content people send to friends goes viral.
- Every video should work without sound. On-screen text is non-negotiable.
TikTok Algorithm Deep Dive
How Distribution Works
- Initial test: Your video is shown to a small group (~300-500 people), NOT necessarily your followers.
- Performance evaluation: The algorithm measures watch time, completion rate, replays, shares, comments, likes (in roughly that order of importance).
- Expansion: If metrics are strong, the video is pushed to a larger audience (thousands, then tens of thousands, then hundreds of thousands).
- Plateau: Distribution stops when engagement ratios drop below the threshold for the next tier.
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.
- 2mo ago First seen · 254 lines · 28 tokens per session scan A c3014ffa93ec
social-tiktok is a skill published in the GitHub repository brainbytes-dev/everything-claude-marketing (10 stars, last pushed 7mo ago), licensed MIT. It adds 28 tokens to every session and 2,799 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 2026-09-03.
social-tiktok compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| social-tiktokbrainbytes-dev/everything-claude-marketing | Skill | 10 | 7mo ago | MIT | A | 28 | Claude Code |
| amazon-reviews-api-skillbrowser-act/skills | Skill | 6.3k | 2d ago | MIT | A | 124 | Claude Code, Codex |
| amazon-competitor-analyzerbrowser-act/skills | Skill | 6.3k | 2d ago | MIT | A | 48 | Claude Code, Codex |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | 2d ago | MIT | A | 60 | Claude Code |
| food-orderBitterbot-AI/bitterbot-desktop | Skill | 2.5k | yesterday | MIT | A | 53 | Claude Code, Codex |
| external-purchasesrshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 76 | Claude Code |
| Product Photoshoot Workflowjau123/MeiGen-AI-Design-MCP | Skill | 1.8k | yesterday | MIT | A | 111 | Claude Code |