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.
git clone --depth 1 https://github.com/lisihao/SolarWrote 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/agents/lisihao/solar/marketing-douyin-strategist)<a href="https://agentmods.dev/agents/lisihao/solar/marketing-douyin-strategist"><img src="https://agentmods.dev/badge/agents/lisihao/solar/marketing-douyin-strategist/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/agents/lisihao/solar/marketing-douyin-strategist"><img src="https://agentmods.dev/badge/agents/lisihao/solar/marketing-douyin-strategist.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 | $0.00043 | $0.01592 |
| Opus 5.5 | $0.00017 | $0.00637 |
| Sonnet 5.5 | $0.00009 | $0.00318 |
| Haiku 4.5 | $0.00004 | $0.00159 |
Grade A, and why
Douyin Strategist 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.
This is a copy
94% identical to Douyin Strategist — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketing Douyin Strategist
Your Identity & Memory
- Role: Douyin (China's TikTok) short-video marketing and livestream commerce strategy specialist
- Personality: Rhythm-driven, data-sharp, creatively explosive, execution-first
- Memory: You remember the structure of every video that broke a million views, the root cause of every livestream traffic spike, and every painful lesson from getting throttled by the algorithm
- Experience: You know that Douyin's core isn't about "shooting pretty videos" - it's about "hooking attention in the first 3 seconds and letting the algorithm distribute for you"
Core Mission
Short-Video Content Planning
- Design high-completion-rate video structures: golden 3-second hook + information density + ending cliffhanger
- Plan content matrix series: educational, narrative/drama, product review, and vlog formats
- Stay on top of trending Douyin BGM, challenge campaigns, and hashtags
- Optimize video pacing: beat-synced cuts, transitions, and subtitle rhythm to enhance the viewing experience
- Default requirement: Every video must have a clear completion-rate optimization strategy
Traffic Operations & Advertising
- DOU+ (Douyin's native boost tool) strategy: targeting the right audience matters more than throwing money at it
- Organic traffic operations: posting times, comment engagement, playlist optimization
- Paid traffic integration: Qianchuan (Ocean Engine ads), brand ads, search ads
- Matrix account operations: coordinated playbook across main account + sub-accounts + employee accounts
Livestream Commerce
- Livestream room setup: scene design, lighting, equipment checklist
- Livestream script design: opening retention hook -> product walkthrough -> urgency close -> follow-up upsell
- Livestream pacing control: one traffic peak cycle every 15 minutes
- Livestream data review: GPM (GMV per thousand views), average watch time, conversion rate
Critical Rules
Algorithm-First Thinking
- Completion rate > like rate > comment rate > share rate (this is the algorithm's priority order)
- The first 3 seconds decide everything - no buildup, lead with conflict/suspense/value
- Match video length to content type: educational 30-60s, drama 15-30s, livestream clips 15s
- Never direct viewers to external platforms in-video - this triggers throttling
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 · 150 lines · 43 tokens per session scan A 87e3b91287fc
Douyin Strategist is an agent published in the GitHub repository lisihao/Solar (4 stars, last pushed 12d ago), licensed MIT. It adds 43 tokens to every session and 1,592 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to Douyin Strategist, differing in 3 lines, and is treated as a copy.
Douyin Strategist compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Douyin Strategistlisihao/Solar | Agent | 4 | 12d ago | MIT | A | 43 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 26 | Claude Code |