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 thaolst/ai-growth-agents-for-marketers --skill multi-agent-workflowgit clone --depth 1 https://github.com/thaolst/ai-growth-agents-for-marketersWrote 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/thaolst/ai-growth-agents-for-marketers/multi-agent-workflow)<a href="https://agentmods.dev/skills/thaolst/ai-growth-agents-for-marketers/multi-agent-workflow"><img src="https://agentmods.dev/badge/skills/thaolst/ai-growth-agents-for-marketers/multi-agent-workflow/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/thaolst/ai-growth-agents-for-marketers/multi-agent-workflow"><img src="https://agentmods.dev/badge/skills/thaolst/ai-growth-agents-for-marketers/multi-agent-workflow.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 | $0.00087 | $0.00413 |
| Opus 5 | $0.00044 | $0.00206 |
| Sonnet 5 | $0.00017 | $0.00083 |
| Haiku 4.5 | $0.00009 | $0.00041 |
Grade A, and why
multi-agent-workflow 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 9d 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.
What it actually says
Multi-Agent Workflow: Research + Plan
Hai giai đoạn nối tiếp nhau. Output của giai đoạn 1 là input của giai đoạn 2.
Giai đoạn 1 — Research Agent
Đọc data campaign và xuất ra JSON có cấu trúc:
{
"top_performing_mechanics": [],
"underperforming_areas": [],
"segment_insights": {},
"recommended_focus": [],
"data_gaps": []
}
Chỉ trả về JSON, không giải thích thêm.
Giai đoạn 2 — Strategy Agent
Nhận JSON từ giai đoạn 1. Dựa trên analysis, viết campaign plan với:
- Strategy tổng thể và lý do
- Campaign cụ thể với mechanic, budget, timeline
- Giải thích tại sao mỗi quyết định dựa trên insight từ giai đoạn 1
Nguyên tắc
Không bỏ qua data gaps từ giai đoạn 1. Mọi quyết định trong plan phải có dẫn chứng từ analysis.
English
Two stages in sequence. Output of stage 1 is input of stage 2.
Stage 1: Analyze campaign data, return structured JSON with top performing mechanics, underperforming areas, segment insights, recommended focus, and data gaps.
Stage 2: Use the JSON analysis to build a specific campaign plan. Every decision must reference insights from stage 1.
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.
- 9d ago First seen · 57 lines · 87 tokens per session scan A 4b2c9b94f08f
multi-agent-workflow is a skill published in the GitHub repository thaolst/ai-growth-agents-for-marketers (5 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 413 once invoked, about $0.0004 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
find-leads
Find qualified B2B leads with OpenOutreach — run openoutreach find N [emails], read the CSV it prints on stdout, and hand the rows to whatever sends. Use when the user wants leads, prospects, an ICP-matched contact list, or asks what a campaign already has. Also covers first-run setup (openoutreach init), openoutreach…
audit
Analyze whether TikTok or Instagram search traffic is a viable growth channel for your business. Uses ScaleBrick's framework to evaluate demand, competition, content fit, and intent categories. Ends with a go/no-go recommendation.
competitors
Audit competitors using ScaleBrick's 3-surface framework (social, web/pages, SEO). Categorizes their pricing, features, and landing pages. Identifies gaps you can exploit, positioning angles no one is claiming, and specific moves you can make this week.
keywords
Research high-intent TikTok and Instagram search keywords using ScaleBrick's framework. Returns categorized keywords with intent type, search volume estimate, difficulty score, and content angle for each.
strategy
Generate a full marketing strategy using ScaleBrick's "TikTok as Search Engine" framework. Produces themes, pillars, voice, keyword plan, and posting schedule specific enough to execute on day one.
11-ai-growth
Prompt để tận dụng AI trong growth marketing. Từ personalization, segmentation, campaign optimization đến predictive analytics và gamification.