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 fintech-campaign-designergit 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/fintech-campaign-designer)<a href="https://agentmods.dev/skills/thaolst/ai-growth-agents-for-marketers/fintech-campaign-designer"><img src="https://agentmods.dev/badge/skills/thaolst/ai-growth-agents-for-marketers/fintech-campaign-designer/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/fintech-campaign-designer"><img src="https://agentmods.dev/badge/skills/thaolst/ai-growth-agents-for-marketers/fintech-campaign-designer.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 | $0.00062 | $0.00745 |
| Opus 5 | $0.00031 | $0.00373 |
| Sonnet 5 | $0.00012 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
fintech-campaign-designer 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 11d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fintech Campaign Designer
Growth strategist for fintech campaigns in Southeast Asia.
Checks
.agents/product-marketing-context.mdfor all product context. Checks.agents/growth-metrics-context.mdfor live metric baselines. If growth-mcp is connected, pulls past campaign performance.
Fintech-Specific Frameworks
1. Promotion Level Matrix (S/M/L/XL)
| Level | Budget | Reach | Typical Duration | Example |
|---|---|---|---|---|
| S | < $5K | 50K-200K users | 3-7 days | Flash voucher, daily login bonus |
| M | $5-20K | 200K-1M users | 7-14 days | Weekly promotion, referral event |
| L | $20-100K | 1M-5M users | 14-30 days | Monthly campaign, seasonal event |
| XL | > $100K | 5M+ users | 30-60 days | Major holiday, platform-wide event |
2. Fintech Mechanic Types
- Top-up cashback (n% back when user tops up)
- Transaction discount (fee waiver or discount)
- Referral bonus (invite + earn)
- Loyalty points multiplier (Xu-like economy)
- Game-based reward (spin, scratch, lucky draw)
- Bundle (pay X get Y + Z)
- First-time user incentive (activation funnel)
3. Risk Checklist
- Budget capped per user? (prevent abuse)
- Minimum transaction value?
- Anti-fraud rules? (new account detection, device fingerprint)
- Slippage modeled? (budget unused = lower cost, lower reach)
- Cannibalization risk? (existing users vs new)
- Timezone aligned? (SEA has 3 timezones)
- Regulatory compliance? (promotion disclosure, T&C)
4. SEA Market Considerations
- Vietnam: Cash-heavy, high push notification CTR (25-40%), voucher mechanics preferred over cashback
- Indonesia: High mobile-first, super app dominant (Gojek, Shopee), game mechanics perform well
- Philippines: Remittance + bill pay dominant, SMS still effective
- Thailand: Line ecosystem, social commerce, QR payments growing
Related Skills
- campaign-brief — writes full brief
- voucher-mechanic-designer — specific mechanic design
- campaign-planning — fits into calendar
- meu-planning — reverse-plan from MEU target
- growth-mcp-connect — pulls live metrics
- retention-analyzer — measures post-campaign retention
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.
- 11d ago First seen · 77 lines · 62 tokens per session scan A 5b7a5fed082e
fintech-campaign-designer is a skill published in the GitHub repository thaolst/ai-growth-agents-for-marketers (5 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 745 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
fundos-covenants
Portfolio company covenant monitoring for private credit and leveraged buyout funds — leverage and coverage covenant computation, cushion and RAG status, breach detection, equity cure rights, lender notification, and waiver or amendment workflow, against live FundOS covenant records. Use when checking covenant…
fundos-fund-admin
Fund administration for emerging VC, PE, and private credit managers — NAV, capital accounts, DPI/RVPI/TVPI, IRR, management fees, and ILPA reporting standards, computed from live FundOS fund data. Use when asked for fund metrics, a fund snapshot, NAV, capital account detail, or fund-level financials. Triggers on…
fundos-lp-reporting
Drafting communications to limited partners — quarterly reports, exit and write-down notices, capital call cover letters, and ad-hoc investor updates — grounded in live FundOS fund and LP data. Use when drafting anything that will be sent to LPs. Triggers on "draft LP update", "write to my LPs", "investor letter"…
fundos-waterfall
Private fund distribution waterfall mechanics — European and American structures, preferred return accrual, GP catch-up, carried interest, clawback, and exit sensitivity — computed against live FundOS fund data. Use when modelling distributions, working out LP/GP splits, running exit scenarios, or explaining carry…
fundos-vdr
Virtual data room and diligence workflow for fund managers — room inventory, document checklists and gap analysis, grounded document Q&A with citations, access control review, and engagement analytics, against live FundOS data rooms. Use when organizing a data room, finding missing diligence documents, asking…
fundos
Connect to FundOS, the fund-operations system of record for VC, private equity, and private credit managers — deals, LP investors, capital calls, NAV, waterfalls, covenants, and the data room. Use this skill to reach live fund data before answering ANY question about a fund's LPs, portfolio, capital, performance…