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 minhnv0807/ai-business-skills --skill 61-budget-planning-globalgit clone --depth 1 https://github.com/minhnv0807/ai-business-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/minhnv0807/ai-business-skills/61-budget-planning-global)<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/61-budget-planning-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/61-budget-planning-global/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/minhnv0807/ai-business-skills/61-budget-planning-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/61-budget-planning-global.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00159 | $0.02817 |
| Opus 5 | $0.00079 | $0.01409 |
| Sonnet 5 | $0.00032 | $0.00563 |
| Haiku 4.5 | $0.00016 | $0.00282 |
Grade A, and why
61-budget-planning-global 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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Budget Planning (Global)
A budget is not a fixed number — it is a decision tool: where you place bets and when you pull back. The leader must know total spend, ROI per channel, what to increase, and what to cut. Run
10-reverse-kpi-globalfirst to derive the minimum budget from the revenue target before allocating anything.
Information gathering
Read .agents/product-marketing-context-global.md, the marketing plan, and the previous period's report if available. If missing, ask up to 4 questions:
- Total budget and planning period? How much, for a month, a quarter, or a year (USD)?
- Revenue target for the period? Needed to compute marketing as a percent of revenue and the minimum viable budget.
- Active channels and last period's ROI? Meta / TikTok / Google / email + SMS / affiliates / agency — which has the best ROAS or CPA?
- Any large campaign needing a reserve? Launch, Black Friday / Cyber Monday, or another seasonal peak.
Principles
- Budget follows performance. Do not stay rigid to the opening plan. Channels that work get more; channels that do not get cut.
- Always hold 10-15% in reserve. Never allocate everything on day one. The reserve covers unexpected opportunities and incidents.
- Every dollar has a measurable KPI. "Branding you cannot measure" is not an acceptable line item.
- Do not spread evenly. Concentrate on the best-performing channel. New channels get a minimum test allocation (10-15%) first.
- Plan backwards from revenue, not from channels. The budget is the output of a revenue equation, not an arbitrary number.
- Do not divide the annual budget evenly across quarters. Median Meta CPM in Q4 runs roughly 26% above Q1 (
references/benchmarks-global.md), so identical monthly spend buys materially less reach in Q4. Either front-load acquisition into cheap Q1 months or explicitly reserve a larger Q4 allocation for the same volume.
Workflow
1. Choose the budget-setting method
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 · 210 lines · 159 tokens per session scan A f3d3a71b2a13
61-budget-planning-global is a skill published in the GitHub repository minhnv0807/ai-business-skills (572 stars, last pushed 26d ago), licensed MIT. It adds 159 tokens to every session and 2,817 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
lbo-model
Build leveraged buyout workbooks with IRR/MOIC in Excel.
evm
Read-only EVM client: wallets, tokens, gas across 8 chains.
excel-author
Build auditable financial workbooks headless via openpyxl.
hyperliquid
Hyperliquid market data, account history, trade review.