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 Ad-Superpowers/ad-superpowers-plugin --skill meta-bid-strategy-selectorgit clone --depth 1 https://github.com/Ad-Superpowers/ad-superpowers-pluginWrote 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/ad-superpowers/ad-superpowers-plugin/meta-bid-strategy-selector)<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/meta-bid-strategy-selector"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/meta-bid-strategy-selector/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/ad-superpowers/ad-superpowers-plugin/meta-bid-strategy-selector"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/meta-bid-strategy-selector.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 | $0.00095 | $0.02953 |
| Opus 5.5 | $0.00038 | $0.01181 |
| Sonnet 5.5 | $0.00019 | $0.00591 |
| Haiku 4.5 | $0.00010 | $0.00295 |
Grade A, and why
meta-bid-strategy-selector 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 1mo 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 — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bid Strategy Selector
Advisor for selecting the optimal Meta Ads bid strategy based on goals, budget, and account situation.
Quick Selection Guide
WHAT IS YOUR PRIMARY GOAL?
│
├─► Maximum volume (leads/sales)
│ └─► LOWEST COST (Highest Volume)
│
├─► Keep CPA under control
│ └─► COST CAP
│
├─► Strict margin requirements
│ └─► BID CAP
│
└─► Profitability focus (e-commerce)
└─► ROAS GOAL (Minimum ROAS)
Bid Strategy Overview
| Strategy | Control | Risk | Best For | Min. Data |
|---|---|---|---|---|
| Lowest Cost | None | Low | Beginners, volume | Little |
| Cost Cap | CPA target | Medium | CPA constraints | 50+ conv/week |
| Bid Cap | Max bid | High | Competitive niches | 100+ conv/week |
| ROAS Goal | Min ROAS | Medium | Profitability | 50+ conv/week + CAPI |
Lowest Cost (Highest Volume)
How It Works
Meta gets as many results as possible within your budget, without a CPA limit.
When to Use
- New accounts with little historical data
- Learning phase (first 2-4 weeks)
- Volume more important than efficiency
- Unsure about realistic CPA targets
- Brand awareness campaigns
When NOT to Use
- Strict CPA requirements
- Limited budget with margin pressure
- Competitive auctions where CPA can spike
Setup
Campaign Settings:
├── Budget optimization: Advantage Campaign Budget or Ad Set Budget
├── Bid strategy: Highest Volume
├── No cost controls: Leave empty
└── Conversion goal: Select optimization event
Expectations
- CPA fluctuates day-to-day
- AI optimizes for volume, not efficiency
- Best baseline for new campaigns
Cost Cap
How It Works
Meta keeps average CPA around your target. May temporarily exceed but balances over time.
When to Use
- Known target CPA (from historical data)
- Lead gen with fixed lead value
- E-commerce with known break-even CPA
- Scaling while monitoring efficiency
When NOT to Use
- No idea of realistic CPA
- Cap set too low (delivery stops)
- New accounts without benchmarks
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.
- 1mo ago First seen · 405 lines · 95 tokens per session scan A 21f9c73ce602
meta-bid-strategy-selector is a skill published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 29d ago), licensed MIT. It adds 95 tokens to every session and 2,953 once invoked, about $0.0004 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 2026-09-11.
Other skills, from other repositories
budget-pacing
A budgeting procedure that compares spending so far this month with the monthly target and forecasts the likely month-end total.
ai-api-alternative-ai-hive
A billing-comparison guide for moving between AI API providers, which are services that let software send requests to AI models.
ai-api-live-price-snapshot-ai-hive
A guide for recording current AI model prices and setting spending limits before submitting generation jobs.
ai-hive-boss-fundraising-deck
A fundraising business-plan workflow that organizes a company’s problem, solution, market, progress, team, and use of funds into an evidence-based investor presentation.
sealeap-baize-amazon-inventory-profit-balance
A framework for balancing Amazon inventory, advertising spend, cash use, and profit for each product. It uses sales capacity, costs, conversion, stock timing, and risk across a product portfolio.
sealeap-pixiu-amazon-finance-profit-tax
A financial review workflow for Amazon sellers brings sales, fees, taxes, advertising, shipping, returns, exchange rates, and inventory funding into one view. It calculates contribution profit, cash needs, and stress cases.