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 agentmods add rules/kubachour/mobile-growth-mcp/knowledge-basegit clone --depth 1 https://github.com/kubachour/mobile-growth-mcpWrote 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/rules/kubachour/mobile-growth-mcp/knowledge-base)<a href="https://agentmods.dev/rules/kubachour/mobile-growth-mcp/knowledge-base"><img src="https://agentmods.dev/badge/rules/kubachour/mobile-growth-mcp/knowledge-base.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00810 |
| Opus 5 | $0.00014 | $0.00405 |
| Sonnet 5 | $0.00005 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
knowledge-base 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 4d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using the Knowledge Base
The knowledge base contains curated insights from industry experts about mobile advertising, focused on subscription apps and user acquisition across Meta, Google, and TikTok.
Tools
search_insights
Semantic + keyword hybrid search. Best for specific questions.
search_insights(query="how to structure Meta campaigns for subscription apps", topics=["campaign_architecture"], limit=5)
list_insights
Browse everything. Good for seeing what's available.
list_insights(topic="creative_strategy")
get_insight
Read the full content of a specific insight by slug.
get_insight(id="mb-li-002")
When to Use
- User asks "how should I..." or "what are best practices for..." →
search_insights - User asks about a specific insight ID →
get_insight - User wants to browse what's available →
list_insights - Running a report and need to cite recommendations →
get_insightfor the specific IDs
Key Insight IDs to Know
These are the most frequently referenced insights across reports:
| ID | Author | Topic |
|---|---|---|
| wk-tw-001 | William Kast | 4 diagnostic metric patterns |
| wk-tw-002 | William Kast | ROAS troubleshooting decision tree |
| ds-pt-001 | Dara Saeed | Primary vs secondary metrics |
| ds-pt-003 | Dara Saeed | Frequency >5 = saturation |
| ds-pt-004 | Dara Saeed | Don't force spend to low-spend winners |
| ds-pt-005 | Dara Saeed | ASC needs 20+ creatives |
| ds-pt-008 | Dara Saeed | Analyze first, optimize second |
| mb-li-001 | Marcus Burke | Creative unlocks scale |
| mb-li-002 | Marcus Burke | Deconsolidation |
| mb-li-003 | Marcus Burke | Signal quality > volume |
| mb-li-005 | Marcus Burke | One price = one audience |
| mb-li-006 | Marcus Burke | App vs Web campaign demographics |
| mb-li-008 | Marcus Burke | Value Rules (age/gender) |
| mb-li-009 | Marcus Burke | Placement Value Rules |
| mb-li-010 | Marcus Burke | Age-based conversion rates |
| mb-cd-001 | Marcus Burke | EAC for subscription apps |
| oh-li-001 | Olly Hudson | Andromeda: first 3 seconds matter |
| oh-li-003 | Olly Hudson | Persona-based ads unlock audiences |
| lp-pt-001 | Lauren Petrullo | 25% visual difference required |
| lp-pt-002 | Lauren Petrullo | Minimum 6 creatives per offering |
| lp-pt-003 | Lauren Petrullo | Contribution vs attribution |
| jl-pt-004 | Jon Loomer | Don't kill ads if aggregate is good |
| vs-nt-001 | Virendra Shekhawat | Meta auto-shifts spend |
| vs-nt-002 | Virendra Shekhawat | Don't re-test degraded creatives |
| br-li-001 | Ben Radack | CBO scaling with winner rotation |
| br-li-002 | Ben Radack | Zombie campaign |
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.
- 4d ago First seen · 78 lines · 27 tokens per session scan A e3f9ff82c7ee
knowledge-base is a cursor rule published in the GitHub repository kubachour/mobile-growth-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 810 once invoked, about $0.0001 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.