reports

reports is a cursor rule for Cursor from kubachour/mobile-growth-mcp. It costs 32 tokens per session (1,161 once invoked), scanned A, original, MIT.

A set of instructions for producing reports from Meta advertising account data. Meta ads are paid campaigns run on Facebook, Instagram, and related services.

In plain words
What is it for?
Use it for ad-account audits, fatigue checks, performance snapshots, creative and placement analysis, audience reports, and architecture reviews.
Why use it?
It defines which data to request and how to examine issues such as ad fatigue, changing performance, placements, audiences, and campaign structure.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Install

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.

agentmods
npx agentmods add rules/kubachour/mobile-growth-mcp/reports
Clone the repo
git clone --depth 1 https://github.com/kubachour/mobile-growth-mcp

Made for: Cursor.

Wrote 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.

agentmods badge for reports

README.md
[![agentmods](https://agentmods.dev/badge/rules/kubachour/mobile-growth-mcp/reports.svg)](https://agentmods.dev/rules/kubachour/mobile-growth-mcp/reports)
Your own site
<a href="https://agentmods.dev/rules/kubachour/mobile-growth-mcp/reports"><img src="https://agentmods.dev/badge/rules/kubachour/mobile-growth-mcp/reports.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,161 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.01161
Opus 5 $0.00016 $0.00580
Sonnet 5 $0.00006 $0.00232
Haiku 4.5 $0.00003 $0.00116

Measured 6d ago against content hash d536fb39401d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reports 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 6d 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.

.cursor/rules/reports.mdc · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Running Reports

Reports are pre-built analysis workflows. Each combines Meta API tool calls with knowledge base insights for grounded recommendations.

Always ask for the ad_account_id if not provided.

Report Quick Reference

Ad Fatigue Report

When: User asks about creative fatigue, frequency issues, declining CTR, or rising CPA.

Use get_meta_ad_fatigue tool directly — it's a single API call that returns a full analysis.

Key thresholds: frequency >3 (warning), >5 (critical). CTR decline >30% from peak. CPA rising >20%.

Diagnosis framework [wk-tw-001]:

  • High frequency + rising CPA → audience saturation
  • Declining CTR + rising CPA → creative fatigue

Recommendations cite: wk-tw-001, ds-pt-003, vs-nt-001, vs-nt-002, oh-li-001, lp-pt-001.

Weekly Performance Snapshot

When: User wants a performance overview, Monday check-in, or week-over-week comparison.

2 API calls:

  1. get_meta_insights(date_preset="this_week_mon_today", level="campaign")
  2. get_meta_insights(date_preset="last_week_mon_sun", level="campaign")

Compute deltas per campaign, apply Kast's 4 diagnostic patterns [wk-tw-001]:

  1. Frequency↑ + CPA↑ → creative fatigue
  2. CPM↑ + CPA↑ → audience saturation
  3. CPA↑ + CVR↓ → ad-to-LP mismatch
  4. CTR↓ + CPA↑ → creative fatigue

End with: "Analyze first, optimize second" [ds-pt-008].

Creative Performance Report

When: User wants to know which ads are working, which to pause, creative health.

1 API call: get_meta_insights(level="ad", sort="spend_descending", limit=50)

Categorize each ad:

  • Scaling: High spend, good CPA → let it run [mb-li-001]
  • Promising: Low spend, good CPA → don't force spend [ds-pt-004]
  • Contributing: Low conversions but ad set is healthy → halo role [jl-pt-004, lp-pt-003]
  • Fatiguing: Frequency >3, CTR declining → prepare replacement [oh-li-001]
  • Dead weight: High spend, CPA >2x target → pause only if ad set also bad [jl-pt-004]

Read the full file on GitHub · 108 lines

Changes

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.

  1. 6d ago First seen · 108 lines · 32 tokens per session scan A d536fb39401d

Subscribe to this mod's changes

reports is a cursor rule published in the GitHub repository kubachour/mobile-growth-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,161 once invoked, about $0.0002 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.