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 skills/citedy/adclaw/ads-applenpx skills add citedy/adclaw --skill ads-applegit clone --depth 1 https://github.com/citedy/adclawWrote 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/citedy/adclaw/ads-apple)<a href="https://agentmods.dev/skills/citedy/adclaw/ads-apple"><img src="https://agentmods.dev/badge/skills/citedy/adclaw/ads-apple.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 5.1 | $0.00080 | $0.02004 |
| Opus 5 | $0.00040 | $0.01002 |
| Sonnet 5 | $0.00016 | $0.00401 |
| Haiku 4.5 | $0.00008 | $0.00200 |
Grade A, and why
ads-apple 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.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Search Ads (ASA) Deep Analysis
Process
- Collect ASA account data (exports from Apple Search Ads dashboard or pasted metrics)
- Identify active placement types (Search Results, Search Tab, Today Tab, Product Pages)
- Evaluate all applicable checks as PASS, WARNING, or FAIL
- Calculate ASA Health Score (0-100)
- Generate findings report with action plan
What to Analyze
Campaign Structure (25% weight)
BOFU; Bottom of Funnel (Search Results, Exact Match brand)
- Brand keyword campaign present (own app name + misspellings)
- Competitor campaign present (competitor app names as keywords)
- Category campaigns targeting high-intent generic terms (e.g. "workout app", "budget tracker")
MOFU; Middle of Funnel (Search Match / broad discovery)
- Search Match campaigns active in at least one ad group for discovery
- Search Match ad groups isolated from Exact Match (separate ad groups; never mix)
- Search Terms Report reviewed to mine converting queries for Exact Match promotion
Campaign Architecture Rules:
- Brand / Category / Competitor should be separate campaigns (different CPT bids, budgets)
- Search Match ad groups isolated from manual keyword ad groups; NEVER mix in same ad group
- Goal: let Search Match discover, then promote winners to Exact Match campaigns
Bid Health (20% weight)
CPT (Cost Per Tap) vs Install Rate by Match Type:
- CPT vs category benchmarks (see Benchmarks section below)
- TTR (Tap-Through Rate): benchmark >2.5% for Search Results, >1.5% for Search Tab
- Conversion Rate (tap → install): benchmark 50-65% for brand terms, 20-40% for category
- CPT/CPG (Cost Per Goal): compare against target CPI/CPA from MMP
Bid Strategy:
- Manual CPT bidding appropriate? (Or use Apple's CPA Goals auto-bidding for scaled accounts)
- CPA Goals available at campaign level; evaluate if conversion volume supports it (>100 installs/month per campaign)
- Are bids differentiated by match type? (Brand Exact > Category Exact > Search Match)
- Keyword-level CPT bids set, not just ad group default?
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.
- 6d ago First seen · 185 lines · 80 tokens per session scan A d2b1eb3b3ccb
ads-apple is a skill published in the GitHub repository citedy/adclaw (35 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 2,004 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
skill-creator
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
update-setup
One-time setup wizard for the nanobot upgrade skill. Triggers: setup update, configure update, 设置更新, 初始化更新.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
cron
Schedule reminders and recurring tasks.
weather
Get current weather and forecasts (no API key required).