CLAUDE LABJP
FORK — Claude Code 2.1.212 changes what /fork does: it copies your conversation into a new background session with its own row in claude agents, so you can keep working. The old in-session subagent is now /subtaskLIMITS — WebSearch calls are now capped at 200 per session by default, and subagent spawns get the same 200 ceiling, so a runaway search or delegation loop stops on its ownMCPBG — MCP tool calls running past two minutes now move to the background automatically, keeping the session usable. Tune the threshold with CLAUDE_CODE_MCP_AUTO_BACKGROUND_MSPLANFIX — Fixed plan mode auto-running file-modifying Bash commands such as touch and rm without a permission prompt or an SDK canUseTool callbackSONNET5 — Claude Sonnet 5 is running on introductory pricing of $2 per million input tokens and $10 per million output. After August 31 it moves to $3 and $15IPO — Bankers are reportedly lining up investor meetings for Anthropic ahead of a possible public listing as soon as OctoberFORK — Claude Code 2.1.212 changes what /fork does: it copies your conversation into a new background session with its own row in claude agents, so you can keep working. The old in-session subagent is now /subtaskLIMITS — WebSearch calls are now capped at 200 per session by default, and subagent spawns get the same 200 ceiling, so a runaway search or delegation loop stops on its ownMCPBG — MCP tool calls running past two minutes now move to the background automatically, keeping the session usable. Tune the threshold with CLAUDE_CODE_MCP_AUTO_BACKGROUND_MSPLANFIX — Fixed plan mode auto-running file-modifying Bash commands such as touch and rm without a permission prompt or an SDK canUseTool callbackSONNET5 — Claude Sonnet 5 is running on introductory pricing of $2 per million input tokens and $10 per million output. After August 31 it moves to $3 and $15IPO — Bankers are reportedly lining up investor meetings for Anthropic ahead of a possible public listing as soon as October
Articles/Claude.ai
Claude.ai/2026-05-30Intermediate

A Month of Reading App Store Connect Sales and Trends Weekly with Claude in Chrome

Notes from one month of switching App Store Connect Sales and Trends from a monthly glance to a weekly review, with Claude in Chrome walking the dashboards and four apps worth of numbers showing me what I had been missing.

Claude in Chrome14App Store Connect3Sales and Trendsindie developer19iOS24weekly review3

For a long time, I treated App Store Connect's Sales and Trends as a once-a-month glance. Ad revenue moved more visibly day to day, so the AdMob dashboard pulled most of my attention, and the small waves in paid app sales and in-app purchases ended up being something I only noticed in hindsight.

I have been making apps as an indie developer since 2014, and even now with the catalogue grown to around 50 million downloads in total, I only recently noticed that the metrics I had written off as "monthly is enough" actually read very differently at a weekly cadence. I tried switching to weekly reviews with Claude in Chrome riding along for one month, and below are my notes from four apps' worth of numbers and what I started seeing.

Why I bothered changing the habit

The trigger was simple. After plugging AppLovin MAX mediation into AdMob in March, I started checking the AdMob dashboard every morning. It felt strange to leave App Store Connect on a monthly cadence while the other dashboard moved daily. Watching only ad revenue means missing the smaller currents in paid downloads and in-app purchases, and after a while that mismatch started to feel like something I owed my own apps to fix.

The four apps in scope are Beautiful HD Wallpapers, my Ukiyo-e wallpaper app, Relaxing Healing, and Law of Attraction Everyday. Ad revenue carries most of the income, so the in-app purchase totals are not huge in absolute terms, but the country mix carries clear marks of seasonality and campaigns. Rolling them into a single monthly view was burying signal that I did not want to keep burying.

The first week I tried doing the rounds manually, logging into App Store Connect and downloading reports country by country. Even with just Japan, the US, China, Germany and Brazil, I was looking at apps × countries × product codes × weeks coming to more than 80 rows, and the UI requires enough clicking that my attention ran out before I finished reading through.

The standing route I hand to Claude in Chrome

So I switched the work over. Claude in Chrome walks the dashboard pages in order and returns only the numbers I asked for, as plain Markdown. By the time I get back from my morning walk, four apps' worth of reports are waiting in a single document.

The instructions I hand it are nearly identical each week.

1. Open App Store Connect's Sales and Trends.
2. Set the filter to the most recent calendar week (Mon-Sun).
3. For each of the four apps, pull
   - Units (sales count)
   - Proceeds (USD net)
   - Refunds (count and amount)
   for Japan, the US, China, Germany and Brazil.
4. Separate IAP (Subscription / Consumable) from one-time purchases,
   and present a delta vs. the prior week with + / - notation.
5. Leave a blank "reason" column for outliers (WoW change of >= 30%).

The thing I am deliberate about is keeping judgment out of this layer. I asked Claude in Chrome only for extraction and deltas. When I tried letting it speculate on why a country moved, I ended up correcting bad hypotheses later, which is double work. Leaving the reason column blank also protects a small ritual: the quiet half hour over coffee after my walk, where I get to think about why on my own.

Patterns I had missed at the monthly cadence

Four weeks in, a few patterns surfaced that the monthly view had quietly hidden.

The first was that Relaxing Healing's IAP revenue clusters on Friday evenings. Read monthly, it looked like a steady seller. Read weekly, Units on Friday and Saturday were roughly 2.4x the other days. A sleep app picking up momentum on the evening before the weekend has its own quiet logic, and seeing that alone made the weekly cadence worth the effort.

The second was that my Ukiyo-e wallpaper app's US Proceeds lean toward the first half of the month. That distribution vanishes when collapsed into a monthly total, but a weekly view across two months showed weeks one and two consistently above weeks three and four. Whether it is pay-cycle timing or some calendar I do not personally feel, I do not yet have a confident answer. Keeping the reason column blank is paying off here as well, because I do not feel pressured to fill it with a guess.

The third was Refunds. The weekly count is small, one or two events, but Brazil showed clusters in weeks that lined up with a fresh app version going out. My own release rhythm was producing small Refund waves I had never seen at the monthly level. I started a small local adjustment: for the first 48 hours after a release, I keep notification banner copy gentler than usual.

What worked, and what I stopped doing

Two things worked. First, placing the AdMob dashboard and Sales and Trends inside the same morning route. I had assumed ad revenue and IAP would feel like different mental modes and that switching would be tiring, but because Claude in Chrome returns both in the same Markdown shape, the context-switch cost was effectively zero.

Second, drawing a line at extraction-only from day one. Old habits from agency days have me writing "why it went up" before I have read the row, and when I let Claude in Chrome share that habit, I spent too much time undoing wrong guesses. Leaving the reason column blank turned out to be a small but real operating discipline.

What I stopped doing is the end-of-month catch-up review. Because the weekly read is already in place, I no longer open Sales and Trends with the bank-statement feeling I used to bring at month-end. The monthly roll-up now sits behind the weekly view as background context for the quarter, which is where I think it belongs.

What I want to try next month

Next month I want to look more carefully at the relationship between release timing and Refunds. Concretely, I will pull the 7 / 14 / 30 day Refund rate after each of the last 12 releases per app, to isolate which of my release habits are hurting me. Claude in Chrome only gets the simple job of pulling the Refund rows from the 7 days after each release; the judgment stays with me.

I also want to extend beyond Japan, the US, China, Germany and Brazil to Indonesia and the Philippines next month. The Units are small, but the conversion rates are interestingly high, and the AppLovin MAX side has also started surfacing Southeast Asia activity that I want to see paired against Sales and Trends.

Since 1997, when I was a sixteen-year-old just discovering the internet, I have been the kind of person who is happy to meet a new metric. Sales and Trends is an old screen, but I learned again this month that the view changes considerably when only my reading habits change. Taking a number you had been treating as monthly, and reading it one step finer. It is unglamorous work, but as a foundation for indie development, it is the work I most enjoy right now.

Thank you for reading. If you have also been giving Sales and Trends only a monthly glance, I hope this nudges you to try a weekly pass at it.

Share

Thank You for Reading

Claude Lab is ad-free, supported entirely by members like you. We publish practical guides daily with implementation code, benchmarks, and production-ready patterns. If you've found it useful, we'd love to have you on board.

  • Copy-paste ready implementation code
  • New advanced guides published daily
  • $5/mo or $10 for lifetime access
View Membership →

If you found this article helpful, a small tip ($1.50) would mean a lot to us. Your support helps keep this site ad-free and covers server and hosting costs.

Related Articles

Claude.ai2026-05-25
Catching AdMob Fill-Rate Drops in the Morning with Claude in Chrome — Two-Week Notes
I kept noticing fill-rate drops only by late afternoon. So I switched to having Claude in Chrome read the AdMob report each morning. Here are my two-week notes, with the numbers and the friction I ran into.
Claude.ai2026-05-24
One month of weekly AppLovin MAX A/B test reviews with Claude in Chrome
Waterfall A versus B—how do you compare them every week without burning out? Here are my notes from running AppLovin MAX A/B tests across four indie apps with Claude in Chrome handling the weekly roll-up.
Claude.ai2026-05-21
Three Weeks of Tuning AdMob Floor Prices with Claude in Chrome
Notes from three weeks of small daily floor-price adjustments across four iOS apps, with Claude in Chrome doing the dashboard rounds and me keeping the judgment calls.
📚RECOMMENDED BOOKS
Build a Large Language Model (From Scratch)
Sebastian Raschka
LLM Dev
Prompt Engineering for LLMs
Berryman & Ziegler
Prompting
AI Engineering
Chip Huyen
AI Eng
* Contains affiliate links
See all →