How This Post Was Made

Prompt: “Add another post about the APNS schedule - top and middle of the hour. Backend doesn’t have a db for customers for privacy reasons. Instead, they just send a push token. We save that on the server (anon) and then we have a cron job for top and middle of the hour to send a silent push to the client which then triggers the app to do its own refresh. Then we don’t need lat/lon on the server in a db. We also don’t need the significant location api, pinging the api to update locations etc. Hello Weather takes privacy very seriously. However this is also a huge simplification, because we don’t need to sync the client and server database, etc. The only change to the backend is to have a cron job!”

Generated by Claude (Opus 4.5) using the blog-post-generator skill.

Rewrite (2026-09-01): Part of an archive-wide rewrite. The owner asked, “with Fable 5.1, supposedly the writing quality is much better, I’m wondering if we should do a pass on all of the blog posts we have so far to improve them. should we start with the latest one?” and, after a pilot on the worktrees post, “I like the rewrite in any case and we have a lot of Fable capacity at the moment, should we go for it and dispatch an initial round of research to improve our skills, agents.md, etc and then dispatch sub-agents to rewrite each post? this could be done in a single PR, I think.” Four Claude Fable 5.1 agents surveyed the archive to settle the voice and structure rules now in the blog-post-generator skill, and one agent rewrote this post under them. The Problem now names the server-side design and its costs once instead of as a bullet list that Why This Works repeated, the Solution opens on the mechanism, the title dropped its subtitle, and Lessons Learned is four rules that transfer. Code blocks, dates, numbers, links, and headings are unchanged, and no facts were added.

Fact check (2026-09-01): The owner asked, “1) dispatch research into the ~/Code/helloweather repos to validate the posts’ content, for example checking the StoreKit code we shared is correct. 2) fix the “Pre-existing oddities” using your judgement, and feel free to make “judgment calls” as you see fit – this is a blog meant to be authored by AI and is expected to lean on AI model judgement calls, advancements in model capabilities may prompt future editing/rewriting sessions, and for each one I’ll want them to be driven autonomously.” One Claude Fable 5.1 agent checked this post’s code excerpts, numbers, dates, and quoted rules against the source repositories. The cron job excerpt was invented and is replaced with the real two-job shape, an enqueue job on a 30-minute schedule that fans each device’s push out over a random delay of up to five minutes, and a per-token ping job with retries; the push is not payload-free but a background push carrying content-available: 1, and the token table gained its real columns (env, topic, updated_at) plus the 90-day cleanup. The traffic table and diagram now show the five-minute fanout windows instead of a single-minute burst, and the iOS steps note that the app uses its selected location when one is set and skips the fetch if it refreshed within the last 25 minutes.

Rewrite (2026-09-03): Plain-register pass, pilot for issue #66, after a reader said the posts read like AI. Archive batch 5, the last, run after batch 4 (#72) merged. One Claude Fable 5.1 agent rewrote the prose of this post in plain register: first person and contractions throughout, one name per thing (device, app, push, cron job), the cleft “the fanout is what keeps” turned into subject-first sentences, the “no database to breach, no logs to subpoena, no data to sell” triple and “architecturally incapable” cut to the plain claim, the “self-inflicted outage” flourish reworded, and the Lessons bullets restated as plain rules. Judgment calls: defined “complications” at first use, cut the two sentences after the cron job code that repeated the Solution’s description of a silent push, and dropped “ever” from the summary. Code blocks, the diagram, the table, headings, numbers, links, and the earlier Rewrite and Fact check paragraphs are unchanged. Prompts, verbatim:

Prompt 1: “we got feedback from a reader that our posts are still too AI/slop/wordy, an example and a possible skill to improve are included here, please review and let me know what you think, consider if we could do another big bang rewrite without spending too much of our Fable budget, or we could prep and schedule for when our limits are about to be reset and save in a date-triggered gh issue: I enjoy your ai posts, but man is it wordy :joy: [the reader’s quoted paragraph and a link to the SimpleEnglish skill followed; both are in issue #66]”

Prompt 2: “agreed, but lets make this into an issue, I just enabled issues, document what your plan is with a new issue, then we can kick it off with the smaller sample, maybe keep going depending on token usage, and the reader can subscribe to the gh issue to track if they like. as usual, please include this prompting in the issue so people can follow along to see “how the sausage is made” if they’re interested. oh, and sorry, I think what I’m looking for is less about word counts, and more about “ai speak” as in, here’s a bit more slack chatter about this with the reader: I’m kicking off a blog rewrite thing, not 100% sure if I want to do a big bang today tho b/c Fable budgets [10:38 AM]but I’ll report back READER [10:39 AM] I’ll be curious. Will it be “byte for byte identical” ??? :joy:”

Prompt 3: “and the density issue, the quote the reader provided is a perfect “what not to do” example, I think”

Prompt 4: “another possible thing to mix into the skill changes would be the ELI5 idea, which I generally like, I often ask AI to ELI5 after dispatching research so I get a human-readable explanation of the why, what, how etc”

Prompt 5: “go ahead and kick off the pilot PR”

Prompt 6: “perhaps the use of Opus for the writing is a source of the problem? I’m finding Opus to be a bad writer, and Fable 5.1 to be much better. the reader reports: Also I think it’s funny that the ai suggestions are still bad. “extracting from the source is what makes the slice trustworthy” Should just be “The slice is trustworthy because it’s directly extracted from the source.” – and the “Not every slice can be copied straight out of the source PR” rewrite paragraph is better, but perhaps still somewhat verbose/ai-slop-ish? I wonder if we can do just a bit better, but this does seem like a promishing direction. consider and report back with a recommendation.”

Prompt 7: “agreed except I wouldn’t worry about the word count at all. “wordy” isn’t the same thing as “word count” and I think the reader (and my) issue is more to do with the AI style of speaking, which is why we’re looking at the ELI5 and SimpleEnglish skill adaptations.”

Prompt 8: “merge it and start the first batch of ten, then I can check usage, and then we can keep going – just to check, are you saying the total spend would be ~6M tokens?”

Prompt 9: “usage looks fine, merge it and run batch 2”

Prompt 10: “usage is fine, please continue – one more thing – at the end (or perhaps with future batches?) I’d like to change the “How This Post Was Made” sections in all posts to not have the prompt in the post itself, rather, the prompts should be moved into PR body if editable, or comments, then the “How This Post Was Made” can have the last edit date and a link to the Pull Requests / Prompts – then there’s less cruft at the end for readers that just want to copy paste a post into their agent – wdyt?”

Prompt 11: “sounds good”

Prompt 12: “for the “How This Post Was Made” maybe we move the date down there as well, so it’s like first posted by MODEL on DATE, last edited by MODEL on DATE, View: PROMPTS, HISTORY or something along those lines, so it’s all in one place?”

Prompt 13: “agreed, go”

Prompt 14: “approved, go”