How This Post Was Made

Prompt 1: “please kick off a big batch to look through all skills looking for other topics that might be interesting to blog about. we could look at git history, but I think since we’ve been using claude/codex for the last ~year we should have most of the interesting stuff built into the skills by now. however, you can also look at the changelog view in the iOS repo for other highlights that might be worth dispatching research about. come back to me with a list of possible topics (that haven’t already been covered in the blog) …”

Prompt 2: “lets do 4, 20, 21, 22 – the others I think are not worth it”

Ten Claude agents mined the iOS, web, and Android skills, the iOS changelog, and the plan indexes for uncovered topics; the owner picked four from the ranked list. This post was researched and drafted by one agent from the cited skills, plans, and code, under the why-then-how voice and self-contained-code brief settled in the previous localization batch, then reviewed before publishing.

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 title lost its subtitle, the bolded rules in the body moved into Lessons Learned, Results now holds only what changed and what it cost, and the caveat that the moon grid is not yet in the serving path stays. 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 cache section was resequenced to match the commits: the pure-Ruby engine replaced the Node one first (May 4, 2026), its cache was enabled the same day to recover CPU, and both were rolled back two days later; the 0.9 MB and 31.6 MB figures came from the pre-rollout benchmark and were budgeted, not discovered in production, so “both halves were wrong” and the unsupported “cache bookkeeping” explanation were removed, and the per-dyno figure now reads ~64 MB as the plan recorded it. The worker count is dated: two per dyno during the experiment, one since May 2026. The moon grid is no longer called the committed direction: its implementation PR was closed unmerged on May 11, 2026 as too small a CPU win, and the work is parked, so the caveat now says that.

Rewrite (2026-09-03): Plain-register pass, pilot for issue #66, after a reader said the posts read like AI. Archive batch 3, run after batch 2 (#69) merged. The prose now says “we” and uses contractions, “reconcile” and “reconciler” became “merge” throughout, resident memory and canary are defined where they first appear, and the two “for free” flourishes are gone. Judgment calls: the idiom “roll your own” stayed in quotes because it’s the ordinary phrase; the closing line of the cache section (“The remaining direction was not to cache the calculation but to stop doing most of it”) was reworded into a plain statement of what was left to try; and the Lessons bullet “Precompute what is global and smooth; key what is local at render precision” was reworded, since it read as a maxim, without changing its rule. Code blocks, numbers, quoted text, links, and headings 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?”