How This Post Was Made

Prompt 1: “see recent work in ~/Code/helloweather, perhaps a blog post about our opus 4.8 agents and why we decided to do that? perhaps something about the swift testing + snapshots inspired by minitest-snapshots? anything else? bring me a list of potential post ideas for review.”

Prompt 2: “skip 4, 5, 6, 9 but create posts for each of the others in the 1-9 list. also add Four Answers to One Question, and Write the Rule, Not the Story – show me a concise version of your plan and then I can approve” — then “proceed, one pr per post”

Research by one Claude agent per repo mining git history since the previous post; this draft was written by a dedicated agent from that research plus the underlying commits and skill files, 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 post now opens on the two bespoke recorders and the web repo’s 180 snapshots instead of a general observation, the paragraph after the Swift helper names the CI lock instead of re-walking the code, the Swift Testing differences are a list, and Lessons Learned went from nine bullets to five, while the design-record caveat, the PR citation, and the Verify: flag stay. 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 helper is no longer unshipped: it landed in iOS #1514 on 2026-08-06 with the date matrix as first adopter, the golden-table system the post said would stay was deleted in that PR, and the #_sourceLocation spelling compiled as written, so the caveat, the non-goals section, the Verify: bullet, and the last lesson were reworded to say so. The Swift and bash excerpts were replaced with the landed code (snake_case sanitization, a defined firstDifferences, the test seam for the environment, a do/catch on the write); the helper is ~100 lines rather than ~120, the gem is ~170; and the web repo’s live snapshot count is about 90 files across nine suites, not 180 across 17 (the larger number counted an abandoned 2023 snapshot tree in an older naming scheme).

Rewrite (2026-09-03): Plain-register pass, pilot for issue #66, after a reader said the posts read like AI. Archive batch 1, run after the pilot (#67) merged. This post lost its bolded caveat paragraph, its closing maxims in the Naming section and Lessons Learned, and a set of specialized terms (the ergonomic layer, surface, wire-visible, the wrong altitude, a spy’s serial/parallel counts, transliteration) in favor of plain phrases; the design-record caveat, the PR citations, the numbers, and the Verify: flag stay. Judgment calls: “the contract tests” in the Design paragraph now reads “the helper’s own tests” and in the non-goals section “the date-format contract tests”, both checked against the iOS repo’s test files, and “byte-equal” became “the same bytes”. 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?”