How This Post Was Made

Prompt 1: “kick off a post in a PR for that, then let’s kick off another more comprehensive round of digging into the web and ios code looking for more good stuff to post. to start I’d like to find more stuff I can share for falcon/async/async-http users. the author of async is asking if I’ve done any writing about out cost savings, so this is a great start, but I’d love to find more to share.”

Prompt 2: “kick off posts for: 2, 3, 4, 7, 11, 12, 17, 22, 31 – note we might want to sequence once at a time using a task list since we may run out of capacity, at least not all at once?”

Prompt 3: “kick off the remainder in sub-agents, we have capacity”

Generated by Claude Fable 5.1 using the blog-post-generator skill. One agent researched the iOS repository and proposed this post among a dozen candidates; a second agent verified the claims and wrote it. Sources: the plans index and its banked-PR definition, the July 15, 2026 consolidation PR and the closing comment left on each banked PR, the July 2026 session tracking issue, the per-location storage split plan and the reference PR’s body and review rounds, slice A’s PR body and its August 13 update, the ForEach hoisting plan as first committed on August 4, the hoisting sweep PR’s closing comment, the two rejected slices’ closing comments and the lite re-cut’s body, the plan retirement PR of August 6, and the design queue policy in the index. PR states were confirmed with the GitHub CLI and the refs/pull/<n>/head refs were confirmed to resolve on the remote for three banked PRs. Judgment calls: the repository is private, so no PR is linked or numbered in the body and features are named by kind; the owner and the designer are unnamed; the closing comment and index line are quoted with the PR number replaced by a placeholder; the count of banked implementations is given as “more than sixty” because the index’s banked lines reference 66 closed, unmerged PRs and two of those are cross-references rather than deposits.

Rewrite (2026-09-03): Plain-register pass, pilot for issue #66, after a reader said the posts read like AI. The reader’s quoted paragraph (the “lite slice” one) was replaced with the plain version from the skill, fitted to the facts. Hoist is now defined where it first appears, “lite slice” is gone in favor of “cut again with only the hoists”, and the code-copying step is called copying throughout instead of extraction. Retired words removed: byte-identical, adversarial, lean on, surface, the whole contract, for free, bespoke, “the thing extraction buys”, “has to be paid”. The closing aphorism in Lessons Learned became a plain rule. Judgment calls: “adversarial review rounds” became “rounds of review”, since the word described the rounds rather than naming a practice; the summary line changed “surfacing” to “showing up”; and “flag-off behavior was byte-identical to production” became “behaved the same as production”, since the claim is that the flag-off path is a no-op rather than a byte comparison. Second pass (same day) after the reader reviewed the first: contractions and “we” allowed, subject first with the reason after “because”, restating sentences cut, category or examples but not both. Judgment calls in the second pass: “the team” became “we” throughout, with “the owner” kept for the person; the closing line of the sequential section (“Drift shows up as an apply conflict, not as a quiet divergence”) was cut as a restatement of the sentence before it; “a banked draft is a lost draft” and “the catalog is what makes a bank retrievable” became plain rules; the front-matter summary was reworded in the same voice. 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.”