How This Post Was Made
Prompt 1: “see recent claude opus48 delegating, I think we might want to default to ELI5 output in Fable for now, too. how do we do that? we may want to update all helloweather repos, too”
Prompt 2: “and add a blog post about this (trevorturk.github.io repo) and also review recent work with date formatting extensions etc”
Prompt 3: “dispatch research / adversarial review with opus48 to determine if there’s anthropic docs, user sentiment etc about this which might inform our choices, it’s ok if this is all correct, but let’s dispatch one more round of research, you digest and report back”
Prompt 4: “agreed with your recommendation, but also update the blog post pr (we’re working on 4 prs in this session)”
Generated by Claude using the blog-post-generator skill, in the same session that made the config changes it describes. The mechanism was verified against the current Claude Code docs before writing; the “Attack your own config” section documents the three-agent research round that then hardened both the config and this post.
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 checklist rule and the model change that prompted the work, Results states expectations as expectations plus the accepted cost, and Lessons Learned dropped the two bullets that repeated body sections. 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 style file, settings key, nine-file count, and checklist quote match the repos; the style excerpt now carries the file’s em dashes, the checklist rule is described as one item rather than the last one, and the exit-condition quote uses the current wording plus a note that the AGENTS.md section split into CLAUDE.md and AGENTS.md on 2026-08-13. The /output-style version note now cites the changelog’s v2.1.73 deprecation, the styles deprecation is dated to v2.0.30 in late October 2025, and the two accepted limits are marked as since lifted: the drift fix landed in v2.1.238 and issue #81334 closed pointing to --settings.
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’s rewrite keeps the style file, settings key, and every version number and issue link, and swaps the third-person, contract-heavy prose for a person explaining what we did and why. Judgment calls: “adversarial review” became “a second model’s review” everywhere except the quoted AGENTS.md rationale, which must stay verbatim; “the contract” became “the rule” in the body while the title keeps “Output Contract” because the skill links the post by that name; the aphorisms (“The findings were the work. The ELI5 was the interface.”, “A default you cannot cheaply reverse is a policy.”, “swims against that current”) were replaced with the plain fact each stood for. 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?”