How This Post Was Made
Prompt: “I’m seeing a bunch of chatter lately about claude code permissions. we recently did a bunch of work in helloweather/web to make permissions a bit more flexible and to allow a bit more editing files etc, but tried to keep things a bit more strict and defintiely avoiding dangerously-skip-permissions. see some chatter here: [discussion about YOLO mode, containers, and permission approaches] – don’t reference names, but I’d like you to use the blog post skill and add a post to our blog about how we’re doing permissions for claude and codex, using a new permissions skill we added. see recent prs in helloweather/web. create a pr with a blog post about how we’re approaching permissions for sharing with others. make sure to include this prompt as the ‘how this was made’ part as well.”
Generated by Claude (Opus 4.5) using the blog-post-generator skill. Context gathered from commit 77c236d5 (“Streamline Claude Code permissions (v2)”) and the permissions sync skill in helloweather/web.
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 failure modes instead of a question, the Solution states the sorting criterion once, each config is followed by a line on what to notice, and Lessons Learned holds only 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 “loosened an earlier, stricter version” claim held: before commit 77c236d5, Edit, Write, and local git add, commit, and checkout all sat in ask. Both config excerpts now include the HEAD:main push deny that the real files have always carried, the Codex excerpt shows the match/not_match self-tests the guard rules gained in July 2026, and the Sync Workflow excerpt uses the skill’s current wording (nine steps, validation last). gh api:GET was dropped from the Allow list because the web repo stopped allowing it on 2026-07-16; gh api now prompts and its mutating methods, plus mutating curl, are denied, which the Ask and Deny lists now say. The commit title in the meta was corrected to “(v2)”.
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. The post now reads as one person explaining the setup: contractions and “we” throughout, the cleft “The push rules are what to notice” became “Look at the push rules”, the three Why Not YOLO paragraphs with bold lead-ins became list items, the restating Deny sentence was merged into one, and the summary was reworded to say “asks first” and “refused outright” instead of “get a glance” and “blocked”. The title was kept because the prompts file front matter carries it, and the policy bullets were left as they were because they are lists of facts. Code blocks, the table, dates, numbers, 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?”
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”