📝Note: This post is not about ICM, it's about tuning the AI systems you are using with ICM, if you're new to ICM, you can start Here: https://www.skool.com/cliefnotes/welcome-to-clief-notes-heres-where-to-start-2?p=f8f85a09 @Mira Bradshaw also made a great post to get you started! https://www.skool.com/cliefnotes/clief-notes-gems-for-starting-in-icm?p=0385cbf9 Let's dive into the results just 48 hours later! 👇 Two days ago, I posted about pointing Fable at my own environment and finding out where my tokens were really going. 📝If you need to catch up with my first post: https://www.skool.com/cliefnotes/i-just-spent-the-last-few-hours-asking-fable-to-make-itself-cheaper?p=cc666986 A lot of you went hunting in your own setups after that post (and found GOLD 👏). So, here's the part two: what happened AFTER the audit. 📌 TL;DR - The fixes shipped, the savings are real, and the most important lesson came from re-measuring two days later: optimization is not an event. Drift never sleeps. The audit is worth nothing without a cadence behind it. 🧾 First, the receipts. Every fix from the audit is now live: ✅ The file that lied. My startup menu file claimed "450 tokens" in its own header and was actually ~7,000. It got rebuilt down to ~750, and the detail it was hoarding moved to where it already lived anyway (each project's own handoff file). 💡One fact, one place, and everything else that needs it points to it by design. ✅ The silent tax. My safety hook was injecting ~800 tokens into EVERY prompt, repeating rules that already load once at session start. It's now ~85 tokens: a short pointer to the rules instead of a full copy of them. 💡The enforcement never lived in the repetition; it lives in the hooks that physically block bad actions. Cut the prose, keep the mechanism. That one saves on every prompt, in every session, forever.

My weekly limits roll over in about 9 hours. I have a bunch of Fable tokens left that I do not want to use. But I’m also at ~96% of my 5 hour usage window and I need to go to bed. Doesn’t reset for an hour. So, I did what anyone would do, I asked Fable what my options are. Apparently it has a timer. It has set one for 80 minutes and that will wake it so it can fire what we have queued up… I guess I’ll find out what does or doesn’t happen to that branch come morning…!!! Fable has immense confidence that all the results will be ready for me to review over a coffee… ☕️

💪 It did not disappoint. 👉TL:DR - It made all AI use cheaper in my environment, made me more efficient, and it increased my memory system usage by almost half. It should be no secret to anyone here: I don't count tokens. 🪙 I'm on a Pro Max plan and I go where the work, and the passion takes me. But I have used Fable before, and I know about the token burn! So I came up with a plan! I pointed Fable at my own setup and pulled the report. 😅 I'm glad I did. Turns out it could've been cheaper and cleaner the whole time. I didn't ask Fable what it thinks. I pointed it at the real thing. My hooks, my handoff files, my subagent config, the actual token counts on disk. Two questions: where does the money go? & how do we spend less? 💡The answers. A silent forgotten tax on every message, A safety hook was injecting around 800 tokens into every prompt I sent. Repeated rules I already load once at the top. And a file that runs at every session start called itself " 450 tokens" in its own header. It was not... it was 7,000. My actual face when I saw this--->🤬 a few moments later--->😆 (Apparently, it's not only AI that is bad at counting sometimes!) My own file lied to me, and I'd read past that number a hundred times with a smile on my face! My long sessions. The ones I'm proudest of. Turns out that hour six is my most expensive and also least impactful at the same time. 💩 I know that models follow instructions worse at higher context. And because the quality was still there, the marathon I read as momentum was being billed to me at top rates for the weakest output of the day. 🙄 My helper agents were all running on the flagship (Most expensive model). These are the agents Claude spins up to send off to do tasks to get more accomplished in a shorter amount of time! This I knew about, and it was by choice, it's my environment and I never hit my 5 hour or weekly cap, so I did not care about this for myself, bigger = better right? Use Fable 5 on UltraCode in my environment, and we find out that logic was wrong....

Is it real? Edit: How much better is Claude Fable 5 vs. Opus 4.8? (Anthropic’s launch benchmarks, June 9, 2026) • SWE-Bench Pro (agentic coding): 80.3% vs. 69.2% for Opus 4.8 • FrontierCode Diamond: 29.3% vs. 13.4% — more than double • Core pattern: the longer and more complex the task, the larger Fable 5’s lead; on short, well-scoped tasks the two are much closer In practice: noticeably better on long multi-step work (migrations, feature builds, complex pipelines); barely different for quick, simple tasks. Caveat: these are Anthropic’s own benchmarks — directionally correct, but vendor numbers.

This is a devlog from David! A lot of people are saying they want the ability to scale and deploy their ICM and their workflows. We looked at all the possible problems security issues and we have been spending a lot of time building something for all of you! It's almost ready for release, but here's a little developers log to kind of check out some things that David has been doing to build it up. It's far from perfect, but for those technical folks out there you may enjoy it!