Sun, Nov 1, 2026
5 notes this week
Your job is not to use agents to help you write code. Your job is to lead the agents to help them write code.
— Uncle Bob Martin, paraphrasing the CTO of Proton skill-diet
nicobailon/skill-diet is an agent skill that slims your other agent skills, then proves the slim version still works. It runs each task with the old skill, the new one and no skill at all, 3 times each, and keeps the cut only if the new one scores at least as well.
I ran it on three of my skills with gpt-6-luna:
- adr:
SKILL.mdwent from 13 KB to 1.6 KB, 30/30 before and after. With no skill it still passed 26/30. The model already knew ADRs. - notion: 32/33 to 33/33 at 55% fewer tokens per run. With no skill, the agent did one-line edits with a whole-page replace and reported success.
- web-browser: 16 KB to 6.4 KB. The no-skill runs used twice the tokens of the old skill, because the agent explored the scripts by hand.
The size cut was not the best part. For a skill that wraps a tool, it checks every claim against the tool and your session logs. It found 16 places where my skills or scripts were wrong, such as
agent.mjs --domain x.comsilently setting no allow-list. The rule I’m keeping: fix the tool’s error message before adding a line to the skill.The cost: 1,434 agent sessions and 23.5M tokens for three skills, and a
sandbox-execprofile, because the test agents kept finding my installed skills on disk.The diet commit shows what got cut, and the full report covers the method and the costs.
- adr:
django-bolt decides where your code runs by reading it
django-bolt serves Django from a Rust server, with one Python worker thread per process. In an independent benchmark it ran 1.6 to 1.7x django-ninja on real database endpoints. The catch: a slow sync handler must move to a thread pool, or every request in that process waits. Bolt decides at startup by scanning each handler’s source for ORM calls like
.objects.get.The scan reads only the handler.
return Order.objects.get(id=id)goes to the pool.return services.get_order(id)runs the same query inline on the worker thread, and the whole process stalls until it returns. A codebase with a service layer hits this on nearly every route. The way out is async handlers:async defputs the waiting in the signature, so it can’t hide one call down.A scan of one function sees what’s written there, not what it calls. A fact that has to cross calls belongs in the signature, which is Ron Minsky’s argument for types.
AI tricks get folded into the product
Charles Miller: “a skill that can be picked up in a few weeks, and will be obsolete in a few months, has no value outside the moment.” His mechanism: a prompt trick that works gets folded into the product and ships as the default a few months later. His analogy is the 1990s C belief that
++ibeatsi++, which survived long after compilers erased the difference.He’s right about tricks, but not every AI skill is a trick. Verification, choosing context and deterministic gates depend on your problem, not the model, so no release absorbs them. Ron Minsky argues they matter more with agents. My test when I learn something: is this about the model or about the problem? Model tricks go in a skill file I can delete on release day.
Ron Minsky: types, expect tests and review matter more with agents
Ron Minsky’s Bug Bash 2026 talk argues Jane Street’s old habits (rich types, expect tests, real code review) matter more with agents: they give the model fast, exact feedback and keep the code readable for the humans who own it. He goes the other way from the Claude Code team on review: its main job is keeping a human able to explain the system, not catching bugs.
The idea I’m taking: expect tests. The test prints output, the expected text lives inline, and a change shows up as a diff of behavior, not just code. Python’s version is inline-snapshot:
assert result == snapshot(), filled in by pytest.- Gotcha with agents: under
--inline-snapshot=fix(orcreate,review) every snapshot comparison returns True and the file is rewritten. An agent chasing green doesn’t need to delete a test; it re-accepts the wrong output. Keep acceptance with a human and never auto-fix in CI.
- Gotcha with agents: under