22 POSTS
A skill that reviews a workspace against someone else's methodology is only as honest as its sources. Notes on building one from quoted records, freezing the answer key before writing the skill, and what a 4 of 9 first run taught me.
The claim that the harness matters more than the model is repeated everywhere. I went through what my sources actually show, what they only assert, and why a same-prompt head-to-head cannot carry the conclusion people draw from it.
When agents write the code, the scarce thing is knowing whether it is right. Practitioners handle that with deterministic gates, review depth scaled to blast radius, and a reviewer that did not write the code. Most of it is judgment, not measurement.
Agents make code cheap to write, so the scarce thing is how much complexity a codebase can carry. Lee Robinson's argument for spending abstractions like a budget, and where Ousterhout-style design fundamentals agree with it.
Generated interfaces share the same defaults, so their failures form a short list. That makes the fix a checklist run after generation, most of it checkable against source code, instead of better taste in the prompt.
AI-assisted CAN bus reverse engineering works when the model sits inside a pipeline of deterministic decoding and validation. It fails when the model is asked to guess signals from raw frames.
There are three ways to give an agent a tool. The choice mostly comes down to who else needs the tool and what it costs in context, not which one is best.
A skill that holds up is built in a fixed order: do the task by hand, write down what you did, turn it into a skill, then test it against cases. Most broken skills skipped a step.
What makes a coding agent reliable is mostly the layer around the model: the context it is handed, its tools, the checks on its output and the code that orchestrates sessions. That layer is ordinary engineering.
For a single person's knowledge base, markdown articles compiled by an LLM plus a generated index answer questions without retrieval infrastructure. That holds up to a size limit, and the limit is worth naming.
An agent loop is a trigger, an action and a stop condition. The stop condition is the only hard part, because done has to be something a machine can check.
When I cannot judge a plan myself, the model that wrote it should not be its only reviewer. A model from a different vendor can critique it in a bounded loop, and any factual claim the reviewer makes still has to be checked.
A skill library gets worse past a certain size, because everything in it competes for the model's attention. Deleting is a real optimization, and the test for keeping a skill is whether the agent does better with it than without it.
Compaction keeps a general summary that the tool chose. A handoff document keeps what I decided the next session needs. They solve different problems, and the handoff is the one worth writing by hand.
Chase AI argues generic Claude Code front ends come from a communication gap, not a capability ceiling. Notes on his seven levels for giving the agent real design direction.
Greg Isenberg and Ras Mic on how context windows actually work, why most agent setups waste them, and why skills do more than a long CLAUDE.md.
Ras Mic walks through documentation generated from Claude Code's leaked source: the agentic loop, how context is assembled, how tools run and how permissions work.
Cole Medin's architecture for a personal second brain on Claude Code and Obsidian, and his security argument for building your own instead of deploying an off-the-shelf agent.
Seven tips from Eric Tech for keeping Claude Code accurate, all following from one diagnosis: output degrades as the context window fills.
Notes on three community frameworks for Claude Code that address different trust problems with generated code and can be stacked rather than chosen between.
Accuracy drops as a Claude Code session's context fills, and most people never check. Notes on Eric Tech's status-line display that keeps context usage visible.
Matt Pocock's case that agent output quality follows the process you steer it with, and the five skills he uses to encode that process for an agent with no memory.