agent-skills

kept by eddie may 28

The piece defines a structured pre-commit code review skill for AI agents, specifying contracts, scope governance, and engine isolation across multiple review engines including Codex, Claude, and others.

The cost of caring about software - Alex Rios Substack
AI reduces code-writing effort but shifts verification cost onto reviewers, creating an externality where comprehension debt rises despite faster generation.
also on Copilot, Cursor, Claude, #ai-coding, #software-engineering, #developer-tools
The Evolution of the Agent Harness - by Dan McAteer
The article argues that as AI models internalize agent harness capabilities, the remaining harness evolves into an interface for managing scarce human attention rather than directing model behavior.
also on Copilot, Cursor, #automation, #ai-coding, #software-engineering, #developer-tools
Using AI to write better code more slowly
Using multiple LLMs for rigorous code review and bug finding can produce higher-quality code than the common fast-output approach, though it slows development velocity.
also on #code-review, Cursor, Codex, Claude, #ai-coding, #software-engineering, #developer-tools
Building a better Bugbot
Cursor improved Bugbot's bug-finding rate by defining a custom AI-driven resolution rate metric that enabled systematic hill-climbing experiments, raising resolution from 52% to over 70% and doubling resolved bugs per PR to roughly 0.5.
also on #code-review, Cursor, #ai-coding, #software-engineering, #developer-tools
Pi, Minimal and Performant
Pi's minimal coding harness improves cost and performance by using fewer tools and less context, validated by Databricks' benchmark and Shopify's extensible pi-autoresearch extension.
also on pi, Codex, #ai-coding, #software-engineering, #developer-tools