#coding-agent
Wiki 15
- AI Agents and the Refactoring That Never Happens Getting lost in tangled code used to be what made engineers stop and refactor; agents don't get lost, so the checkpoint has to be put back on purpose
- AI-Written Code Is Still Your Code Writing code used to force understanding it; with agents writing, understanding becomes a separate cost, and shipping the code still means owning it
- Awesome DeepSeek Agent (deepseek-ai curated list) DeepSeek's official curated list of 16 AI agent and coding-assistant tools that ship step-by-step integration guides for DeepSeek-V4-Pro and DeepSeek-V4-Flash
- Build Your Own OpenClaw 18-step Python tutorial for building a Claude Code-style coding agent from scratch
- Clean Code in the Age of Coding Agents Code structure matters more with agents — context windows are finite, messy code wastes tokens
- Control the Ideas, Not the Code antirez argues line-by-line review of LLM code is mostly wasted effort — own the design, spend the hours on QA and direction
- GLM-5.2 is the step change for open agents Nathan Lambert on GLM-5.2 as the first open-weight model that works as a general coding agent, released while Claude Fable 5 was restricted
- In Defense of Not Understanding Your Codebase Goedecke's case that partial understanding is the honest baseline in large systems, and one engineering value traded against others
- itayinbarr.substack.com Itay Inbarr's Substack on agent scaffolds, small-local-model benchmarks, and the scaffold-model-fit framing of coding-agent evaluation
- Let's talk about LLMs (Bennett) Bennett applies Brooks' No Silver Bullet to LLM coding — math caps upside, DORA/CircleCI show instability
- little-coder — Scaffold-Model Fit on Aider Polyglot Itay Inbarr shows Qwen3.5-9B Q4_K_M goes from 19.11% (default Aider) to 45.56% (little-coder) on Aider Polyglot by redesigning the scaffold around small-model behavior
- Prompt Caching in Agents How KV-cache reuse sets the cost, latency and tool design of a coding agent, and what Pi shows
- Scaffold-Model Fit Coding-agent benchmark scores measure model × scaffold, not model alone — small local models inherit responsibilities the scaffold assumed they'd self-manage
- SWE-1.7 — Cognition's Coding Model Cognition's SWE-1.7, RL-trained from Kimi K2.7, reportedly near GPT-5.5 on coding benchmarks — with the strongest numbers on its own FrontierCode
- With AI, You Barely Need a Frontend Framework Framework implicitness is the enemy of AI-generated code — a minimal explicit pattern that replaces it
Toolbox 6
- botctl Process manager for scheduled autonomous Claude agents, each defined by a BOT.md file
- LazyPi One-command installer that configures unmodified Pi with 60+ community skills and 67 themes
- oh-my-pi Batteries-included fork of the Pi coding agent bundling LSP, browser control, SSH and search
- OpenCode Provider-agnostic terminal coding agent that points at any OpenAI-compatible or local endpoint
- Pi Coding Agent Minimal terminal coding agent with no built-in MCP or sub-agents, extended via TypeScript modules
- vamp Single-file TypeScript view layer with explicit DOM bindings, written to be legible to LLMs