Tagged: claude code
7 posts from the Dosu blog
Turning Coding Sessions Into Shared Agent Memory
Recurring discoveries in Claude Code and Codex show why shared agent memory needs explanations and sources.
Taylor DolezalHead of OSSHow 20 Vercel AI SDK tickets drove the agent cost gap
Claude Code on Opus 5.5 and Codex on GPT 6.1 Sol attempted the same 49 tickets. The recorded cost gap came entirely from high-scope work.
Taylor DolezalHead of OSSYour coding agent budget pays for context, not code
Planning and gathering context account for two thirds of agent costs.
Introducing Decant: Insights for your Claude Code and Codex sessions
Claude Code and Codex log every session you run. Decant turns those logs into real numbers for what your agents did and how much it cost, without leaving your machine.
Taylor DolezalHead of OSSHow Fresh Are Your Docs? Score Documentation Freshness in CI
A 0-100 freshness signal that catches documentation drift in CI on every PR. Three deterministic checks plus a Claude Code semantic layer for the gray zone.
Taylor DolezalHead of OSSA Claude Code Skill for Auto-Generating Project Docs
Generate your project's entire documentation layer from source code with a single Claude Code skill. Build /doc-it and run it against a real FastAPI project.
Taylor DolezalHead of OSSHow to Catch Documentation Drift with Claude Code and GitHub Actions
Let's craft a GitHub Actions workflow with Claude Code that helps to catch stale docs as you iterate on your code.
Taylor DolezalHead of OSS