Engineering 12 min read
When Good Analysis Misses Critical Problems
OpenClaw looked great by every standard metric. Clean code, strong architecture, massive test suite. It also had 8 CVEs. Here's why good analysis isn't enough.
Blog
What we're learning about AI-generated code, quality drift, and keeping velocity without the mess.
Benchmark 14 min read
Claude Code vs Codex CLI: Same Model, Same Task, Different Agent
We ran the exact same code analysis on the same codebase with the same LLM. The only variable: which agent CLI executed the work. 2.7x difference in findings. 2.2x difference in cost.
Benchmark 12 min read
Code Quality Showdown: OpenAI Codex vs Google Gemini CLI vs OpenCode
We ran Octokraft's full analysis pipeline on three open-source coding agents. Codex scored an A, Gemini CLI a B+, OpenCode a B. Here's what the data shows -including why one ships with no linter at all.
Deep Dive 18 min read
OpenClaw Scores a C. The Most-Starred Project on GitHub Has Real Problems.
285,000 GitHub stars. 8 CVEs. 42,000 exposed instances. We analyzed OpenClaw's 1.1 million lines of code across four dimensions. Here's what we found.
Engineering 8 min read
What Technical Debt Management Actually Looks Like When Your Tool Does the Work
Most technical debt processes fail because they rely on separate tracking rituals. The sustainable model is tooling that surfaces friction where work already happens.
More articles coming soon.
Try Octokraft on your repos
Health scores, architecture reviews, and convention detection. Free to start.
Sign In and Try