SpecWeave asks agents to plan work as an increment: a spec.md with acceptance criteria and tasks. We build SpecWeave, SpecWithCode and Verified Skill with it, so we asked a plain question of our own last four weeks: does planning make the work longer, bigger or more complicated?
You are halfway through a feature and the usage limit hits. The goal, the decisions and your uncommitted edits are sitting in a session no other tool can read. SpecWeave 3.0 is built around that moment.
On February 5, 2026, Snyk Labs published the ToxicSkills study — the first large-scale security audit of AI agent skills. They scanned 3,984 publicly listed skills across every major registry. The results should concern every developer using AI agents.
1,467 skills (36.82%) contained at least one security flaw. Of those, 76 contained confirmed malicious payloads — not accidental overpermissions, but deliberate credential theft, reverse shells, and data exfiltration.
We're excited to introduce SpecWeave, a revolutionary framework that replaces vibe coding with Spec-Driven Development.