some of the friction of using coding agents for product building (not just writing code) is every new session starts from scratch.draft is my attempt at a fix. before getting into how it works — a lot of memory/context plugins solve this by calling an external api or running their own model, which either charges you separately or quietly inflates your usage. draft runs entirely within your existing claude subscription.it's a codex/claude code plugin a few core pieces:1. session-init hookon every session start, a hook fires and injects a structured context summary into claude's working memory. specifically, it reads the `name` and `description` frontmatter from each context index file — company, product, priorities, team, decisions — and assembles them into a single compressed summary under ~5k tokens.2. learning — inference-driven and manuallearning is inference-driven rather than hook-based. the main claude agent reads its instructions and decides when something is worth persisting — ...