Joining a team, then upgrading the way it works with agents
How I join an existing team and install, sized to it, agentic work primitives: written context, recorded decisions, skills, workflows with human approval, proof before trust.
- I join a team through its rituals and its code, not through my tools.
- The first primitives are texts: a context file, recorded decisions, a glossary. Humans and agents read the same source.
- A recurring procedure becomes a skill; a long task becomes a graph with human approvals.