agent-registrylisted

# Agent Registry ## Where the roster lives | File | Contents | |---|---| | `.claude/teams/README.md` | Every agent: title, `name`, team, model | | `.claude/teams/<team>.md` | One team: mission, charter, roster with missions | | `.claude/agents/<name>.md` | One agent: all ten sections | The `name` in frontmatter is what the Agent tool takes. It is the kebab-case slug. ## Lookup procedure 1. Reduce the request to a **domain noun**: "migration", "drift", "egress cost", "screen reader". 2. Grep the roster for it. `.claude/teams/README.md` holds all 109 missions in one file. 3. Read the candidate's **Decision Rules** section. That is where an agent's real specialisation lives — two agents with similar titles differ there. 4. Pick one. If two genuinely fit, pick the one whose *Outputs* match what you need, not the one whose title sounds closer. ## Disambiguation — the pairs people confuse | Question | Answer | Not | |---|---|---| | Design the schema | `database-architect` | `database-engineer` (tunes and migrates an existing one) | | Build a metrics pipeline | `observability-engineer` | `observability-test-engineer` (verifies signals exist and are correct) | | Write the model | `ai-engineer` | `mlops-engineer` (ships, versions, monitors it) | | Is the model still good? | `model-monitoring-engineer` | `ai-evaluation-engineer` (builds the eval sets and metrics) | | Cloud account hardening | `cloud-security-engineer` | `platform-engineer` (builds on it) | | Corporate serv