hirelisted

This skill runs only when the CEO invoked it directly or as the last step of /kickoff or /assess via the Skill tool. Either way, assignments are applied only after CEO approval. Hire the team (assign a model and effort per role). Note: $ARGUMENTS 1. Candidates: the default candidates are the aliases opus / sonnet / haiku (they resolve to the plan's latest models). Include other model IDs (API, Bedrock, Vertex) only if the CEO names them. Plan and usage caps cannot be read from the CLI — ask, do not guess. 2. Conditions (one AskUserQuestion call): budget tier (unlimited = API/in-house / high = Max 20x / medium = Max 5x / low = Pro), project character (see docs/CHARTER.md and ASSESSMENT.md — a legacy rebuild weights critic and reviewer; a prototype weights speed), whether parallel development is planned, and any role to make deliberately strong or cheap. 3. Proposal: a role × model × effort table with a one-sentence reason per row and a note of where tokens concentrate. Principle: strong model and high effort where judgment happens (planner, critic, reviewer); verifier on haiku·low; implementer by budget. Also propose an operating profile: default review lenses (2 or 4), parallelism (none / session-level / /parallel), minimum steps for critic. On the low tier, drop parallelism and 4 lenses from the defaults. 4. After CEO approval, apply: - Models and effort: `node .claude/scripts/apply-models.mjs --flavor claude --dest .claude/agents --settings .claude/settings.json --budg