model-tiers
This skill should be used when an orchestrator needs to choose or resolve a model for a delegated agent — i.e. by /bee:planner when authoring a plan (assigning a capability tier per agent per slice) and by /bee:plan-implementer when executing one (resolving a tier to a concrete subagent model value). Contains the single source of truth mapping capability tiers (best / excellent / fast) to Claude Code subagent model values, with per-tier guidance for picking the right one. Load this skill instead of hardcoding any model name.
Install
With your agent
Install OMGSkills skill "incubyte/ai-plugins:bee/skills/model-tiers" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/incubyte/ai-plugins /tmp/ai-plugins && ln -s /tmp/ai-plugins/bee/skills/model-tiers ~/.claude/skills/model-tiersFrom README
Model tiers — the single source of truth Bee references models only by capability tier, never by concrete model name. This file is the one place that maps a tier to a model. Changing the model lineup means editing only this file — no command, skill, plan, or routing decision names a model. (A few agents carry a model: frontmatter default for /bee:sdd's fixed loop; under the /bee:start → /bee:planner → /bee:plan-implementer chain the plan-resolved value passed at dispatch time always overrides it.) /bee:planner writes tiers into the plan (docs/plans/ -plan.md); /bee:plan-implementer then resolves a tier to the value below and passes it as the model when spawning an agent via the Task tool. No spec, agent prompt, command, or routing decision ever names a concrete model.
More from this repo
ai-ergonomics
This skill should be used when evaluating how well code supports LLM-assisted development.
ai-workflow
This skill should be used when explaining why Bee follows spec-first TDD workflows, or when teaching mode is on.
architecture-patterns
This skill should be used when evaluating architecture options, checking dependency direction, or deciding between...