Agent Types
Reference catalog matching built-in and plugin agent types (Explore, Plan, sdlc:*, swarm:rlm-*) to tasks.
Działa po konfiguracji
Co robi ten skill
A lookup table for choosing the right `subagent_type` for a Task() call -- built-in types (Bash, Explore, Plan, general-purpose, claude-code-guide, statusline-setup) plus an extensive catalog of plugin-provided agents (sdlc:, feature-dev:, refactor:, code-simplifier:, adr:, swarm:rlm-*, auto-harness:, human-voice:) grouped by review/research/refactoring/RLM-chunk-analysis role. Triggers when selecting an agent type, comparing agent capabilities/tool access, or matching an agent to a task.
Raport z testu
A verbatim single-folder copy breaks: the skill's own body links to 4 sibling skills (../orchestrating, ../team-management, ../orchestration-patterns, ../rlm-pattern) that live outside the agent-types folder in the source repo, and roughly two-thirds of the document's content (the whole 'Plugin Agent Types' catalog: sdlc:*, feature-dev:*, refactor:*, code-simplifier:*, adr:*, swarm:rlm-*, auto-harness:*, human-voice:*) only works if the user has separately installed each of those 8 named plugins, which the doc never flags as a prerequisite.
Testowano: 2026-07-15 · Claude Code 2.x (agent harness)
Instalacja
git clone https://github.com/zircote/claude-team-orchestration mkdir -p ~/.claude/skills cp -r claude-team-orchestration/skills/agent-types ~/.claude/skills/agent-types
Komendy i przykładowe prompty
/agent-typesReference catalog matching built-in and plugin agent types (Explore, Plan, sdlc:*, swarm:rlm-*) to tasks.
Skille uruchamiają się na zwykłe polecenia — bez komend do zapamiętania. Po instalacji aktywują go prompty takie jak te (po angielsku):
Which subagent type should I use for exploring this large codebase?What's the difference between the Explore and Plan agent types here?Help me pick the right agent type for an explore-plan-implement workflow