Agent Types
Reference catalog matching built-in and plugin agent types (Explore, Plan, sdlc:*, swarm:rlm-*) to tasks.
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 15, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · b19039c
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.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 3/5
What Agent Types does
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.
How to install Agent Types
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
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Agent Types
-
/agent-typesReference catalog matching built-in and plugin agent types (Explore, Plan, sdlc:*, swarm:rlm-*) to tasks.
It also activates on plain-language prompts like these:
-
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
Frequently asked questions
- Is the Agent Types skill free?
- Yes. The skill itself is free from zircote/claude-team-orchestration. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Agent Types work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Works with setup. 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.
- What is the Agent Types SkillProof Score?
- 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.
- How do I install Agent Types?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Agent Types with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.