agent-development
Explains how to write a subagent: frontmatter, the when-to-use description, tools and the system prompt.
- Kind
- Skill
- Works with
- Claude Code
- Source
- anthropics/claude-plugins-official @ 58267944f921
- Path
- plugins/plugin-dev/skills/agent-development/SKILL.md
- Jobs
- Documentation
Credit
- Made by
- anthropics
- Original
- github.com/anthropics/claude-plugins-official/blob/58267944f9…
- License
- Apache-2.0
Listed by Skill Manifest; not made by us.
InstallInstall it from a plugin marketplace.
/plugin install plugin-dev@claude-plugins-official
Install factsScanned 2 Nov 2026
- Adds
- .claude/skills/agent-development/ (the skill folder)
- 5 file(s) the skill refers to
- Runs scripts
- None found
- Uses the network
- None found
- Needs secrets
- None found
- Source revision
- 58267944f921
- Licence
- Apache-2.0
- Last activity
- 1 Nov 2026
- Review
- Reviewed
Found by a static scan of the stored text; nothing is run. “None found” is not a guarantee, so read what you install before you run it.
- Only the main file is read; other files in the folder are not scanned
# Agent Development for Claude Code Plugins ## Overview Agents are autonomous subprocesses that handle complex, multi-step tasks independently. Understanding agent structure, triggering conditions, and system prompt design enables creating powerful autonomous capabilities. **Key concepts:** - Agents are FOR autonomous work, commands are FOR user-initiated actions - Markdown file format with YAML frontmatter - Triggering via description field with examples - System prompt defines agent behavior - Model and color customization ## Agent File Structure ### Complete Format ```markdown --- name: agent-identifier description: Use this agent when [triggering conditions]. Typical triggers include [scenario 1 in prose], [scenario 2 in prose], and [scenario 3 in prose]. See "When to invoke" in the agent body for worked scenarios. model: inherit color: blue tools: ["Read", "Write", "Grep"] --- You are [agent role description]... ## When to invoke [Two to four representative scenarios written as prose, e.g.:] - **[Scenario name].** [What the situation looks like and what the agent should do.] - **[Scenario name].** [Same.] **Your Core Responsibilities:** 1. [Responsibility 1] …