Agent skill · Security

write-subagent

CRITICAL: Before deploying any subagent, spawn a reviewer agent with REVIEW.md to audit tools. Overly permissive tool access can cause data loss or leak secrets.'

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill write-subagent --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 7 KB
Bundled scripts: none
Path: skills/agent/write-subagent/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

--- name: write-subagent description: Use when the user wants to create a new Claude Code subagent. Guides subagent creation with focused prompts and constrained tool access. argument-hint: "[global|local] [subagent-name] [purpose...]" {{- template "bedrock-model" (dict "tier" "opus" "root" .) }} disable-model-invocation: true allowed-tools: - Read - Glob - Grep - Write - Bash(chezmoi apply:*) - Bash(chezmoi diff:*) - Bash(chezmoi status:*) --- # Subagent Creation Playbook **CRITICAL: Before deploying any subagent, spawn a reviewer agent with REVIEW.md to audit `tools`. Overly permissive tool access can cause data loss or leak secrets.** Create subagents as focused specialists, not general-purpose assistants. ## Arguments ``` $ARGUMENTS ``` ## Process ### 0. Determine Scope Check if arguments specify `global` or `local`: - **`global`** or **`in ~/.claude/agents/`** → Subagent goes in dotfiles via chezmoi, available everywhere - **`local`** or **`in .claude/agents/`** → Subagent goes in current project's `.claude/agents/`, scoped to this repo If scope is unclear, ask: > "Should this subagent be **global** (available in all projects via dotfiles) or **local** (scoped to this project

What's inside
Steps it walks through
  1. Arguments
  2. Process
  3. 0. Determine Scope
  4. 1. No Arguments? Extract from Conversation
  5. 2. Gather Context (when args provided)
  6. 3. Draft Subagent
  7. 4. Principles
  8. 5. Review (REQUIRED)
  9. Quick Reference
  10. Supplementary Docs
  11. Examples
  12. Scope Decision Guide
  13. Anti-patterns
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the write-subagent skill do?

CRITICAL: Before deploying any subagent, spawn a reviewer agent with REVIEW.md to audit tools. Overly permissive tool access can cause data loss or leak secrets.'

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill write-subagent --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going