How do I install the Agent Template skill?

Run npx skillmds@latest add claude-world-director-mode-lite/agent-template in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Agent Template safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Agent Template?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Agent Template free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Agent Template?

claude-world (@claude-world-director-mode-lite) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Agent Template by claude-world-director-mode-lite

Name: Agent Template
Rating: 4.2 (5 reviews)
Author: claude-world

File contents

Agent Template Generator

Generate a custom agent file based on requirements.

Usage: /agent-template [agent-name] [purpose]

Templates

Purpose	Template	Tools	Color	Model
Review/Audit	Reviewer	Read, Grep, Glob, Bash	yellow	inherit
Generate/Create	Generator	Read, Write, Grep, Glob	cyan	inherit
Fix/Modify	Fixer	Read, Write, Edit, Bash, Grep	red	inherit
Test/Validate	Tester	Read, Bash, Grep, Glob	green	inherit
Document	Documenter	Read, Write, Grep, Glob	cyan	inherit
Orchestrate	Orchestrator	Read, Write, Bash, Grep, Glob, Agent	cyan	haiku

Process

Gather Requirements
- Agent name (lowercase, hyphenated)
- Purpose
- Tools needed
- Model (fable/opus/sonnet/haiku/inherit — inherit is the recommended default)
- Preloaded skills (if any)
Select Template based on purpose
Generate File at .claude/agents/[name].md
Validate with /agent-check

Frontmatter Reference (official fields)

---
name: agent-name            # Required: lowercase, hyphenated, 3-50 chars
description: >              # Required: 200-1000 chars recommended, include <example> blocks.
  Use this agent PROACTIVELY when [triggering conditions]. Examples:
  <example>
  Context: [situation]
  user: "[request]"
  assistant: "[response]"
  <commentary>[why this agent]</commentary>
  </example>
color: cyan                 # Required by Director Mode convention (CI-enforced); optional per spec
model: inherit              # Required by Director Mode convention (CI-enforced); optional per spec.
                            #   Valid: fable, opus, sonnet, haiku, inherit, default, best, sonnet[1m],
                            #   opus[1m] (or a full model ID). inherit recommended. NOT opusplan.
effort: medium              # Optional: low, medium, high, xhigh, max
tools:                      # Optional: YAML list (omit = all tools)
  - Read
  - Write
  - Edit
  - Bash
  - Grep
  - Glob
  - Agent
  - WebFetch
  - WebSearch
  - TodoWrite
  - NotebookEdit
disallowedTools:            # Optional: explicit tool blocking
  - NotebookEdit
maxTurns: 20                # Optional: max agentic turns before stopping (positive integer)
skills:                     # Optional: preloaded skill names (list)
  - linked-skill
memory: project             # Optional: one of user, project, local
background: false           # Optional: run the agent in the background (boolean)
isolation: worktree         # Optional: run the agent in an isolated git worktree
---

Not supported in filesystem/plugin agent frontmatter — do not emit these: hooks, mcpServers, permissionMode (security restriction), and forkContext (not an official field). Agents fork automatically when dispatched.

Reviewer Template Structure

---
name: [name]
description: >
  Use this agent PROACTIVELY when [triggering conditions]. Examples:
  <example>
  Context: [situation]
  user: "[request]"
  assistant: "[response]"
  </example>
color: yellow
tools:
  - Read
  - Grep
  - Glob
  - Bash
model: inherit
skills:
  - linked-skill
# maxTurns: 20
# memory: project
---

# [Name] Agent

## Activation
When to trigger

## Review Checklist
- [ ] Check items

## Output Format
Report structure

Example

/agent-template security-scanner "scan code for vulnerabilities"

Output: Created .claude/agents/security-scanner.md

---name: agent-templatedescription: Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.user-invocable: true---# Agent Template GeneratorGenerate a custom agent file based on requirements.**Usage**: `/agent-template [agent-name] [purpose]`---## Templates| Purpose | Template | Tools | Color | Model ||---------|----------|-------|-------|-------|| Review/Audit | Reviewer | Read, Grep, Glob, Bash | yellow | inherit || Generate/Create | Generator | Read, Write, Grep, Glob | cyan | inherit || Fix/Modify | Fixer | Read, Write, Edit, Bash, Grep | red | inherit || Test/Validate | Tester | Read, Bash, Grep, Glob | green | inherit || Document | Documenter | Read, Write, Grep, Glob | cyan | inherit || Orchestrate | Orchestrator | Read, Write, Bash, Grep, Glob, Agent | cyan | haiku |---## Process1. **Gather Requirements** - Agent name (lowercase, hyphenated) - Purpose - Tools needed - Model (fable/opus/sonnet/haiku/inherit — inherit is the recommended default) - Preloaded skills (if any)2. **Select Template** based on purpose3. **Generate File** at `.claude/agents/[name].md`4. **Validate** with `/agent-check`---## Frontmatter Reference (official fields)```yaml---name: agent-name # Required: lowercase, hyphenated, 3-50 charsdescription: > # Required: 200-1000 chars recommended, include <example> blocks. Use this agent PROACTIVELY when [triggering conditions]. Examples: <example> Context: [situation] user: "[request]" assistant: "[response]" <commentary>[why this agent]</commentary> </example>color: cyan # Required by Director Mode convention (CI-enforced); optional per specmodel: inherit # Required by Director Mode convention (CI-enforced); optional per spec. # Valid: fable, opus, sonnet, haiku, inherit, default, best, sonnet[1m], # opus[1m] (or a full model ID). inherit recommended. NOT opusplan.effort: medium # Optional: low, medium, high, xhigh, maxtools: # Optional: YAML list (omit = all tools) - Read - Write - Edit - Bash - Grep - Glob - Agent - WebFetch - WebSearch - TodoWrite - NotebookEditdisallowedTools: # Optional: explicit tool blocking - NotebookEditmaxTurns: 20 # Optional: max agentic turns before stopping (positive integer)skills: # Optional: preloaded skill names (list) - linked-skillmemory: project # Optional: one of user, project, localbackground: false # Optional: run the agent in the background (boolean)isolation: worktree # Optional: run the agent in an isolated git worktree---```**Not supported in filesystem/plugin agent frontmatter** — do not emit these:`hooks`, `mcpServers`, `permissionMode` (security restriction), and `forkContext`(not an official field). Agents fork automatically when dispatched.---## Reviewer Template Structure```markdown---name: [name]description: > Use this agent PROACTIVELY when [triggering conditions]. Examples: <example> Context: [situation] user: "[request]" assistant: "[response]" </example>color: yellowtools: - Read - Grep - Glob - Bashmodel: inheritskills: - linked-skill# maxTurns: 20# memory: project---# [Name] Agent## ActivationWhen to trigger## Review Checklist- [ ] Check items## Output FormatReport structure```---## Example```/agent-template security-scanner "scan code for vulnerabilities"Output: Created .claude/agents/security-scanner.md```

Frequently asked questions

Agent Template