create-agent

A template for creating a specialized Claude Code agent, including its name, purpose, available tools, model, and status color.

In plain words
What is it for?
Use it to create the agent file and define when the agent is used, which tools it can access, and which model it runs.
Why use it?
It prevents missing or incorrectly formatted configuration when adding an agent to a plugin.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/jpoutrin/product-forge/create-agent
Any agent
npx skills add jpoutrin/product-forge --skill create-agent
Clone the repo
git clone --depth 1 https://github.com/jpoutrin/product-forge

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 693 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.00693
Opus 5 $0.00024 $0.00347
Sonnet 5 $0.00010 $0.00139
Haiku 4.5 $0.00005 $0.00069

Measured 2d ago against content hash 0ab96a79cc4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/claude-code-dev/skills/create-agent/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Agent Skill

Create new Claude Code agents with proper configuration and structure.

Agent File Format

Agents are markdown files in the agents/ directory with YAML frontmatter:

---
name: agent-name
description: Full description of what the agent does and when to use it
tools: Glob, Grep, Read, Write, Edit, Bash, WebFetch, WebSearch, TodoWrite
model: sonnet
color: green
---

# Agent Title

Agent prompt content goes here...

Required Frontmatter Fields

Field Description Example
name Unique identifier (kebab-case) code-reviewer
description One-line summary of agent's purpose Reviews code for quality and best practices
tools Comma-separated list of available tools Glob, Grep, Read, Write, Edit, Bash
model Model to use: opus, sonnet, or haiku sonnet
color Status line color green, blue, purple, red, orange, cyan, magenta, yellow, pink, teal, violet

Model Selection Guidelines

  • opus: Strategic decisions, complex architecture, security-critical, compliance, executive-level analysis
  • sonnet: Technical implementation, code writing, general development tasks (most common)
  • haiku: Quick lookups, simple transformations, fast responses

Available Tools

Common tool combinations by agent type:

Code Development Agents

Glob, Grep, Read, Write, Edit, Bash, TodoWrite

Research/Analysis Agents

Glob, Grep, Read, WebFetch, WebSearch, TodoWrite

Full-Featured Agents

Glob, Grep, Read, Write, Edit, Bash, WebFetch, WebSearch, TodoWrite

Creation Process

  1. Determine the agent's purpose and expertise area
  2. Choose appropriate model based on complexity
  3. Select tools needed for the agent's tasks
  4. Write clear, actionable agent prompt
  5. Save to plugins/<plugin-name>/agents/<agent-name>.md

Example Agent

---
name: code-reviewer
description: Reviews code changes for quality, security, and best practices. Use when user wants code reviewed, needs security audit, or asks about code quality.
tools: Glob, Grep, Read, TodoWrite
model: sonnet
color: yellow
---

# Code Reviewer Agent

You are an expert code reviewer focused on quality, security, and maintainability.

## Review Checklist

- Code correctness and logic
- Security vulnerabilities
- Performance considerations
- Code style and consistency
- Test coverage
- Documentation

## Output Format

Provide structured feedback with:
1. Summary of changes
2. Issues found (categorized by severity)
3. Recommendations
4. Approval status

Read the full file on GitHub · 103 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 103 lines · 48 tokens per session scan A 0ab96a79cc4b

Subscribe to this mod's changes

create-agent is a skill published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 693 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens