What is create-subagent?

A command for creating a subagent, a separate agent given a specialised task that another agent can delegate to.

Use it to create a specialised helper for delegated coding work.

It helps split work into focused tasks that can be handled independently.

How fltman/project-scaffolder configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to fltman/project-scaffolder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/fltman/project-scaffolder/main/.claude/commands/create-subagent.md

Clone the repo

git clone --depth 1 https://github.com/fltman/project-scaffolder

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/fltman/project-scaffolder/create-subagent/github.svg)](https://agentmods.dev/commands/fltman/project-scaffolder/create-subagent)

Your own site

<a href="https://agentmods.dev/commands/fltman/project-scaffolder/create-subagent"><img src="https://agentmods.dev/badge/commands/fltman/project-scaffolder/create-subagent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/fltman/project-scaffolder/create-subagent"><img src="https://agentmods.dev/badge/commands/fltman/project-scaffolder/create-subagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 848 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00848
Opus 5.5	$0.00000	$0.00339
Sonnet 5.5	$0.00000	$0.00170
Haiku 4.5	$0.00000	$0.00085

Measured 2mo ago against content hash 6bda7547ccdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-subagent 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 2mo 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.

.claude/commands/create-subagent.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a Custom Subagent

Create a specialized subagent for delegated tasks.

Arguments

$ARGUMENTS should contain: <subagent-name> [description]

What Are Subagents?

Subagents are specialized AI assistants that:

Have their own context window (preserves main conversation)
Can be configured with specific tools
Have custom system prompts
Are automatically invoked when matching tasks appear

Subagent Creation Process

Step 1: Gather Information

Ask the user:

Name: Short, descriptive (kebab-case, e.g., test-runner)
Purpose: What specific task does this subagent handle?
Trigger: When should Claude delegate to this subagent?
Tools needed: What tools does it need? (or inherit all)
Model: sonnet (default), opus, haiku, or inherit

Step 2: Choose Scope

Project-level (.claude/agents/): Available only in this project
User-level (~/.claude/agents/): Available across all projects

Recommend project-level for project-specific workflows.

Step 3: Generate Subagent File

Create the subagent with this structure:

---
name: <name>
description: <description>. Use PROACTIVELY when <trigger condition>.
tools: <tool1>, <tool2>  # Or omit to inherit all tools
model: <model>           # Optional: sonnet/opus/haiku/inherit
---

<Detailed system prompt>

## When Invoked
1. First step
2. Second step
...

## Process
<Detailed instructions>

## Output Format
<Expected output structure>

Step 4: Write an Effective Description

The description is CRITICAL for automatic invocation. Include:

What the subagent does
"Use PROACTIVELY" or "MUST BE USED" for automatic triggering
Specific trigger conditions

Good descriptions:

"Expert code reviewer. Use PROACTIVELY after writing or modifying code."
"Test runner specialist. MUST BE USED when tests fail or new tests needed."

Bad descriptions:

"Helps with code" (too vague)
"Reviews things" (no trigger)

Step 5: Configure Tools

Read the full file on GitHub · 138 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.

2mo ago First seen · 138 lines · 0 tokens per session scan A 6bda7547ccdc

Subscribe to this mod's changes

create-subagent is a command published in the GitHub repository fltman/project-scaffolder (88 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 848 tokens. 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.

Building agents

create-subagent next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
create-subagentfltman/project-scaffolder	Command	88	9d ago	MIT	A	0	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code

project-scaffolder: Command for Claude Code