create-subagent

create-subagent is a skill for Claude Code from QBall-Inc/the-bulwark. It costs 42 tokens per session (4,657 once invoked), scanned A, original, MIT.

A workflow for creating Claude Code sub-agents: small agents assigned one focused job and run through the Task tool. It gathers requirements, generates the agent setup, and validates it.

In plain words
What is it for?
Use it to create, scaffold, or generate a dedicated sub-agent for a specific task.
Why use it?
It helps turn a broad request into a clearly scoped worker with suitable permissions and configuration.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Part of the the-bulwark plugin — 30 skills, 17 agents, 6 hooks shipped together

Good fit Use it to create, scaffold, or generate a dedicated sub-agent for a specific task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/qball-inc/the-bulwark/create-subagent
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.

Any agent
npx skills add QBall-Inc/the-bulwark --skill create-subagent
Clone the repo
git clone --depth 1 https://github.com/QBall-Inc/the-bulwark

Made for: Claude Code.

Or install the-bulwark, the plugin that ships this one along with the rest of its 30 skills, 17 agents, 6 hooks.

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.

agentmods badge for create-subagent

README.md
[![agentmods](https://agentmods.dev/badge/skills/qball-inc/the-bulwark/create-subagent.svg)](https://agentmods.dev/skills/qball-inc/the-bulwark/create-subagent)
Your own site
<a href="https://agentmods.dev/skills/qball-inc/the-bulwark/create-subagent"><img src="https://agentmods.dev/badge/skills/qball-inc/the-bulwark/create-subagent.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,657 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 231
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
How audits are shown
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 5.1 $0.00042 $0.04657
Opus 5 $0.00021 $0.02329
Sonnet 5 $0.00008 $0.00931
Haiku 4.5 $0.00004 $0.00466

Measured 8d ago against content hash 91c608e18d38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/create-subagent/SKILL.md · 363 lines

How it starts

The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Sub-Agent

Generates a complete single-purpose Claude Code sub-agent from a description or requirements document. Conducts an adaptive interview to understand the agent's identity and mission, determines tool permissions and supporting configuration, spawns a Sonnet sub-agent to generate the agent file, validates with anthropic-validator, and presents the scaffold with architectural decisions.

Sub-agents are invoked via Task(subagent_type=...) and run in a forked context. They perform a single focused task and return results. They cannot spawn other sub-agents — pipeline orchestration belongs in skills, not agents.


When to Use This Skill

Load this skill when the user request matches ANY of these patterns:

Trigger Pattern Example User Request
Sub-agent creation "Create a sub-agent for X", "Make an agent for X"
Agent scaffolding "Scaffold an agent", "Set up a new agent"
Agent generation "Generate an agent that does X"
Dedicated worker "Create a dedicated agent for this sub-agent role"
Task tool agent "I need an agent I can invoke via Task tool"

DO NOT use for:

  • Creating pipeline orchestration (use create-skill — it generates the orchestrating skill + sub-agent files)
  • Creating Agent Teams leads (use create-skill with the research template)
  • Creating skills (use create-skill)
  • Editing existing agents (edit directly)
  • Debugging agent issues (use issue-debugging)
  • Validating existing agents (use anthropic-validator)

Dependencies

Category Files Requirement When to Load
Decision framework references/decision-framework.md REQUIRED Load at Stage 0 for interview + classification
Agent conventions references/agent-conventions.md REQUIRED Include in Stage 2 generator prompt
Content guidance references/content-guidance.md REQUIRED Include in Stage 2 generator prompt
Agent template references/template-single-agent.md REQUIRED Load at Stage 2
Diagnostic template templates/diagnostic-output.yaml REQUIRED Use at Stage 6
Subagent prompting subagent-prompting skill REQUIRED Load at Stage 0 for 4-part prompt template

Read the full file on GitHub · 363 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 363 lines · 42 tokens per session scan A 91c608e18d38

Subscribe to this mod's changes

create-subagent is a skill published in the GitHub repository QBall-Inc/the-bulwark (8 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 4,657 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 2026-08-31.

Related

Other skills, from other repositories

github-pr-review

Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…

fvadicamo/dev-agent-skills · 95 tokens

privacy-guard

Prevents private infrastructure details (node hostnames, internal project names, local usernames and personal emails, absolute home paths, private and VPN IP ranges) from leaking into public repositories through commits, PRs, docs or release artifacts. Use when working in a public or soon-to-be-public repo, before…

fvadicamo/dev-agent-skills · 128 tokens

github-pr-merge

Merges GitHub Pull Requests after validating pre-merge checklist. Use when user wants to merge PR, close PR, finalize PR, complete merge, approve and merge, or execute merge. Runs pre-merge validation (tests, lint, CI, comments), confirms with user, merges with proper format, handles post-merge cleanup.

fvadicamo/dev-agent-skills · 72 tokens

github-pr-creation

Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…

fvadicamo/dev-agent-skills · 75 tokens

git-commit

Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.

fvadicamo/dev-agent-skills · 49 tokens

resolve-plugins

Curate Claude Code skill / MCP / hook picks against live upstream sources and pin them in .claude/settings.json. Adding a process harness (a paired skill set) is an ordinary pick this door handles. Reads stack from docs/techstack.md, workflow signal from docs/overview.md + existing pins, then live-queries six source…

RockyHong/super-bootstrap · 133 tokens