agent-creator

agent-creator is a skill for Claude Code from krzysztofsurdy/code-virtuoso. It costs 103 tokens per session (1,406 once invoked), scanned A, original, MIT.

A guided design tool for creating focused sub-agents, including their role, permissions, memory, and instructions.

In plain words
What is it for?
Use it to create an agent definition for a specialist, worker, or team lead with clear inputs and outputs.
Why use it?
It helps avoid vague agents with unclear responsibilities, excessive access, or inconsistent results.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Part of the tools-virtuoso plugin — 11 skills shipped together

Good fit Use it to create an agent definition for a specialist, worker, or team lead with clear inputs and outputs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/krzysztofsurdy/code-virtuoso/agent-creator
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 krzysztofsurdy/code-virtuoso --skill agent-creator
Clone the repo
git clone --depth 1 https://github.com/krzysztofsurdy/code-virtuoso

Made for: Claude Code.

Or install tools-virtuoso, the plugin that ships this one along with the rest of its 11 skills.

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 agent-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/agent-creator.svg)](https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/agent-creator)
Your own site
<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/agent-creator"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/agent-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,406 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00103 $0.01406
Opus 5 $0.00051 $0.00703
Sonnet 5 $0.00021 $0.00281
Haiku 4.5 $0.00010 $0.00141

Measured 8d ago against content hash a03d629bcd5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-creator 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.

skills/tools/agent-creator/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Creator

Create a sub-agent that earns its context window. Most agents fail not because the model is weak but because the definition is vague - unclear trigger, sprawling tool list, a body that mixes persona and procedure, and no output contract. This skill walks you through a six-phase design so the resulting agent is focused, least-privileged, and predictable.

Core Principles

Principle Meaning
One job, one agent An agent that does two things does neither well. Split the responsibility before writing.
Least privilege Grant the smallest tool set that lets the agent finish its job. Read-only by default.
Trigger-first description The description field is the only thing read before delegation. Pack it with keywords and "when to use".
Contract over conversation Define explicit input, process, and output. Agents are not chat sessions.
Isolation when writing If the agent edits files, run it in a worktree so the orchestrator can review before merging.
Portable body, platform frontmatter Keep the system prompt agent-agnostic. Adapt frontmatter fields per target platform.

Agent vs Skill - Quick Disambiguation

Before creating an agent, confirm it is the right primitive.

Use a Skill Use an Agent
Reference material (patterns, checklists, schemas) Work to perform (investigate, review, implement)
Loaded into an existing session Runs in its own context window
Passive knowledge Active actor with tools and a workflow
"Where do I learn about X" "Do X for me and return a result"

If the answer is reference material, stop and use the skill-creator skill instead. If the answer is work, continue.


Archetype Selection

Agents fall into three archetypes. Pick one before designing.

Archetype Scope Memory Modifies files Typical examples
Specialist Single, repeatable task type Stateless Rarely (doc writer, implementer) Investigator, Reviewer, Refactor Scout, Dependency Auditor, Test Gap Analyzer
Role Entire domain of responsibility Often persistent (project-level) Dev roles yes, others no Product Manager, Architect, Backend Dev, QA Engineer, Project Manager
Team-Lead Coordinates multiple workers in parallel Shared task list No (delegates) Orchestrator, release-train lead, review dispatcher

Read the full file on GitHub · 100 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. 8d ago First seen · 100 lines · 103 tokens per session scan A a03d629bcd5e

Subscribe to this mod's changes

agent-creator is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (21 stars, last pushed 3mo ago), licensed MIT. It adds 103 tokens to every session and 1,406 once invoked, about $0.0005 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

hermes-diagnostic-review

Use when running a read-only diagnostic review of recent Hermes sessions to find recurring mistakes, failed tool calls, and repeated fixes, then propose suggestion-only improvements and reusable skills. Human-gated; never auto-applies.

AtlasOmnia/hermes-custom-pack · 49 tokens

instruction-eval

Change one condition an agent runs under (instruction text, the reference material instructions point at, MCP tools and permissions, hooks, skill files), then run the same prompts before and after, several times each, to see what actually changes. Produces an HTML report showing both arms' answers side by side. Use…

2ykwang/agent-skills · 179 tokens

worth-building

Decide how elaborate to build something (simple vs. robust) and return a concrete, PoC-shaped proposal at that level — not over- or under-engineered, but right-sized. Use whenever someone is building something and the investment level is unclear: "quick or proper?", "MVP vs. real product", "is this over-engineering?"…

2ykwang/agent-skills · 128 tokens

django-ticket-triage

Analyze a Django Trac ticket and produce a triage recommendation report — duplicate search, related PRs, forum threads, and the affected source code. Use when the user gives a Django ticket number, or asks whether a ticket is valid, a duplicate, or ready for a triage stage.

2ykwang/agent-skills · 65 tokens

gh-issues

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…

SafeAI-Lab-X/ClawKeeper · 116 tokens

healthcheck

Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).

SafeAI-Lab-X/ClawKeeper · 70 tokens