Agent Creator

What it does

When your agent uses it

• Tasks that involve Building AI agents

Example prompts

• “Use the agent-creator skill to create new specialized agents with frontmatter, tools, delegation”
• “/agent-creator”

Requirements

• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Grep, Glob

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Capture role -- what problem space should the agent own?
2. 2Define triggers -- which keywords or task types should route to this agent?
3. 3Choose tools -- minimal tool set, least privilege first
4. 4Choose model -- preserve the approved tier or inherit the parent selection; verify available models and effort controls in the target client
5. 5Map supporting skills -- which knowledge skills should the agent reference?
6. 6Write instructions -- capabilities, constraints, escalation rules, deliverables
7. 7Validate -- frontmatter, naming, skills references, tool whitelist

What it can do on your machine

Read from SKILL.md and the folder at commit d64db2b. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash
  • Grep
  • Glob

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml and markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Creator loads about 1.3k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 583 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~38

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Write, Edit, Bash, Grep, Glob

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from softspark/ai-toolkit at commit d64db2b, republished under its Apache-2.0 licence (© softspark). 583 words, ~1,309 tokens.

name

agent-creator

description

Creates new specialized agents with frontmatter, tools, delegation. Triggers: new agent, create agent, agent scaffold, specialized agent.

allowed-tools

Read, Write, Edit, Bash, Grep, Glob

effort

high

disable-model-invocation

true

argument-hint

[agent name or role]

<!-- CLAUDE_CODE_ONLY_START -->

<!-- CLAUDE_CODE_ONLY_END -->

---
name: agent-name
description: "When to use this agent. Triggers: keyword1, keyword2."
tools: Read, Write, Edit
model: inherit
skills: skill-one, skill-two
---

---
name: {agent-name}
description: "When to use this agent. Triggers: keyword1, keyword2."
tools: Read, Edit
model: inherit
skills: relevant-skill
---

You are a specialized agent for {domain}.

## Responsibilities
- Responsibility one
- Responsibility two

## Constraints
- Do not edit files outside owned scope unless required
- Escalate security, data-loss, or architecture risks

## Deliverables
- Clear findings
- Specific edits or recommendations
- Validation notes

© softspark, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in app/skills/agent-creator of softspark/ai-toolkit.

Open the folder on GitHubat commit d64db2b