agent-creator

agent-creator is a skill for Claude Code, Codex from anilcancakir/claude-code. It costs 146 tokens per session (6,820 once invoked), scanned A, original, MIT.

A guide for designing and reviewing custom coding-agent worker definitions. These definitions control how delegated agents use tools, choose models, retain memory, load skills, and isolate their work.

In plain words
What is it for?
Use it to create or fix agent files, set tool and permission rules, choose execution settings, preload skills, and configure isolated worktrees.
Why use it?
It helps prevent workers from having unsuitable permissions, missing context, unclear instructions, or unsafe shared access to the main checkout.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the ac plugin — 8 skills, 3 commands, 11 agents, 3 hooks, 1 MCP server shipped together

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/anilcancakir/claude-code/agent-creator
Any agent
npx skills add anilcancakir/claude-code --skill agent-creator
Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code

Made for: Claude Code, Codex.

Or install ac, the plugin that ships this one along with the rest of its 8 skills, 3 commands, 11 agents, 3 hooks, 1 MCP server.

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/anilcancakir/claude-code/agent-creator.svg)](https://agentmods.dev/skills/anilcancakir/claude-code/agent-creator)
Your own site
<a href="https://agentmods.dev/skills/anilcancakir/claude-code/agent-creator"><img src="https://agentmods.dev/badge/skills/anilcancakir/claude-code/agent-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,820 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 $0.00146 $0.06820
Opus 5 $0.00073 $0.03410
Sonnet 5 $0.00029 $0.01364
Haiku 4.5 $0.00015 $0.00682

Measured 3d ago against content hash f493a000531e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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/ac/skills/agent-creator/SKILL.md · 435 lines

How it starts

The opening of the file, as written. The whole thing — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Creator

You are about to write or edit a Claude Code custom subagent another Claude will delegate to. An agent is a markdown file that becomes a named worker the orchestrator can spawn with the Agent tool: the parent fills in subagent_type, prompt, and optional description, name, run_in_background, isolation; Claude Code spawns a fresh isolated context, injects the agent's body as the system prompt, and runs the agent until completion. The agent returns its final message to the parent as the tool result.

This skill is the playbook for designing tool restrictions, choosing model and effort, picking permissionMode, adding memory, preloading skills, structuring the system-prompt body, and routing the storage choice. Target is Opus 5. Same patterns work for Sonnet 5 at lower cost and for Haiku 4.5, which supports no effort parameter.

Three jobs, not one

Writing a custom subagent splits into three tasks. Conflating them is the most common authoring mistake.

  1. Surrounding skill shape. File location, scope, naming, frontmatter parsing. Same rules as any markdown config. Route through ac:skill-creator for the broader file-shape decisions (scope, name validation, char budget).
  2. Agent-specific shape. Tool allowlist/denylist, model and effort, permissionMode, memory, skills: preload, isolation, background. This file teaches that.
  3. System-prompt body content. The markdown the orchestrator injects as the agent's system. This is a prompt. Route through ac:prompt-writer (architecture, snippets, anti-patterns, Opus 5 tuning) for the body, and apply the five-section pattern from ${CLAUDE_SKILL_DIR}/references/system-prompt-structure.md for the shape.

A great agent body inside the wrong shape (wrong tools, wrong model, wrong permission mode) returns useless work. A modest body inside the right shape returns sharp results every time.

What an agent actually is, mechanically

Source of truth: tools/AgentTool/loadAgentsDir.ts, tools/AgentTool/builtInAgents.ts, tools/AgentTool/built-in/<name>.ts, utils/plugins/loadPluginAgents.ts, tools/AgentTool/prompt.ts in the CC source.

Read the full file on GitHub · 435 lines

Files

What ships with it

8 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. 3d ago First seen · 435 lines · 146 tokens per session scan A f493a000531e

Subscribe to this mod's changes

agent-creator is a skill published in the GitHub repository anilcancakir/claude-code (3 stars, last pushed 15d ago), licensed MIT. It adds 146 tokens to every session and 6,820 once invoked, about $0.0007 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.