agent-creator

agent-creator is a skill for Claude Code, Codex from anilcancakir/claude-code-plugin. It costs 32 tokens per session (1,466 once invoked), scanned A, original, MIT.

A tool for creating Claude Code agents with defined roles, working steps, output formats, and limits. An agent is a focused worker that analyzes information or carries out a particular task.

In plain words
What is it for?
Use it to design advisory, execution, or search agents for Claude Code plugins, including agents that read only, make changes, or perform bounded lookups.
Why use it?
It gives each agent a clear responsibility and response format, reducing overlap and making failures or restrictions explicit.

Skill for Claude CodeCodex

Part of the ac plugin — 6 skills, 9 commands, 2 hooks 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-plugin/agent-creator
Any agent
npx skills add anilcancakir/claude-code-plugin --skill agent-creator
Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code-plugin

Made for: Claude Code, Codex.

Or install ac, the plugin that ships this one along with the rest of its 6 skills, 9 commands, 2 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 agent-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/anilcancakir/claude-code-plugin/agent-creator.svg)](https://agentmods.dev/skills/anilcancakir/claude-code-plugin/agent-creator)
Your own site
<a href="https://agentmods.dev/skills/anilcancakir/claude-code-plugin/agent-creator"><img src="https://agentmods.dev/badge/skills/anilcancakir/claude-code-plugin/agent-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,466 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 $0.00032 $0.01466
Opus 5 $0.00016 $0.00733
Sonnet 5 $0.00006 $0.00293
Haiku 4.5 $0.00003 $0.00147

Measured 3d ago against content hash dc7a6892b46b, 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 · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Claude Code agents that follow the kodizm 5-section format — Identity, Execution, Output Format, Failure Conditions, Constraints — producing concise, CC-optimized agent definitions.

Core Process

1. Classify Agent Type

Determine the agent's role before drafting:

Type Posture Key Traits
Advisory Read-only (declared in Constraints) Analyzes, reports findings, never writes
Execution Write access Implements changes, runs tests, verifies own work
Search Read-only + maxTurns cap Fast lookup, bounded turns, structured references

If the agent's purpose spans types, default to the more restrictive — advisory over execution. Execution agents must justify write access in their Identity.

2. Research Existing Agents

Use Glob + Read directly to find similar agents in the target project:

  • Glob **/agents/*.md under the plugin root, scan frontmatter description for overlapping responsibilities
  • Read 2-3 closest matches to absorb naming, structure, and style
  • Check for naming conflicts — agent names must be unique within the plugin

3. Dedup Audit

Before drafting, identify what CC already provides so the agent does not repeat it:

  • CC auto-injects: identity preamble, tool schemas, permissions, CLAUDE.md
  • CLAUDE.md provides: project architecture, conventions, stack info
  • Parent prompt provides: task briefing, specific context for this invocation

Read ${CLAUDE_SKILL_DIR}/../prompt-writer/references/cc-dedup-guide.md for the full dedup checklist. Strip anything CC or CLAUDE.md already covers — every repeated token wastes context budget.

4. Draft Agent

Follow the kodizm 5-section format from references/agent-patterns.md. Read it before drafting any agent.

Section targets:

Section Lines Purpose
Identity 1-3 Role + mission in imperative form
Execution 10-30 Numbered steps or strategy
Output Format 5-15 Structured markdown template
Failure Conditions 3-8 "FAILED if:" checklist
Constraints 2-5 Scope, style, hard limits, read-only posture if applicable

Read the full file on GitHub · 158 lines

Files

What ships with it

1 file 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 · 158 lines · 32 tokens per session scan A dc7a6892b46b

Subscribe to this mod's changes

agent-creator is a skill published in the GitHub repository anilcancakir/claude-code-plugin (2 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,466 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

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

python-feature-lifecycle

Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.

microsoft/agent-framework · 43 tokens

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens

python-code-quality

Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.

microsoft/agent-framework · 40 tokens

verify-dotnet-samples

How to build, run and verify the .NET sample projects in the Agent Framework repository. Use this when a user wants to verify that the samples still function as expected.

microsoft/agent-framework · 40 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens