agent-creator

agent-creator is a skill for Claude Code from bjorn-ingmanson/thefroject-plugins. It costs 76 tokens per session (954 once invoked), scanned A, original, MIT.

A guided tool for designing and generating specialized Claude Code sub-agents. A sub-agent is a separate assistant configured for one focused job in a project.

In plain words
What is it for?
Creating agents for jobs such as code review or drafting customer replies, after clarifying their single responsibility, required information, and workspace setup.
Why use it?
It helps turn a vague request for an assistant into a clear definition with suitable context and tool limits. It also checks existing project patterns to avoid duplicates.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Part of the thefroject-customer-success plugin — 47 skills, 11 commands shipped together

Good fit Creating agents for jobs such as code review or drafting customer replies, after clarifying their single responsibility, required information, and workspace setup.

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

Made for: Claude Code.

Or install thefroject-customer-success, the plugin that ships this one along with the rest of its 47 skills, 11 commands.

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/bjorn-ingmanson/thefroject-plugins/agent-creator.svg)](https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/agent-creator)
Your own site
<a href="https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/agent-creator"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/agent-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 954 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 $0.00076 $0.00954
Opus 5 $0.00038 $0.00477
Sonnet 5 $0.00015 $0.00191
Haiku 4.5 $0.00008 $0.00095

Measured 6d ago against content hash a592f6945262, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 6d 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.

customer-success/skills/agent-creator/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Creator

Design Claude Code sub-agents through a short interview, then generate the agent file. Agents are best when their job, tool restrictions, and context boundary are crisp.

Gather Context First

  1. Read context/ for project conventions and existing agent patterns
  2. Scan .claude/agents/ for existing agents — avoid duplicates, match the file style
  3. Identify the workspace's project type (software, marketing, sales, ops, etc.) — this shapes which tools the agent should have

The Interview

Run these in order. Don't generate the agent until all five answers are clear.

1. What is the one job?

A good agent does one thing well. If the answer to "what does this agent do?" needs the word "and," push back.

Weak (multi-job) Strong (one job)
"Reviews code and writes tests and documents APIs" "Reviews code for bugs and security issues"
"Handles customer questions and updates the CRM" "Drafts customer replies in our voice"
"Plans the week and tracks progress" "Generates a weekly plan from quarterly priorities"

2. What does the agent need to read?

List the files, directories, or external sources required. Be specific:

  • Files in outputs/transcripts/?
  • Active plans in plans/?
  • The git diff?
  • A specific reference doc?

Reading scope determines context size. Smaller scope means faster, more focused agents.

3. What does the agent produce?

The output should be one of:

  • A specific file path (e.g. outputs/reviews/<pr>.md)
  • A structured response shown to the user (markdown report, JSON)
  • An action taken on the system (file moved, label applied)

If it's "a recommendation," push for the format — "a markdown checklist," "a 3-bullet summary."

4. Which tools does it need?

Default to the smallest tool surface that gets the job done:

Agent type Typical tools
Read-only research / review Read, Grep, Glob
Code writer Read, Edit, Write, Bash, Grep, Glob
Auditor running commands Read, Grep, Glob, Bash
External-API caller Read + the relevant MCP tool

Read the full file on GitHub · 119 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. 6d ago First seen · 119 lines · 76 tokens per session scan A a592f6945262

Subscribe to this mod's changes

agent-creator is a skill published in the GitHub repository bjorn-ingmanson/thefroject-plugins (1 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 954 once invoked, about $0.0004 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens