agentmods.dev

agent-creator

agent-creator is a skill for Claude Code, Codex from joe-broadhead/open-cowork. It costs 27 tokens per session (508 once invoked), scanned A, original, MIT.

A design workflow for creating custom OpenCode agents, which are specialized assistants delegated particular kinds of work. It defines their role, inputs, outputs, tools, skills, and permission limits.

In plain words
What is it for?
Use it to draft and save focused agents with stable IDs, suitable read-only or write-capable tools, and clear rules for missing context.
Why use it?
It helps prevent agents from becoming too broad, over-equipped, or allowed to change more than their task requires.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions OpenCode.

not rated 11repo 5d ago A scan 27 tokens original MIT

Good fit Use it to draft and save focused agents with stable IDs, suitable read-only or write-capable tools, and clear rules for missing context.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joe-broadhead/open-cowork/agent-creator
View source ↗ joe-broadhead/open-cowork joe-broadhead.github.io
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 joe-broadhead/open-cowork --skill agent-creator
Clone the repo
git clone --depth 1 https://github.com/joe-broadhead/open-cowork

Made for: Claude Code, Codex.

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/joe-broadhead/open-cowork/agent-creator/github.svg)](https://agentmods.dev/skills/joe-broadhead/open-cowork/agent-creator)
Your own site
<a href="https://agentmods.dev/skills/joe-broadhead/open-cowork/agent-creator"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/agent-creator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/joe-broadhead/open-cowork/agent-creator"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/agent-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 508 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 $0.00027 $0.00508
Opus 5 $0.00014 $0.00254
Sonnet 5 $0.00005 $0.00102
Haiku 4.5 $0.00003 $0.00051

Measured 9d ago against content hash 4e45eb8623e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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/agent-creator/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Creator

Use this skill when a user wants to create or update a custom OpenCode agent in Open Cowork.

Purpose

  • Turn a rough specialist role into a reusable custom agent.
  • Keep the agent focused enough for reliable delegation.
  • Attach only the skills and tools the agent actually needs.
  • Save through the Agents MCP after preview and explicit confirmation.

Workflow

  1. Clarify the agent's job:
    • what work it should own
    • when the main agent should delegate to it
    • what output it should return
    • whether it may change files or product metadata
  2. Choose a clean agent id:
    • lowercase
    • hyphenated
    • stable and descriptive
    • not a built-in or existing custom agent id
  3. Select capabilities:
    • skills for reusable judgment or workflow instructions
    • tools for concrete external actions
    • read-only tools by default
    • write-capable tools only when the job requires them
  4. Draft agent instructions:
    • start with the role
    • state the expected inputs and outputs
    • include tool and skill usage guidance
    • include stop/ask conditions for missing context
    • avoid broad rules that duplicate the main Build agent
  5. Use the Agents MCP:
    • agents_list_agents and agents_get_agent before updating an existing custom agent
    • agents_preview_agent before saving any new or changed agent
    • agents_save_agent only after the user explicitly confirms the preview
    • agents_delete_agent only after explicit deletion confirmation

Guardrails

  • Built-in agents are read-only. Do not try to edit Build, Plan, General, Explore, Executive Assistant, Autoresearch, or configured bundled agents.
  • Prefer one focused custom agent over a broad catch-all.
  • Do not grant write-capable tools just because they might be useful.
  • If a skill or tool is missing, ask the user whether to create/connect it first instead of inventing an id.
  • Do not save an agent that cannot explain when it should be delegated to.

Output

  • Agent id.
  • One-sentence routing description.
  • Selected skills and tools.
  • Any write-capable permissions that will require approval.
  • Confirmation that the preview was shown before saving.

Read the full file on GitHub · 61 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. 9d ago First seen · 61 lines · 27 tokens per session scan A 4e45eb8623e5

Subscribe to this mod's changes

agent-creator is a skill published in the GitHub repository joe-broadhead/open-cowork (11 stars, last pushed 5d ago), licensed MIT. It adds 27 tokens to every session and 508 once invoked, about $0.0001 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.

Building agentsai-agentsautomationsdesktop-appelectronmcpopencode
Related

Other skills, from other repositories

imap-smtp-email

Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.

freestylefly/wesight · 82 tokens

feishu-create-doc

A skill for creating Feishu cloud documents from Lark-flavoured Markdown, a Feishu-specific form of plain-text document formatting.

op7418/CodePilot · 40 tokens

feishu-bitable

A skill for managing Feishu Bitable, a database-like spreadsheet for organising structured records. It supports tables, fields, views, filters, and bulk changes.

op7418/CodePilot · 159 tokens

feishu-calendar

A Feishu calendar and scheduling skill. It manages calendars and events and can check when people are available or busy.

op7418/CodePilot · 33 tokens

feishu-im-read

A Feishu messaging skill for reading chat history and downloading shared media. Feishu, also called Lark, is a work-chat and collaboration app.

op7418/CodePilot · 176 tokens

feishu-fetch-doc

A skill for retrieving the contents of Feishu cloud documents as Markdown. Markdown is plain text formatted with simple symbols for headings, links, and lists.

op7418/CodePilot · 42 tokens