agent-creator
Create new OpenCode agents with a gpt-5.2-codex default.
Skill by different-ai
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/different-ai-agent-creator
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-creator
What's inside
- Skill name
agent-creator- Description
- Create new OpenCode agents with a gpt-5.2-codex default.
- License
- unknown
- Instructions
- 48 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Instructions read files in your home folder (~/.ssh, ~/.aws…)
Files (5)
- .env.example
- SKILL.md
- client.ts
- first-call.ts
- load-env.ts
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from different-ai/openwork-hub
- 0.498score
worktree-ux-pr
different-ai
Automate the worktree-based UX PR workflow: rebase against origin/dev, verify via Chrome MCP, and attach evidence.
SkillDFreshness: D★ 34Claude Code +9 - 0.498score
sandbox-lifecycle-fastlane
different-ai
Fast preflight for sandbox lifecycle work: sync pins, create a worktree, and run the standard Docker + Chrome MCP verification path.
SkillDFreshness: D★ 34Claude Code +9 - 0.498score
owpenbot-test
different-ai
Run owpenbot/openwrk integration tests with Telegram test tokens.
SkillDFreshness: D★ 34Claude Code +9 - 0.498score
sync-submodules
different-ai
Safely sync/pull the superproject and update git submodules, including handling dirty submodules (e.g.
SkillDFreshness: D★ 34Claude Code +9 - 0.498score
worktree-workflow
different-ai
Enforce a worktree-per-task workflow with regular commits and pushes.
SkillDFreshness: D★ 34Claude Code +9 - 0.493score
openwork-chrome-mcp-testing
different-ai
Use Chrome MCP to verify OpenWork UI flows, especially any feature that touches remote behavior.
SkillDFreshness: D★ 34Claude Code +9 - 0.493score
mcp-arch
different-ai
Explain how MCP is wired between OpenWork, OpenCode, and the OpenWork server, and guide config or auth troubleshooting.
SkillDFreshness: D★ 34Claude Code +9 - 0.493score
openwork-docker-chrome-mcp
different-ai
Start the OpenWork dev stack via Docker and verify real user flows via Chrome MCP.
SkillDFreshness: D★ 34Claude Code +9 - 0.493score
research-doc
different-ai
Create and commit a research doc in research/ for a requested topic.
SkillDFreshness: D★ 34Claude Code +9 - 0.490score
screenpipe
different-ai
Screenpipe records your screen and microphone 24/7.
SkillDFreshness: D★ 34Claude Code +9 - 0.489score
create-cal-com-link
different-ai
Create targeted Cal links for specific people or teams
SkillDFreshness: D★ 34Claude Code +9 - 0.487score
workspace-guide
different-ai
Workspace guide to introduce OpenWork and onboard new users.
SkillDFreshness: D★ 34Claude Code +9
Signals
- Stars
- 34
- Forks
- 13
- Open issues
- 0
- Last commit (this folder)
- Feb 11, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/different-ai/openwork-hub
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from different-ai
- 0.694score
AGENTS.md · different-ai/openwork
different-ai
AGENTS.md from different-ai/openwork: 97 lines covering Confidentiality (hard rule — this repo is public), Generated API contracts, Coding, Verify changes…
TemplateAFreshness: A★ 24.2KCodex +5 - 0.498score
owpenbot-test
different-ai
Run owpenbot/openwrk integration tests with Telegram test tokens.
SkillDFreshness: D★ 34Claude Code +9 - 0.498score
worktree-ux-pr
different-ai
Automate the worktree-based UX PR workflow: rebase against origin/dev, verify via Chrome MCP, and attach evidence.
SkillDFreshness: D★ 34Claude Code +9 - 0.498score
sync-submodules
different-ai
Safely sync/pull the superproject and update git submodules, including handling dirty submodules (e.g.
SkillDFreshness: D★ 34Claude Code +9 - 0.498score
sandbox-lifecycle-fastlane
different-ai
Fast preflight for sandbox lifecycle work: sync pins, create a worktree, and run the standard Docker + Chrome MCP verification path.
SkillDFreshness: D★ 34Claude Code +9 - 0.498score
worktree-workflow
different-ai
Enforce a worktree-per-task workflow with regular commits and pushes.
SkillDFreshness: D★ 34Claude Code +9
Cite this page
agent-creator skill. Agent Mart. https://agentmart.dev/skills/different-ai-agent-creator (last updated 2026-10-24)