SinanTufekci/agent-intern
Give Claude Code or Antigravity an intern: drive Gemini (Antigravity), Codex, Copilot, Cursor and opencode as sub-agents, plus experimental Grok, Kimi and Muse. Text answers, image generation, real repo work and parallel swarms, on quota yo
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~2.7k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code
$ claude mcp add intern -- uvx agent-intern MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add intern -- uvx agent-intern $ npx degit SinanTufekci/agent-intern/plugin/skills/doctor .claude/skills/doctor $ npx degit SinanTufekci/agent-intern/plugin/skills/image .claude/skills/image $ npx degit SinanTufekci/agent-intern/plugin/skills/second-opinion .claude/skills/second-opinion
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| agent-intern · "intern" | pypi | 2.5k |
Skills (3)
Similar rigs
Mellow-Machines-Lab/buddygotchi
A little creature for your desk that keeps an eye on your AI coding agents.
Pragmatist 7.6k tok · · Q0
Abhi902/headroom-plugin
Claude Code plugin that keeps big outputs out of your context with the local, offline headroom engine: hcat compress-on-read, an automatic read gate, Dangi nudges, a savings badge in the status line, and a doctor that repairs setup with you
Pragmatist 2.7k tok · · Q0
sravan27/context-os
Cut Claude Code token usage by 40.9% and ship a CI gate for coding-agent cost leaks. Stdlib Python hook + GitHub Action for Claude Code, Codex, Cursor, and agentic coding teams.
Pragmatist 680 tok · · Q0
stickerdaniel/browserjack
Use OpenAI's installed Codex browser runtime from Claude Code or any MCP client on macOS.
Pragmatist 2.7k tok · · Q0