igorxmel/agent-offload
Let Claude, Codex or any agent hand bulk coding work to free models through OpenCode - on its own branch and worktree, behind a check the executor cannot fake.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit igorxmel/agent-offload/skills ./rig-agent-offload/skills 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.
$ npx degit igorxmel/agent-offload/skills/offload .claude/skills/offload 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 *)"
]
}
} Skills (1)
Similar rigs
zhoushoujianwork/offload
Delegate focused tasks to Codex or Claude Code with named account profiles, persistent sessions, usage tracking, and a native macOS dashboard.
Minimalist 866 tok · · Q5
haiggoh/free-agents
📡🦾 Run Claude Code on free inference — local models (Apple-Silicon MLX support, CUDA support on Linux, Windows port coming soon), and free-tier cloud APIs (NVIDIA, Gemini, & many more). Dispatch free agents for sub-tasks off your paid sessi
Pragmatist 747 tok · · Q0
inkatze/planwright
Autopilot for spec-driven development on Claude Code: sign off a spec and a guardrailed agent fleet builds, reviews, and delivers draft PRs. Scales from one feature to an agentic software factory. You keep sign-off and merge.
Skill Collector 133 tok · · Q0
Eric-Lingren/claude-code-toolkit
My Claude Code toolkit: a skill and agent pipeline from plan to merged PR, with evals, model tiering and guardrail hooks
Orchestrator 3.5k tok · · Q0