agentrigs
+ submit rig
~ / rigs / Aryan-Saini / agent-fleet

Aryan-Saini/agent-fleet

Run coding agents on an always-on worker box, driven from your laptop and phone. Same rules and skills in every harness. Self-healing, never silent.

↗ GitHub ★ 0 MIT updated 1d ago personal setup Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.4k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit Aryan-Saini/agent-fleet/skills ./rig-agent-fleet/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 Aryan-Saini/agent-fleet/skills/automation .claude/skills/automation
$ npx degit Aryan-Saini/agent-fleet/skills/codex-implementation .claude/skills/codex-implementation
$ npx degit Aryan-Saini/agent-fleet/skills/edit-md-files .claude/skills/edit-md-files
$ npx degit Aryan-Saini/agent-fleet/skills/file-pr .claude/skills/file-pr
$ npx degit Aryan-Saini/agent-fleet/skills/fleet .claude/skills/fleet
$ npx degit Aryan-Saini/agent-fleet/skills/subagents .claude/skills/subagents
$ npx degit Aryan-Saini/agent-fleet/skills/technical-writing .claude/skills/technical-writing
$ npx degit Aryan-Saini/agent-fleet/skills/unslop .claude/skills/unslop
$ npx degit Aryan-Saini/agent-fleet/skills/worker .claude/skills/worker

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (9)

automationcodex-implementationedit-md-filesfile-prfleetsubagentstechnical-writingunslopworker

Similar rigs

danjdewhurst/dotclaude
Global Claude Code config, synced between machines by one script: CLAUDE.md, writing rules, vendored skills and the bash environment commands run in, symlinked into ~/.claude and wherever Codex and other agents look
★ 6 setup Claude Code 6 skills 15d ago
Pragmatist 398 tok ·
devon-systems/hoenn
NixOS, nix-darwin, and Home Manager configurations, ft. niri+noctlaia dotfiles + homelab.
★ 238 setup Codex 10 skills 13d ago
Skill Collector 1.2k tok ·
Waishnav/devspace
Minimal Coding Agent Harness on MCP for ChatGPT, Claude, Hermes, Grok Bot, OpenClaw
★ 5,189 project Codex 2 skills 4d ago
Minimalist 2.2k tok ·
exPardus/fleet
Fleet manager for Claude Code: one manager session spawns, steers, and monitors many durable headless Claude Code agent sessions in parallel across projects. Mid-turn steering, token budgets, usage-limit park/resume, journals + respawn, git
★ 4 project Claude CodeCodex 2 skills 1d ago
Pragmatist 851 tok ·
copied ✓