agentrigs
+ submit rig
~ / rigs / JinchengGao-Infty / agent-loadout

JinchengGao-Infty/agent-loadout

Portable skills, MCP configs, and workflows for AI coding agents across Codex, Claude Code, and Gemini

↗ GitHub ★ 3 MIT updated 7mo ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~635 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 JinchengGao-Infty/agent-loadout/skills ./rig-agent-loadout/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 JinchengGao-Infty/agent-loadout/skills/ace-search .claude/skills/ace-search
$ npx degit JinchengGao-Infty/agent-loadout/skills/bib-verify .claude/skills/bib-verify
$ npx degit JinchengGao-Infty/agent-loadout/skills/clashverge-rules-debug .claude/skills/clashverge-rules-debug
$ npx degit JinchengGao-Infty/agent-loadout/skills/grok-imagine .claude/skills/grok-imagine
$ npx degit JinchengGao-Infty/agent-loadout/skills/grok-search .claude/skills/grok-search
$ npx degit JinchengGao-Infty/agent-loadout/skills/hydra .claude/skills/hydra
$ npx degit JinchengGao-Infty/agent-loadout/skills/lit-review .claude/skills/lit-review
$ npx degit JinchengGao-Infty/agent-loadout/skills/memory-palace .claude/skills/memory-palace

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 (8)

ace-searchbib-verifyclashverge-rules-debuggrok-imaginegrok-searchhydralit-reviewmemory-palace

Similar rigs

sshtomar/claude-code-skills-social-science
Claude Code skills for rigorous social science research: DID, RCTs, regression diagnostics, visualization, literature reviews, and more. Encode methodological best practices directly into your AI coding workflow.
★ 15 project Claude Code 11 skills 7mo ago
Skill Collector 789 tok ·
ccomunello/cursor-my-workflow
A ready-to-fork Cursor template for academics using LaTeX/Beamer + R based on claude-code-my-workflow. Multi-agent review, quality gates, adversarial QA, and replication protocols.
★ 0 project Claude CodeCodexCursor 28 skills 5mo ago
Skill Collector 8.6k tok ·
zhaohaoharry/claude-config
Private sync of Claude Code config: skills, hooks, agents, rules, settings, and curated memory
★ 1 setup Claude Code 26 skills 3 agents 7 hooks 1d ago
YOLO Cowboy 7.0k tok ·
pedrohcgs/claude-code-my-workflow
A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols.
★ 1,611 project Claude Code 61 skills 18 agents 12 hooks 12d ago
YOLO Cowboy 8.7k tok ·
copied ✓