agentrigs
+ submit rig
~ / rigs / idk-arsh / data-agent-rules

idk-arsh/data-agent-rules

Rules, skills and a destructive-SQL seatbelt that keep AI coding agents (Claude Code, Codex, Cursor, Gemini CLI, Copilot) from scanning, overwriting or inventing data. With a 162-run DuckDB eval.

↗ GitHub ★ 2 MIT updated 10d ago project Codex Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.2k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/idk-arsh/data-agent-rules

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 idk-arsh/data-agent-rules/plugins/data-agent-rules/skills/dbt-changes .claude/skills/dbt-changes
$ npx degit idk-arsh/data-agent-rules/plugins/data-agent-rules/skills/explore-data .claude/skills/explore-data
$ npx degit idk-arsh/data-agent-rules/plugins/data-agent-rules/skills/safe-writes .claude/skills/safe-writes
$ npx degit idk-arsh/data-agent-rules/plugins/data-agent-rules/skills/spark-performance .claude/skills/spark-performance
$ npx degit idk-arsh/data-agent-rules/plugins/data-agent-rules/skills/test-pipelines .claude/skills/test-pipelines

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 (5)

dbt-changesexplore-datasafe-writesspark-performancetest-pipelines

Similar rigs

codeclawd/fable-mode
Run Claude Fable 5 on Opus 4.8 in Claude Code. The Mythos-class model pulled by export controls — brought back as a native agentic distillation (FABLE_CODE.md), measured playbook, verification hooks, and design/MCP/test skills. "Fable 5 Lit
★ 16 project Claude Code 7 skills 3mo ago
Pragmatist 566 tok ·
anthropics/knowledge-work-plugins
Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork
★ 26.2k collection Claude CodeCodex 32 mcp 144 skills 3d ago
MCP Hoarder 118.2k tok ·
anomalyco/opencode
The open source coding agent.
★ 212k project Codex 2 skills 1d ago
Pragmatist 4.2k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
★ 155k project CodexCursorCopilot 6 skills 4d ago
Pragmatist 1.6k tok ·
copied ✓