~ / rigs / vstorm-co / pydantic-deepagents

vstorm-co/pydantic-deepagents

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

↗ GitHub ★ 1,076 mit updated 24d ago collection Claude CodeCodex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~5.0k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/vstorm-co/pydantic-deepagents

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 vstorm-co/pydantic-deepagents/apps/cli/skills/build-and-compile .claude/skills/build-and-compile
$ npx degit vstorm-co/pydantic-deepagents/apps/cli/skills/code-review .claude/skills/code-review
$ npx degit vstorm-co/pydantic-deepagents/apps/cli/skills/data-formats .claude/skills/data-formats
$ npx degit vstorm-co/pydantic-deepagents/apps/cli/skills/environment-discovery .claude/skills/environment-discovery
$ npx degit vstorm-co/pydantic-deepagents/apps/cli/skills/git-workflow .claude/skills/git-workflow
$ npx degit vstorm-co/pydantic-deepagents/apps/cli/skills/performant-code .claude/skills/performant-code
$ npx degit vstorm-co/pydantic-deepagents/apps/cli/skills/refactor .claude/skills/refactor
$ npx degit vstorm-co/pydantic-deepagents/apps/cli/skills/skill-creator .claude/skills/skill-creator
$ npx degit vstorm-co/pydantic-deepagents/apps/cli/skills/systematic-debugging .claude/skills/systematic-debugging
$ npx degit vstorm-co/pydantic-deepagents/apps/cli/skills/test-writer .claude/skills/test-writer
$ npx degit vstorm-co/pydantic-deepagents/apps/cli/skills/verification-strategy .claude/skills/verification-strategy
$ npx degit vstorm-co/pydantic-deepagents/apps/deepresearch/skills/diagram-design .claude/skills/diagram-design
$ npx degit vstorm-co/pydantic-deepagents/apps/deepresearch/skills/report-writing .claude/skills/report-writing
$ npx degit vstorm-co/pydantic-deepagents/apps/deepresearch/skills/research-methodology .claude/skills/research-methodology
$ npx degit vstorm-co/pydantic-deepagents/examples/full_app/skills/data-analysis .claude/skills/data-analysis
$ npx degit vstorm-co/pydantic-deepagents/examples/full_app/skills/test-generator .claude/skills/test-generator

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 (16)

Similar rigs

copied ✓