agentrigs
+ submit rig
~ / rigs / regent-vcs / re_gent

regent-vcs/re_gent

Version control for AI agents — track what your agent did, blame any line to a prompt, inspect any step.

↗ GitHub ★ 795 apache-2.0 updated 3mo ago project Claude CodeCodex
share on X
ARCHETYPE
Automator
Hooks on every lifecycle event: format, lint, notify, log.
CONTEXT TAX · EVERY TURN
~4.1k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit regent-vcs/re_gent/.claude ./rig-re_gent  # inspect, then merge into .claude/

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 regent-vcs/re_gent/.agents/skills/blame .claude/skills/blame
$ npx degit regent-vcs/re_gent/.agents/skills/log .claude/skills/log
$ npx degit regent-vcs/re_gent/.agents/skills/show .claude/skills/show
$ npx degit regent-vcs/re_gent/.claude/skills/rewind .claude/skills/rewind

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

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

Skills (4)

blamelogshowrewind

Hooks (6)

eventmatcherruns
UserPromptSubmit*rgt message-hook user
Stop*rgt message-hook assistant
PostToolBatch*rgt tool-batch-hook
PostToolBatch*rgt tool-batch-hook
Stop*rgt message-hook assistant
UserPromptSubmit*rgt message-hook user

Similar rigs

matteolippi/claude-dotfiles
—
★ 0 setup Claude Code 1 skills 5mo ago
Minimalist 9 tok ·
thehimanshushukla/personal-cortex
Cortex: a working record for your AI sessions. Guided setup, start card, enforced logging, follow-ups, and Suggest. Plugin for Claude Code and Codex; its AGENTS.md also works in Cursor, Gemini CLI and Copilot.
★ 1 project Claude CodeCodexGemini CLI 14 skills 3d ago
Skill Collector 2.3k tok ·
RockyHong/super-bootstrap
Claude Code plugin: one command scaffolds CLAUDE.md, picks skills/MCPs for your stack, and adds a route-aware workflow with doc-sync commit gate.
★ 3 project Claude CodeCodex 17 skills 1 agents 8 hooks 2d ago
Skill Collector 6.5k tok ·
byjunyoung/claude-product-skills
Claude Code skills aimed at product work rather than the codebase — the Figma file you draw in and the spec beside it
★ 5 collection Claude Code 22 skills 1d ago
Skill Collector 3.1k tok ·
copied ✓