agentrigs
+ submit rig
~ / rigs / tj-agents / nvim

tj-agents/nvim

Neovim learning companion for AI coding agents — teaching method, curriculum and progress tracker over Tommy's nvim config.

↗ GitHub ★ 0 no license updated 2d ago project Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~473 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 tj-agents/nvim/.claude ./rig-nvim  # 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 tj-agents/nvim/.claude/skills/direction .claude/skills/direction
$ npx degit tj-agents/nvim/.claude/skills/knowledge .claude/skills/knowledge
$ npx degit tj-agents/nvim/.claude/skills/learning .claude/skills/learning

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 (3)

directionknowledgelearning

Similar rigs

iamvenuti/garrick
An AI chief of staff for knowledge work: remembers your work and knows whose confidences you hold. Runs on Claude Code or Codex, in files you own.
★ 1 project Codex 7 skills today
Pragmatist 1.9k tok ·
qkitzero/kage-bunshin
🥷 AI agents for knowledge work, not code
★ 1 project Claude Code 5 skills 4 agents 6mo ago
Pragmatist 991 tok ·
whexy/dotfiles
My personal Nix configuration for all my machines: NixOS, Macs, WSL. [maintainer=@whexy]
★ 3 setup Codex 10 skills 1d ago
Skill Collector 2.2k tok ·
tj-agents/dotnet
Personal global config for AI coding agents (Claude Code, Codex) — shared skills, instructions, and settings synced across machines.
★ 0 project Claude CodeCodex 43 skills 4 hooks 2d ago
Skill Collector 5.5k tok ·
copied ✓