agentrigs
+ submit rig
~ / rigs / tudoumashu / ai-memory-skillpack

tudoumashu/ai-memory-skillpack

Bounded project-memory skills for Codex CLI and Claude Code.

↗ GitHub ★ 445 MIT updated 1mo ago project Claude Code
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~260 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 tudoumashu/ai-memory-skillpack/skills ./rig-ai-memory-skillpack/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 tudoumashu/ai-memory-skillpack/skills/ai-project-memory .claude/skills/ai-project-memory
$ npx degit tudoumashu/ai-memory-skillpack/skills/llm-wiki .claude/skills/llm-wiki
$ npx degit tudoumashu/ai-memory-skillpack/skills/project-mastery-coach .claude/skills/project-mastery-coach

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)

ai-project-memoryllm-wikiproject-mastery-coach

Similar rigs

praneybehl/llm-wiki-plugin
Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.
★ 102 collection Codex 1 skills 26d ago
Minimalist 259 tok ·
TheSmuks/ai-project-template
Universal starter template for AI/LLM projects. Optimized for Oh My Pi (OMP) with cross-agent compatibility (AGENTS.md, Cursor, Codex, etc.).
★ 7 collection Codex 5 skills 5mo ago
Pragmatist 2.2k tok ·
panakh/agentic-os
A working agentic setup for Claude Code in one command: starter workspace, protocol skills, self-running routines, local Studio dashboard.
★ 2 project Claude CodeCodex 8 skills 3 hooks 3mo ago
Pragmatist 1.5k tok ·
jellydn/my-ai-tools
Comprehensive configuration management for AI coding tools - Replicate my complete setup for Claude Code, OpenCode, Amp, Li, Codex and Claude Code Switch with custom configurations, MCP servers, plugins, and commands.
★ 123 project Claude CodeCodexGemini CLI 11 mcp 40 skills today
MCP Hoarder 26.4k tok ·
copied ✓