agentrigs
+ submit rig
~ / rigs / Memento-Teams / Memento-Skills

Memento-Teams/Memento-Skills

Memento-Skills: Let Agents Design Agents

↗ GitHub ★ 1,572 apache-2.0 updated 2mo ago collection Claude Code
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~219 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/Memento-Teams/Memento-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 Memento-Teams/Memento-Skills/builtin/skills/filesystem .claude/skills/filesystem
$ npx degit Memento-Teams/Memento-Skills/builtin/skills/skill-creator .claude/skills/skill-creator
$ npx degit Memento-Teams/Memento-Skills/builtin/skills/uv-pip-install .claude/skills/uv-pip-install
$ npx degit Memento-Teams/Memento-Skills/builtin/skills/web-search .claude/skills/web-search

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 (4)

filesystemskill-creatoruv-pip-installweb-search

Similar rigs

PleasePrompto/ductor
Control Claude Code, Codex CLI and Gemini CLI from Telegram. Live streaming, persistent memory, cron jobs, webhooks, Docker sandboxing.
★ 457 project Claude CodeCodexGemini CLI 1 skills 3mo ago
Minimalist 1.9k tok ·
Vivswan/copilot-env
Points the Codex and Claude CLIs at GitHub Copilot: a managed copilot-api proxy, or Copilot Direct.
★ 4 project Claude CodeCodexCopilot 1 skills today
Minimalist 1.7k tok ·
Abdullah-967/my-claudec0de-setup-2026
Transform Claude Code into a professional autonomous agent. This setup includes structured context handoffs, a features.json tracking system, and built-in workflows for synchronization and semantic commits.
★ 3 setup Claude Code 1 skills 7mo ago
Pragmatist 750 tok ·
Suge8/friedbun
My whole coding-agent workstation: 25 agent skills, Pi + FireCode, Herdr, Ghostty and macOS automation. Send the repo to your agent and it sets up your Mac.
★ 3 setup Codex 1 skills 1d ago
Minimalist 244 tok ·
copied ✓