agentrigs
+ submit rig
~ / rigs / IonDen / skills

IonDen/skills

Agent skills for Claude Code and OpenAI Codex: audit subagents (subagent-optimizer), shrink SKILL.md files (skill-optimizer), and write tests that can fail (writing-tests-that-can-fail).

↗ GitHub ★ 1 mit updated 8d ago collection Claude Code Claude plugin
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~40 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/IonDen/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 IonDen/skills/plugins/ionden-skills/skills/skill-optimizer .claude/skills/skill-optimizer
$ npx degit IonDen/skills/plugins/ionden-skills/skills/subagent-optimizer .claude/skills/subagent-optimizer
$ npx degit IonDen/skills/plugins/ionden-skills/skills/writing-tests-that-can-fail .claude/skills/writing-tests-that-can-fail

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)

skill-optimizersubagent-optimizerwriting-tests-that-can-fail

Similar rigs

s977043/river-review
レビューを、組織の判断資産へ。Review Judgment as Code for AI-assisted development — codify your team's review standards as repo-owned skills and run them across the SDLC.
★ 4 project Claude CodeCodexCursor 8 skills 1 agents 3 hooks today
Fort Knox 7.2k tok ·
mcollina/skills
My own collection of skills for modern Node.js development
★ 1,947 collection Codex 11 skills 2mo ago
Skill Collector 1.6k tok ·
stevenmays/dotfiles
tooling
★ 12 setup Claude Code 16 skills 1 agents 1d ago
Skill Collector 1.3k tok ·
danieldeusing/seedr
Seed your coding agents with capabilities — CLI + registry for AI coding assistant content
★ 0 project Claude CodeCodex 24 skills 1 hooks today
Skill Collector 4.8k tok ·
copied ✓