agentrigs
+ submit rig
~ / rigs / talhayme / claude-plugins

talhayme/claude-plugins

Claude Code plugins built around one idea: AI tooling should be measurable

↗ GitHub ★ 0 MIT updated today 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
~257 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/talhayme/claude-plugins

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 talhayme/claude-plugins/plugins/context-audit/skills/context-audit .claude/skills/context-audit
$ npx degit talhayme/claude-plugins/plugins/eval-drift/skills/eval-drift .claude/skills/eval-drift
$ npx degit talhayme/claude-plugins/plugins/injection-probe/skills/injection-probe .claude/skills/injection-probe

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)

context-auditeval-driftinjection-probe

Similar rigs

weellio/gander
Live NOC dashboard + control center for AI coding agents: pixel-art office floor, phone/Telegram/Slack alerts, cost guardrails, task queue with worktrees + test gate. Designed for Claude Code — other agent CLIs (Codex, Gemini, Grok, aider)
★ 7 project Claude Code 4 skills 2 agents 16d ago
Pragmatist 2.2k tok ·
Neeeophytee/finding-unknowns-skills
14 installable skills for Claude Code, OpenAI Codex, and Hermes: find unknowns, clarify requirements, manage context, test assumptions, and verify bug fixes with regression evidence.
★ 339 collection Claude CodeCodex 14 skills 12d ago
Skill Collector 2.5k tok ·
LeeKrane/claude-dotfiles
—
★ 0 setup Claude Code 18 skills 2 hooks 1d ago
Skill Collector 1.8k tok ·
undefined-ui/second-brain-os
An AI second brain that maintains itself. Full guide, starter vault, agent skills and scripts for a self-organizing knowledge base in Claude Code and Obsidian.
★ 811 project Claude Code 23 skills 10d ago
Skill Collector 1.2k tok ·
copied ✓