agentrigs
+ submit rig
~ / rigs / kellmat74 / ai-toolkit

kellmat74/ai-toolkit

Portable personal AI agent toolchain (Claude Code + Hermes): skills, agents, MCP configs, prompts, backlog

↗ GitHub ★ 0 no license updated 1mo ago project Claude Code
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~3.8k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/kellmat74/ai-toolkit

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 kellmat74/ai-toolkit/claude/skills/backlog-protocol .claude/skills/backlog-protocol
$ npx degit kellmat74/ai-toolkit/claude/skills/deploy .claude/skills/deploy
$ npx degit kellmat74/ai-toolkit/claude/skills/driving-hermes .claude/skills/driving-hermes
$ npx degit kellmat74/ai-toolkit/claude/skills/generate-image .claude/skills/generate-image
$ npx degit kellmat74/ai-toolkit/claude/skills/handoff .claude/skills/handoff
$ npx degit kellmat74/ai-toolkit/claude/skills/migrate-db .claude/skills/migrate-db
$ npx degit kellmat74/ai-toolkit/claude/skills/new-app .claude/skills/new-app
$ npx degit kellmat74/ai-toolkit/claude/skills/perf-optimize .claude/skills/perf-optimize
$ npx degit kellmat74/ai-toolkit/claude/skills/plan-sprint .claude/skills/plan-sprint
$ npx degit kellmat74/ai-toolkit/claude/skills/refactor .claude/skills/refactor
$ npx degit kellmat74/ai-toolkit/claude/skills/review-code .claude/skills/review-code
$ npx degit kellmat74/ai-toolkit/claude/skills/security-audit .claude/skills/security-audit
$ npx degit kellmat74/ai-toolkit/claude/skills/tdd .claude/skills/tdd
$ npx degit kellmat74/ai-toolkit/hermes/skills/apple .claude/skills/apple
$ npx degit kellmat74/ai-toolkit/hermes/skills/ascii .claude/skills/ascii
$ npx degit kellmat74/ai-toolkit/hermes/skills/autonomous-ai-agents .claude/skills/autonomous-ai-agents
$ npx degit kellmat74/ai-toolkit/hermes/skills/baoyu .claude/skills/baoyu
$ npx degit kellmat74/ai-toolkit/hermes/skills/creative .claude/skills/creative
$ npx degit kellmat74/ai-toolkit/hermes/skills/data-science .claude/skills/data-science
$ npx degit kellmat74/ai-toolkit/hermes/skills/devops .claude/skills/devops
$ npx degit kellmat74/ai-toolkit/hermes/skills/email .claude/skills/email
$ npx degit kellmat74/ai-toolkit/hermes/skills/gaming .claude/skills/gaming
$ npx degit kellmat74/ai-toolkit/hermes/skills/github .claude/skills/github
$ npx degit kellmat74/ai-toolkit/hermes/skills/mcp .claude/skills/mcp
$ npx degit kellmat74/ai-toolkit/hermes/skills/media .claude/skills/media
$ npx degit kellmat74/ai-toolkit/hermes/skills/mlops .claude/skills/mlops
$ npx degit kellmat74/ai-toolkit/hermes/skills/note-taking .claude/skills/note-taking
$ npx degit kellmat74/ai-toolkit/hermes/skills/productivity .claude/skills/productivity
$ npx degit kellmat74/ai-toolkit/hermes/skills/red-teaming .claude/skills/red-teaming
$ npx degit kellmat74/ai-toolkit/hermes/skills/research .claude/skills/research
$ npx degit kellmat74/ai-toolkit/hermes/skills/smart-home .claude/skills/smart-home
$ npx degit kellmat74/ai-toolkit/hermes/skills/social-media .claude/skills/social-media
$ npx degit kellmat74/ai-toolkit/hermes/skills/software-development .claude/skills/software-development

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 (33)

backlog-protocoldeploydriving-hermesgenerate-imagehandoffmigrate-dbnew-appperf-optimizeplan-sprintrefactorreview-codesecurity-audittddappleasciiautonomous-ai-agentsbaoyucreativedata-sciencedevopsemailgaminggithubmcpmediamlopsnote-takingproductivityred-teamingresearchsmart-homesocial-mediasoftware-development

Similar rigs

AI-BrandFactory/claude-code-starter-pack
Working templates for Claude Code primitives: slash commands, skills, hooks, subagents, MCP configs, Agent SDK starters. Current to Opus 4.7, April 2026.
★ 1 project Claude Code 4 skills 3 agents 2 hooks 6mo ago
Fort Knox 584 tok ·
edlitmus/claude-dotfiles
—
★ 0 setup Claude Code 3 mcp 19 skills 27d ago
Skill Collector 24.7k tok ·
vini-haa/dotfiles
Dotfiles that give Claude Code persistent semantic memory across sessions and machines
★ 4 setup Claude Code 5 mcp 19 skills 6mo ago
Skill Collector 29.8k tok ·
yamanidev/claude-code-configuration
My personal Claude Code configuration.
★ 5 setup Claude Code 12 skills 4mo ago
Skill Collector 1.8k tok ·
copied ✓