svyatov/agent-toolkit
Personal agent toolkit — reusable skills and plugins for Claude Code, Cursor, Codex, and Gemini CLI
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit svyatov/agent-toolkit/.claude ./rig-agent-toolkit # inspect, then merge into .claude/ 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 svyatov/agent-toolkit/plugins/adopt-release/skills/adopt-release .claude/skills/adopt-release $ npx degit svyatov/agent-toolkit/plugins/astro/skills/astro .claude/skills/astro $ npx degit svyatov/agent-toolkit/plugins/atomic-commits/skills/atomic-commits .claude/skills/atomic-commits $ npx degit svyatov/agent-toolkit/plugins/browser-compat/skills/browser-compat .claude/skills/browser-compat $ npx degit svyatov/agent-toolkit/plugins/browser-qa/skills/browser-qa .claude/skills/browser-qa $ npx degit svyatov/agent-toolkit/plugins/cut-release/skills/cut-release .claude/skills/cut-release $ npx degit svyatov/agent-toolkit/plugins/debrief-skill/skills/debrief-skill .claude/skills/debrief-skill $ npx degit svyatov/agent-toolkit/plugins/dependabot-review/skills/dependabot-review .claude/skills/dependabot-review $ npx degit svyatov/agent-toolkit/plugins/generate-dockerfile/skills/generate-dockerfile .claude/skills/generate-dockerfile $ npx degit svyatov/agent-toolkit/plugins/generate-favicon/skills/generate-favicon .claude/skills/generate-favicon $ npx degit svyatov/agent-toolkit/plugins/grill-me/skills/grill-me .claude/skills/grill-me $ npx degit svyatov/agent-toolkit/plugins/humanizer/skills/humanizer .claude/skills/humanizer $ npx degit svyatov/agent-toolkit/plugins/import-skill/skills/import-skill .claude/skills/import-skill $ npx degit svyatov/agent-toolkit/plugins/lefthook/skills/lefthook .claude/skills/lefthook $ npx degit svyatov/agent-toolkit/plugins/llms-visibility/skills/llms-visibility .claude/skills/llms-visibility $ npx degit svyatov/agent-toolkit/plugins/prior-art/skills/prior-art .claude/skills/prior-art $ npx degit svyatov/agent-toolkit/plugins/report-upstream/skills/report-upstream .claude/skills/report-upstream $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/c .claude/skills/c $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/cb .claude/skills/cb $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/cbp .claude/skills/cbp $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/ci .claude/skills/ci $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/cl .claude/skills/cl $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/cp .claude/skills/cp $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/cpr .claude/skills/cpr $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/cprw .claude/skills/cprw $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/deps .claude/skills/deps $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/fa .claude/skills/fa $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/fci .claude/skills/fci $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/lint .claude/skills/lint $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/m .claude/skills/m $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/p .claude/skills/p $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/prd .claude/skills/prd $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/rule .claude/skills/rule $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/wm .claude/skills/wm $ npx degit svyatov/agent-toolkit/plugins/shortcuts/skills/ww .claude/skills/ww $ npx degit svyatov/agent-toolkit/plugins/verify-marketplace/skills/verify-marketplace .claude/skills/verify-marketplace $ npx degit svyatov/agent-toolkit/plugins/verify-skill/skills/verify-skill .claude/skills/verify-skill
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 (37)
adopt-releaseastroatomic-commitsbrowser-compatbrowser-qacut-releasedebrief-skilldependabot-reviewgenerate-dockerfilegenerate-favicongrill-mehumanizerimport-skilllefthookllms-visibilityprior-artreport-upstreamccbcbpciclcpcprcprwdepsfafcilintmpprdrulewmwwverify-marketplaceverify-skill
Plugins (1)
import-skill@svyatov-agent-toolkit
Similar rigs
bpenwell/claude-config
Portable Claude Code setup: settings, hooks, skills, and templated MCP servers with a one-command installer
Pragmatist 290 tok ·
weimeng23/claude-code-dotfiles
Personal Claude Code dotfiles for global instructions, settings, hooks, agents, and reusable setup scripts.
Pragmatist 984 tok ·
MPV/dotfiles
MPV's dotfiles
Pragmatist 290 tok ·
Reiquileut/agent-harness
Dotfiles for AI agents + bootstrapper: one command to configure MCPs, skills, and plugins across Claude Code, Codex, and OpenCode. npx github:reiquileut/agent-harness
Skill Collector 589 tok ·