schen22/claude-config
My Claude Code setup: rules, skills, hooks and the research-round plugin I use to build products with AI
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details
Quality 15/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code $ npx degit schen22/claude-config/skills ./rig-claude-config/skills $ npx degit schen22/claude-config/hooks ./rig-claude-config/hooks
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 schen22/claude-config/marketplace/research-round/skills/research-round .claude/skills/research-round $ npx degit schen22/claude-config/skills/commit .claude/skills/commit $ npx degit schen22/claude-config/skills/delegate .claude/skills/delegate $ npx degit schen22/claude-config/skills/design-review .claude/skills/design-review $ npx degit schen22/claude-config/skills/end .claude/skills/end $ npx degit schen22/claude-config/skills/retro .claude/skills/retro $ npx degit schen22/claude-config/skills/review-gates .claude/skills/review-gates $ npx degit schen22/claude-config/skills/review .claude/skills/review $ npx degit schen22/claude-config/skills/start .claude/skills/start $ npx degit schen22/claude-config/skills/web-kit .claude/skills/web-kit $ npx degit schen22/claude-config/skills/working-model .claude/skills/working-model
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash|Read|Edit|Write|NotebookEdit",
"hooks": [
{
"type": "command",
"command": "CLAUDE_HOOK_MODE=enforce python3 -S ~/.claude/hooks/helper-guard.py"
}
]
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "CLAUDE_HOOK_MODE=enforce python3 -S ~/.claude/hooks/no-verify-guard.py"
}
]
}
]
}
} Skills (11)
Hooks (5)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash|Read|Edit|Write|NotebookEdit | CLAUDE_HOOK_MODE=enforce python3 -S ~/.claude/hooks/helper-guard.py |
| PreToolUse | Bash | CLAUDE_HOOK_MODE=enforce python3 -S ~/.claude/hooks/no-verify-guard.py |
| SubagentStop | * | python3 -S ~/.claude/hooks/usage-ledger.py |
| SessionStart | * | python3 -S ~/.claude/hooks/due.py --session-start |
| SessionEnd | * | python3 -S ~/.claude/hooks/session-log.py |
Plugins (1)
session-report@claude-plugins-official
Similar rigs
Kibertum/tausik-core
AI coding agents can't quietly fake "done". Signed ed25519 receipts prove the gates actually ran — bound to the commit, verifiable offline. Fail-closed hooks block the edit, not the PR. Harness engineering over Claude Code, Cursor, Codex, Q
Skill Collector 1.7k tok · · Q3
bkrishnamachari/claude-elements
Claude Code configuration: CLAUDE.md guidelines, skills, hooks, and settings
Minimalist 967 tok · · Q3
CanArslanDev/claude-code-setup
The complete guide to Claude Code — setup, configuration, memory system, skills, hooks, MCP servers, and a one-prompt auto-setup that configures everything for your project.
Minimalist 71 tok · · Q0
mustafarslan/monerex
An AI-driven development lifecycle for Claude Code: agents do the work in stages, hooks hold the rules, and you approve the plan, what is posted under your name, and the merge.
Skill Collector 735 tok · · Q0