taiyyoson/my-claude-code
Version-controlled Claude Code setup with three working modes
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ npx degit taiyyoson/my-claude-code/agents ./rig-my-claude-code/agents $ npx degit taiyyoson/my-claude-code/commands ./rig-my-claude-code/commands $ npx degit taiyyoson/my-claude-code/skills ./rig-my-claude-code/skills $ npx degit taiyyoson/my-claude-code/hooks ./rig-my-claude-code/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 taiyyoson/my-claude-code/skills/roblox-init .claude/skills/roblox-init $ npx degit taiyyoson/my-claude-code/skills/systematic-debugging .claude/skills/systematic-debugging $ npx degit taiyyoson/my-claude-code/skills/test-driven-development .claude/skills/test-driven-development $ npx degit taiyyoson/my-claude-code/skills/verification-before-completion .claude/skills/verification-before-completion
$ curl -fsSL --create-dirs -o .claude/agents/code-review-debugger.md https://raw.githubusercontent.com/taiyyoson/my-claude-code/main/agents/code-review-debugger.md $ curl -fsSL --create-dirs -o .claude/agents/scribe.md https://raw.githubusercontent.com/taiyyoson/my-claude-code/main/agents/scribe.md $ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/taiyyoson/my-claude-code/main/agents/verifier.md
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 (4)
Subagents (3)
| code-review-debugger model: opus | Use this agent when you need expert code review, debugging assistance, or architectural analysis across the full stack. This includes reviewing recently written code for design flaws, debugging errors |
| scribe model: sonnet | Writes up work — worklog entries, session reports, README and doc updates, PR descriptions. Use when a chunk of work is finished and needs recording for a reader who wasn't there, or when documentatio |
| verifier model: sonnet | Runs builds, tests, linters, and type checks and reports exactly what happened. Cannot edit files, so it cannot turn a failure into a pass. Use it whenever you need a result you'd otherwise be tempted |
Slash commands (5)
/autopilot/bootstrap/build/coach/mode
Similar rigs
nicolasaudran/claude-dotfiles
—
Pragmatist 320 tok ·
raiki61/claude-plugins
Two Claude Code loops that keep reviewing and researching until they reach a fixed point: the implementer and the grader are held in separate contexts, and the machine may only ever declare failure, never convergence. Japanese only for now.
Orchestrator 1.2k tok ·
RichardBray/dotfiles
My personal configuration files and settings
Skill Collector 671 tok ·
ingeun92/claude-code-configs
—
Pragmatist 468 tok ·