ktym4a/claude-code-config
ktym4a's claude code user config
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
$ git clone --depth 1 https://github.com/ktym4a/claude-code-config 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.
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"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(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Plugins (13)
explanatory-output-style@claude-plugins-officialplaywright@claude-plugins-officialcontext7@claude-plugins-officialtypescript-lsp@claude-plugins-officialexample-skills@anthropic-agent-skillsralph-loop@claude-plugins-officialcode-simplifier@claude-plugins-officialfrontend-design@claude-plugins-officialfeature-dev@claude-plugins-officialcode-review@claude-plugins-officialsecurity-guidance@claude-plugins-officialpr-review-toolkit@claude-plugins-officiallearning-output-style@claude-plugins-official
Permissions
deny (0)
—
ask (0)
—
allow (120)
Bash(grep:*)
Bash(find:*)
Bash(find:*)
Bash(rg:*)
mcp__taskmaster-ai__update_task
mcp__taskmaster-ai__get_tasks
mcp__taskmaster-ai__add_task
Bash(pnpm run test:e2e:*)
Bash(pnpm run test:unit:*)
mcp__playwright__browser_snapshot
mcp__Context7__resolve-library-id
mcp__Context7__get-library-docs
mcp__playwright__browser_type
mcp__playwright__browser_click
mcp__playwright__browser_wait_for
mcp__playwright__browser_take_screenshot
mcp__playwright__browser_navigate
mcp__playwright__browser_navigate_forward
mcp__playwright__browser_press_key
Bash(npx stylelint:*)
Bash(git rev-parse:*)
Bash(docker compose exec:*)
Bash(ls:*)
Bash(gh pr diff:*)
Bash(pnpm run typecheck:*)
mcp__playwright__browser_evaluate
Bash(pnpm run lint)
Bash(rm:*)
Bash(mv:*)
Bash(pnpm run format:*)
mcp__playwright__browser_install
Bash(mkdir:*)
mcp__devinwiki__read_wiki_structure
mcp__devinwiki__ask_question
mcp__notionApi__API-get-block-children
Bash(gh pr view:*)
mcp__notionApi__API-retrieve-a-page
Bash(for file in docs/skeleton-usage.md docs/constants-patterns.md)
Bash(do [ -f "$file" ])
Bash(echo "✓ $file exists")
Bash(echo:*)
Bash(done)
Bash(while read f)
Bash(do echo "=== $f ===")
Bash(head:*)
Bash(tree:*)
Bash(cut:*)
Bash(while read -r link)
Bash([ -f "$file" ])
WebSearch
mcp__chrome-devtools__list_network_requests
mcp__chrome-devtools__navigate_page
mcp__chrome-devtools__list_pages
mcp__chrome-devtools__take_snapshot
mcp__chrome-devtools__fill_form
mcp__chrome-devtools__click
mcp__chrome-devtools__get_network_request
mcp__chrome-devtools__wait_for
mcp__chrome-devtools__take_screenshot
mcp__chrome-devtools__evaluate_script
Similar rigs
anomalyco/opencode
The open source coding agent.
Pragmatist 4.2k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Pragmatist 1.6k tok ·
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
Pragmatist 4.2k tok ·
garrytan/gstack
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Pragmatist 8.8k tok ·