MohanTn/mohan-dotfiles
Personal dotfiles and configuration for Claude Code, tmux, and Neovim
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit MohanTn/mohan-dotfiles/.claude ./rig-mohan-dotfiles # 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 MohanTn/mohan-dotfiles/agents/skills/ai-memory-init .claude/skills/ai-memory-init $ npx degit MohanTn/mohan-dotfiles/agents/skills/chrome-devtools-axi .claude/skills/chrome-devtools-axi $ npx degit MohanTn/mohan-dotfiles/agents/skills/feature-plan .claude/skills/feature-plan $ npx degit MohanTn/mohan-dotfiles/agents/skills/frontend-design .claude/skills/frontend-design $ npx degit MohanTn/mohan-dotfiles/agents/skills/repo-map-check .claude/skills/repo-map-check $ npx degit MohanTn/mohan-dotfiles/agents/skills/resolve-ai-notes .claude/skills/resolve-ai-notes $ npx degit MohanTn/mohan-dotfiles/agents/skills/sketch-design .claude/skills/sketch-design
$ curl -fsSL --create-dirs -o .claude/agents/lean-system-prompt.md https://raw.githubusercontent.com/MohanTn/mohan-dotfiles/main/agents/lean-system-prompt.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/MohanTn/mohan-dotfiles/main/agents/skills/ai-memory-init/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/MohanTn/mohan-dotfiles/main/agents/skills/chrome-devtools-axi/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/MohanTn/mohan-dotfiles/main/agents/skills/feature-plan/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/MohanTn/mohan-dotfiles/main/agents/skills/frontend-design/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/MohanTn/mohan-dotfiles/main/agents/skills/repo-map-check/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/MohanTn/mohan-dotfiles/main/agents/skills/resolve-ai-notes/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/MohanTn/mohan-dotfiles/main/agents/skills/sketch-design/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/dotnet.md https://raw.githubusercontent.com/MohanTn/mohan-dotfiles/main/agents/style/dotnet.md $ curl -fsSL --create-dirs -o .claude/agents/react.md https://raw.githubusercontent.com/MohanTn/mohan-dotfiles/main/agents/style/react.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 (7)
ai-memory-initchrome-devtools-axifeature-planfrontend-designrepo-map-checkresolve-ai-notessketch-design
Subagents (10)
| lean-system-prompt | — |
| ai-memory-init | Bootstrap .ai-memory/ (manifest.json + ONE Mermaid diagram, seeded from the actual codebase) for the current repo, so inject-memory.sh has real content to inject from the first prompt instead of an em |
| chrome-devtools-axi | Control a Chrome browser session through the chrome-devtools-axi CLI - navigate, snapshot, click, fill forms, run JavaScript, inspect console and network, take screenshots, audit performance. Use when |
| feature-plan | Take a feature the user has in mind and turn it into a co-authored, code-level feature implementation plan (featurePlan-<slug>.html) — file-by-file change manifest in build order, pseudo-code, edge ca |
| frontend-design | Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defau |
| repo-map-check | Check .claude/repo-map.md for cached file inventory before running filesystem queries. |
| resolve-ai-notes | Resolve every "@AI" instruction left on a sketch-learn canvas page. A human leaves a note like "@AI tighten this section" as ordinary text anywhere on the page; this skill finds each one via the sketc |
| sketch-design | Co-author a system-design sketch on an .excalidraw canvas through the sketch-learn MCP server — drop in a pre-built template or build a custom board, draft what the repo can ground, let the human fill |
| dotnet | — |
| react | — |
Permissions
deny (0)
—
ask (0)
—
allow (4)
Bash(rg *)
Bash(oh-my-posh init *)
Bash(bash claude/hooks/check-conflicts.sh)
Bash(bash claude/hooks/check-conflicts.sh *)
Similar rigs
hta218/dotfiles
My personal macOS development environment — shell config, Git aliases, editor settings, and the tools I install on every new machine.
Skill Collector 491 tok ·
Akshat2634/Codelens-AI
Local-first ROI analytics for Claude Code, OpenAI Codex, and GitHub Copilot
Pragmatist 4.3k tok ·
hendriknielaender/.dotfiles
🧑💻 aerospace + ghostty + neovim
Minimalist 402 tok ·
topruss05-lgtm/claude
Personal Claude Code config: skills, system prompts, MCP, commands
Minimalist 650 tok ·