~ / rigs / lethanhduong / claude-dotfiles

lethanhduong/claude-dotfiles

No description.

↗ GitHub ★ 0 no license updated 3mo ago personal setup Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~1.7k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit lethanhduong/claude-dotfiles/claude/.claude ./rig-claude-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 lethanhduong/claude-dotfiles/claude/.claude/skills/bq-explorer .claude/skills/bq-explorer
$ npx degit lethanhduong/claude-dotfiles/claude/.claude/skills/commit-msg .claude/skills/commit-msg
$ npx degit lethanhduong/claude-dotfiles/claude/.claude/skills/erp-explorer .claude/skills/erp-explorer
$ npx degit lethanhduong/claude-dotfiles/claude/.claude/skills/explain .claude/skills/explain
$ npx degit lethanhduong/claude-dotfiles/claude/.claude/skills/gcp-explorer .claude/skills/gcp-explorer
$ npx degit lethanhduong/claude-dotfiles/claude/.claude/skills/infra-scout .claude/skills/infra-scout
$ npx degit lethanhduong/claude-dotfiles/claude/.claude/skills/notion-explorer .claude/skills/notion-explorer
$ npx degit lethanhduong/claude-dotfiles/claude/.claude/skills/teach .claude/skills/teach
$ npx degit lethanhduong/claude-dotfiles/claude/.claude/skills/ticket-kickoff .claude/skills/ticket-kickoff
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/lethanhduong/claude-dotfiles/main/claude/.claude/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/explorer.md https://raw.githubusercontent.com/lethanhduong/claude-dotfiles/main/claude/.claude/agents/explorer.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/lethanhduong/claude-dotfiles/main/claude/.claude/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/lethanhduong/claude-dotfiles/main/claude/.claude/agents/researcher.md
$ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/lethanhduong/claude-dotfiles/main/claude/.claude/agents/security-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/sys-explorer.md https://raw.githubusercontent.com/lethanhduong/claude-dotfiles/main/claude/.claude/agents/sys-explorer.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 (9)

Subagents (6)

code-reviewer
model: opus
Code review agent. Use after implementing a feature or fix to check for bugs, logic errors, security issues, and adherence to project conventions. Reports only high-confidence findings.
explorer
model: sonnet
Fast, read-only codebase exploration. Use for broad searches, finding files by pattern, understanding structure, or answering "where is X" questions before planning. Protects main context window from
planner
model: opus
Implementation planning agent. Use before starting any non-trivial task to produce a step-by-step plan with file paths, verify criteria, and trade-off analysis. Runs in plan mode — cannot make changes
researcher
model: sonnet
Web research agent. Use when you need current documentation, library APIs, error message lookups, or technology comparisons from the web. Returns concise, actionable findings — not raw search results.
security-reviewer
model: sonnet
Deep security audit agent. Use for authentication flows, data handling, API surface, infrastructure configs, or any code touching secrets/credentials/PII. More thorough than code-reviewer.
sys-explorer
model: sonnet
Generic read-only explorer for external systems and data sources. Delegates to the matching skill for the target system — gcp-explorer (GCP identity/IAM/APIs), bq-explorer (BigQuery), erp-explorer (Pr

Similar rigs

copied ✓