~ / rigs / VishalJ99 / claude-docker

VishalJ99/claude-docker

Docker container for running Claude Code with full permissions and Twilio notifications

↗ GitHub ★ 206 MIT updated 8mo ago project Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~1.8k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit VishalJ99/claude-docker/.claude ./rig-claude-docker  # 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.

$ curl -fsSL --create-dirs -o .claude/agents/code-implementer.md https://raw.githubusercontent.com/VishalJ99/claude-docker/master/.claude/agents/code-implementer.md
$ curl -fsSL --create-dirs -o .claude/agents/code-navigator.md https://raw.githubusercontent.com/VishalJ99/claude-docker/master/.claude/agents/code-navigator.md
$ curl -fsSL --create-dirs -o .claude/agents/issue-stack-tracer.md https://raw.githubusercontent.com/VishalJ99/claude-docker/master/.claude/agents/issue-stack-tracer.md
$ curl -fsSL --create-dirs -o .claude/agents/system-architect.md https://raw.githubusercontent.com/VishalJ99/claude-docker/master/.claude/agents/system-architect.md
$ curl -fsSL --create-dirs -o .claude/agents/ux-ui-designer.md https://raw.githubusercontent.com/VishalJ99/claude-docker/master/.claude/agents/ux-ui-designer.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 *)"
    ]
  }
}

Subagents (5)

code-implementer
model: inherit
Use this agent when you need to implement specific features, fix bugs, or make targeted changes to an existing codebase. This agent excels at understanding architectural plans and translating them int
code-navigator
model: sonnet
Use this agent when you need to explore and understand an unfamiliar codebase, locate specific functionality, or map out the structure of a repository. This includes finding particular modules, unders
issue-stack-tracer
model: opus
Use this agent when you need to diagnose user-reported issues by mapping out the complete technical execution path. This agent excels at transforming vague problem descriptions like 'button doesn't wo
system-architect
model: opus
Use this agent when you need to design the technical architecture for new features, refactor existing systems, or establish the modular structure of a codebase. This agent excels at breaking down comp
ux-ui-designer
model: opus
Use this agent when you need to design user interfaces, create mockups, plan user experiences, or transform functional requirements into intuitive design specifications. This includes tasks like desig

Slash commands (4)

/claude-vocab-section/define-terms/project_init/reload

Permissions

deny (0)
—
ask (0)
—
allow (6)
Read(~/.zshrc)
Bash(ls:*)
Bash(find:*)
Bash(grep:*)
Bash(awk:*)
Bash(sed:*)

Similar rigs

copied ✓