agentrigs
+ submit rig
~ / rigs / roykollensvendsen / claude-voice

roykollensvendsen/claude-voice

MCP bridge for driving local Claude Code sessions by voice

↗ GitHub ★ 1 gpl-3.0 updated 1d ago project Claude CodeCodex
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~598 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 roykollensvendsen/claude-voice/.claude ./rig-claude-voice  # 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 roykollensvendsen/claude-voice/.claude/skills/write-commit .claude/skills/write-commit

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 (1)

write-commit

Hooks (1)

eventmatcherruns
Stop*python3 "$CLAUDE_PROJECT_DIR"/scripts/hooks/unanswered_peer.py

Similar rigs

matheusPavaneli/workbench
Claude Code plugin: ticket-to-PR workflow for AI coding agents. Plans cite file:line and a script verifies every citation; hooks block edits outside the plan. Jira, Azure DevOps, GitHub Issues, or no tracker. Zero dependencies.
★ 1 project Claude Code 10 skills 11d ago
Skill Collector 579 tok ·
ZAidBinAsif/flutter-ai-starter
Flutter starter template for AI agents — runnable app, Cursor rules/skills, CI-enforced agent contract, provider MVVM.
★ 0 project Claude CodeCodexCursor 15 skills 2mo ago
Skill Collector 1.2k tok ·
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
★ 217k collection Claude CodeCursor 1 skills 6mo ago
Minimalist 723 tok ·
shareAI-lab/learn-claude-code
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
★ 78.0k project Claude Code 4 skills 11d ago
Minimalist 156 tok ·
copied ✓