Envoy Setup — Productivity skill for Claude Code
Check whether the local Codex CLI is ready (plus grok/kimi vendor availability) and optionally toggle the stop-time review gate; a successful run is recorded per workspace and unlocks task/review/tran.
How to install Envoy Setup
Installs to ~/.claude/skills/transmutelabs-catalyst-envoy-setup/SKILL.md
mkdir -p ~/.claude/skills/transmutelabs-catalyst-envoy-setup && curl -fsSL https://raw.githubusercontent.com/TransmuteLabs/Catalyst/HEAD/commands/envoy-setup.md -o ~/.claude/skills/transmutelabs-catalyst-envoy-setup/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Envoy Setup does
description: Check whether the local Codex CLI is ready (plus grok/kimi vendor availability) and optionally toggle the stop-time review gate; a successful run is recorded per workspace and unlocks task/review/transfer argument-hint: '[--enable-review-gate|--disable-review-gate]' allowed-tools: Bash(node:*), Bash(npm:*), AskUserQuestion
Run:
node "${CLAUDE_PLUGIN_ROOT}/skills/envoy/scripts/envoy-companion.mjs" setup --json $ARGUMENTS
If the result says Codex is unavailable
Alternatives in Productivity
- Configure Claude HUD — FIRST: Use the Read tool to load ~/.claude/plugins/claude-hud/config.json if it exists 10.9k ★
- GrokSearch — Integrate Grok's powerful real-time search capabilities into Claude via the MCP protocol 1.8k ★
- Spectre — Spectre is a battle-tested 6 stage agentic engineering workflow for building complex, production-ready feature 156 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Claude Code Fleet Orchestrator
Tmux-fleet orchestration: supervisor↔worker dispatch, plan/task tracking, recurring schedules, universal Stop+
Claw Hooks
Simple TOML hooks for Claude Code, Cursor, Windsurf, Antigravity CLI, Codex CLI, Grok CLI - Command blocking,
Auto Dev
Développe une feature en mode RALPH autonome via le workflow v6 (mandat requis, zéro stop, gate PASS obligatoi
Gov Metrics
Governance metrics — measure whether the gates actually work. Block rate, override/waiver rate, false-block pr
Plan Check
You are now a task list completeness checker. Run hard-gate checks against the input tasks.json and output whe
PRD Check
You are now a PRD completeness checker. Run hard-gate checks against the input PRD file and output whether it
Related Agents
Envoy Runner
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper roo
Light Bug MadShi
Use this agent to diagnose and fix a Delphi crash report (.mad file) end-to-end up to and INCLUDING a successf
External LLM
When a request mentions external LLM model names (Kimi, K2, Grok, GLM, Gemini, GPT-5)