Redev — Productivity skill for Claude Code
dev workflow, context-light invocation — same task semantics as /dev, but assumes the /dev workflow instructions are already loaded.
How to install Redev
Installs to ~/.claude/skills/yugoge-claude-code-config-redev/SKILL.md
mkdir -p ~/.claude/skills/yugoge-claude-code-config-redev && curl -fsSL https://raw.githubusercontent.com/Yugoge/claude-code-config/HEAD/commands/redev.md -o ~/.claude/skills/yugoge-claude-code-config-redev/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Redev does
description: dev workflow, context-light invocation — same task semantics as /dev, but assumes the /dev workflow instructions are already loaded. Pass --codex to enable adversarial codex consultation on each subagent's draft; default is self-review only. argument-hint: "[--codex] [--spec ] " disable-model-invocation: true
Run the **/dev** workflow with the full command specification already loaded in this conversation.
- Use the same behavior as
/devfor the curren
Alternatives in Productivity
- Skill Context Detection — Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type 2.8k ★
- Carl — Context Augmentation & Reinforcement Layer — Domain-based behavioral rules for Claude Code, keyword-matched an 368 ★
- Meridian — Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after comp 143 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Harness Dispatch
Delegate coding tasks to the agent CLIs you already pay for — a local MCP server routing each task to the best
Auto Dev
Développe une feature en mode RALPH autonome via le workflow v6 (mandat requis, zéro stop, gate PASS obligatoi
Agent Profile
Shared agent instructions and installable workflow/practice skills for Claude Code and Codex CLI.
Adversarial Execution
Adversarial Execution — an execution-time review gate: two independent strong models must both prove your work
Herdr Agent Quota
Live Claude, Codex, Grok & Agy quota monitoring for Herdr — usage, reset times, task context, and time-aware q
Deiko
Point at it. Say it. Your agent remembers it. Voice and on-screen annotation for coding agents, plus a free bo
Related Agents
Claude Spec Review
First-pass adversarial spec review by Claude. Read-only and advisory. Runs before the Codex spec-reviewer loop
Codex Consultant
An independent code review and debugging subagent that uses Codex MCP as its sole execution engine, acting as
Skeptical Reviewer
Performs adversarial review of PR changes, actively looking for bugs, edge cases, race conditions, and failure