Summary
A compatibility shim that routes coding requests through OpenClaw's plan-first workflow. If you ask it to plan or scope work, it hands off to the plan-issue skill. For implementation requests, it forces you to produce and explicitly approve a plan before any file writes happen. The routing extends to channel aliases like /plan and /plan-review, and it enforces hard gates around the APPROVE contract. Honest take: this is scaffolding for a larger system that wants to prevent you from shipping code without thinking first. If you're used to just asking an LLM to write code immediately, the approval friction will feel heavy.
Install to Claude Code
npx -y skills add kesslerio/coding-agent-openclaw-skill --skill coding-router --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
