cleanexpo/pi-dev-ops/claude-runtime

Claude Code and agent skill by cleanexpo/pi-dev-ops

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Rules for invoking Claude correctly — subprocess vs SDK mode, stream-json parsing, MCP SDK imports, Railway vs local environment differences. Use when writing or reviewing code that invokes Claude via a `claude -p` subprocess with stream-json output, the `claude_agent_sdk`, or an MCP server, especially when deciding between local and Railway cloud deployment (`TAO_USE_AGENT_SDK`, `ANTHROPIC_API_KEY`) or fixing `@modelcontextprotocol/sdk` imports such as `McpServer` not being exported from the t…

Install

npx vskill@latest install cleanexpo/pi-dev-ops/claude-runtime

SKILL.md

The same SKILL.md was published earlier as cleanexpo/pi-dev-ops/claude-runtime.

Claude Runtime Best Practices

Apply when writing code that invokes Claude (subprocess, SDK, or MCP).

Rules

  • TAO engine (`src/tao/`) is stub scaffolding. It is not used by the web server. All intelligence is delegated to claude -p subprocess via stream-json output. Parse events: system, assistant (text + tool_use), tool_result, result.
  • `claude -p` subprocess requires Claude Code CLI in PATH. In cloud (Railway), the CLI is NOT available — cloud deployments must use ANTHROPIC_API_KEY + claude_agent_sdk. Check TAO_USE_AGENT_SDK env var to switch paths.
  • MCP SDK subpath imports are required. Use @modelcontextprotocol/sdk/server/mcp.js and @modelcontextprotocol/sdk/server/stdio.js. The top-level @modelcontextprotocol/sdk import does NOT export McpServer directly.
  • `claude_agent_sdk` is the chosen Python SDK path. Managed Agents API (client.beta.agents) was rejected — 0 successful PoC cycles, schema blocker on config.setup_commands. See .harness/agents/sdk-migration-plan.md.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
2
7-day trend score
5

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/cleanexpo/pi-dev-ops/claude-runtime/badge)](https://verified-skill.com/skills/cleanexpo/pi-dev-ops/claude-runtime)

Something wrong with this skill or its page? Tell us.