openhands

Delegate coding tasks to the Blackbox AI multi-model CLI.

Delegate coding to xAI Grok Build CLI (features, PRs).

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

Reduces AIGC detection rates and AI-like tone in academic papers when using Claude Code and Codex. Based on detectors such as 知网, 万方, PaperPass, and PaperPure, it applies scanning, deterministic replacement, sentence-level restructuring, and Anti-AI auditing to cut templated AI traces while keeping academic register, facts, data, citations, and terminology consistent. Use when the user asks to lower AI tone, reduce AIGC rates, avoid AI detection, reduce false-positive AI similarity, make writing sound more human, or mentions 'remove AI tone', 'reduce similarity', or 'AIGC check'.