LangChain Middleware & HITL
100 / 100 · Low risk
Fine to try.
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'langchain-middleware-hitl' ] || [ -L ~/.agents/skills/'langchain-middleware-hitl' ]; then echo 'A skill folder named langchain-middleware-hitl already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/jackjin1997/ClawForge' "$d" && git -C "$d" checkout --quiet '896286f3d171429c9e8553fae87ddae90c8265c8' -- 'skills/langchain-middleware' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/langchain-middleware' ~/.agents/skills/'langchain-middleware-hitl' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'langchain-middleware-hitl' ~/.claude/skills/'langchain-middleware-hitl' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/jackjin1997/ClawForge/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-08 | 896286f | 100 |
| 2026-11-06 | 896286f | 100 |