John Freier gofullthrottle

Workaround: `${CLAUDE_PLUGIN_ROOT}` not expanding in Claude Code plugin hooks

Claude Code plugin hooks defined in hooks.json that reference ${CLAUDE_PLUGIN_ROOT} silently fail because the variable is not expanded by the harness and not set in the shell environment when the hook command is invoked. Tracking issue: anthropics/claude-code#42564.

Verified affected plugins as of 2026-04-28:

openai-codex/codex@1.0.2 — SessionStart, SessionEnd, Stop hooks all broken
claude-code-plugins/ralph-wiggum — plugin author shipped hardcoded paths to work around it
claude-plugins-official/ralph-loop — same

Goal recap

You want to build a Next.js dashboard, using multiple Codex CLI agents run via codex exec in parallel, with clear roles, minimal overlap, and a concrete workflow from spec → implementation → tests.

Assumptions & constraints

New or existing Next.js app, App Router + TypeScript, lives at <PROJECT_ROOT> (you can adjust).
Node/npm/yarn/pnpm already installed; npx create-next-app@latest is available if you start from scratch.
Codex CLI is installed and authenticated; codex exec "" runs headless tasks in your shell. (developers.openai.com (https://developers.openai.com/codex/noninteractive/?

You are my GPT‑5.1 Prompt Expander.

Goal: take a short, messy, or underspecified user prompt and turn it into a robust, production‑grade instruction set for GPT‑5.1 (or a comparable model) that is:

Explicit about objectives, constraints, and audience.
Decomposed into clear steps.
Defensive against ambiguity and failure modes.

Behavior:

Conventional Commit Messages

See how a minor change to your commit message style can make a difference.

Tip

Take a look at git-conventional-commits , a CLI util to ensure these conventions, determine version and generate changelogs

Commit Message Formats

Default

I will create a fully implemented ethical cybersecurity analysis and penetration testing framework, including files, folders, and installation instructions. This will cover:

Legal and ethical penetration testing guidelines
Best practices for securing applications, including Discord bots
Installation scripts and configurations for security tools
Step-by-step setup for an ethical hacking lab
Guidelines for responsible disclosure and compliance with cybersecurity laws

I'll provide the necessary files and folder structures for easy deployment. I'll update you once it's ready.

	FROM ./mmproj-F16.gguf
	FROM ./Devstral-Small-2505-UD-Q8_K_XL.gguf

	TEMPLATE """{{- range $index, $_ := .Messages }}
	{{- if eq .Role "system" }}[SYSTEM_PROMPT]{{ .Content }}[/SYSTEM_PROMPT]
	{{- else if eq .Role "user" }}
	{{- if and (le (len (slice $.Messages $index)) 2) $.Tools }}[AVAILABLE_TOOLS]{{ $.Tools }}[/AVAILABLE_TOOLS]
	{{- end }}[INST]{{ .Content }}[/INST]
	{{- else if eq .Role "assistant" }}
	{{- if .Content }}{{ .Content }}

	#!/bin/bash
	#
	# check_2tb_support.sh
	# ASCII-formatted CLI diagnostic for >2TB disk support
	# Run from Ubuntu Live USB — NO emoji, no color codes, remote-shell and log-safe

	set -e

	echo
	echo "=================================================="

	#!/data/data/com.termux/files/usr/bin/bash
	# Cloud Mobile C8 Full Setup Script

	# Variables
	FDROID_URL="https://f-droid.org/F-Droid.apk"
	UUID="$(ls /storage/ \| grep -v 'emulated\\|self')" # Attempt to auto-detect SD UUID

	# Helper Functions
	function pause() {
	read -p "Press [Enter] key to continue after completing manual steps..."

	For generating stories and tasks from a video, use the following instructions:
	<INSTRUCTIONS>
	Act as a world-class technical product manager. Your goal is to review customer feedback and break it down into clear stories
	and discrete tasks for a development team to work on. Group your feedback items as sprint tasks, organized in high-level topics
	and 1-point very detailed stories. Your response to any video should contain enough detail for an offshore development team
	to implement the fix without having access to this video. Your response should be in the format of a markdown file with
	numbered stories and empty checkboxes next to each story and task.
	</INSTRUCTIONS>

	For refining the stories in the cursor-tasks file, use the following instructions:

	You are Manus, an AI agent created by the Manus team.

	You excel at the following tasks:
	1. Information gathering, fact-checking, and documentation
	2. Data processing, analysis, and visualization
	3. Writing multi-chapter articles and in-depth research reports
	4. Creating websites, applications, and tools
	5. Using programming to solve various problems beyond development
	6. Various tasks that can be accomplished using computers and the internet