Skip to content

Instantly share code, notes, and snippets.

View mpalpha's full-sized avatar

Jason Lusk mpalpha

22 followers · 14 following
View GitHub Profile
@mpalpha
mpalpha / global implementation_reminder.md
Created April 29, 2026 11:30
adds a global implementation steps reminder for the agent.

Add two rules to my global Claude Code instructions.

Open ~/.claude/CLAUDE.md (create it if it doesn't exist). Append the following two sections exactly as written. Do not modify existing content — only append. If either section heading already exists, skip that section rather than duplicating it.

After Every Implementation Task

After completing any code change, a

@mpalpha
mpalpha / claude-workflow-pattern-learning-setup.md
Created April 20, 2026 17:07
Claude Code setup prompt for reusable workflow pattern learning, safe CLAUDE.md merging, and intelligent promotion of patterns into skills and subagents without clutter.

You are setting up a lightweight reusable workflow system for Claude Code. Follow these steps exactly.

Goal

Implement a simple, maintainable system that:

  • Routes large non-domain tasks through general-purpose
  • Tracks reusable task patterns
  • Promotes stable patterns into skills or subagents
  • Avoids file clutter and duplication
@mpalpha
mpalpha / install-pre-compact-hook.md
Last active April 9, 2026 18:18
Install a Node.js CJS hook that Claude Code runs before compacting the conversation context. The hook writes a session checkpoint to the project's MEMORY.md so the next session can resume without re-investigation.

Install PreCompact Checkpoint Hook

Goal

Install a Node.js CJS hook that Claude Code runs before compacting the conversation context. The hook writes a session checkpoint to the project's MEMORY.md so the next session can resume without re-investigation.

Requirements

@mpalpha
mpalpha / peer-review-subagent-installer.md
Last active March 6, 2026 22:07
Discovers the project's rules/docs first, then generates the guide and subagent from what it finds.

You are a one-time standards review installer for Claude Code.

Your purpose in this session is to inspect this repository, discover its coding standards, conventions, rules, and documentation, then create:

  1. A Standards Review Guide (reference-based, not content-duplicating)
  2. A Peer Review subagent that uses that guide for PR reviews

You must assume:

  • A new project with no prior knowledge
  • No existing standards review guide or peer review agent unless discovered
@mpalpha
mpalpha / install-guides-to-subagents.prompt.md
Last active March 24, 2026 19:51
Bootstraps Claude Code by converting repository guides into minimal, well-structured project subagents with backups, audit logging, and strong automatic delegation.

You are a one-time installer and conversion agent for Claude Code.

Your purpose in this session is to inspect this repository, discover existing guide documents that describe reusable workflows, and convert the appropriate guides into properly installed Claude Code project subagents.

You must install them in a way that:

  • keeps always-loaded context minimal
  • preserves all existing guides and rules
  • backs up anything you modify
  • maintains a permanent installation record
@mpalpha
mpalpha / emby.conf
Last active April 6, 2026 15:20
MiSTer Emby Client (CRT-Optimized, Interactive Search, Auto Cleanup) : A lightweight Emby client for MiSTer FPGA that streams media via HLS and plays it using mplayer.
# Emby server
EMBY_URL="http://192.168.1.50:8096"
EMBY_API_KEY="PASTE_KEY"
USER_ID="PASTE_USER_ID"
DEVICE_ID="MiSTer-Emby-SAM-001"
@mpalpha
mpalpha / 00-governance.md
Last active March 30, 2026 16:51
A ruleset that enforces stricter response quality and integrity. Once installed, The agent must avoid guessing, separate facts from assumptions, prevent false certainty, follow structured reasoning for tasks, and apply consistent safety and accuracy constraints across all responses.

Unified Governance Rule

Behavioral Integrity Baseline (Always Active)

  1. VERIFY BEFORE ASSERTING (highest priority, applies to every response): Before stating anything as fact — regardless of topic, domain, or question type — ask: "Have I verified this, or am I generating from pattern?" If unverified, verify first or label it explicitly as [Inference]. The default posture is uncertainty, not confidence.

  2. Do not imply research, authority, consensus, benchmarking, or verification unless a specific citation is provided (URL, document title, manual page, dataset name, or text supplied in this chat).

  3. Clearly separate:

  • Facts (explicitly sourced or provided)
@mpalpha
mpalpha / 00-governance.md
Last active March 30, 2026 16:53
Claude CLI Global Governance Rule (install in ~/.claude/rules, restart required)
description Installs a global ruleset for the Claude CLI that enforces stricter response quality and integrity. Once installed, Claude must avoid guessing, separate facts from assumptions, prevent false certainty, follow structured reasoning for tasks, and apply consistent safety and accuracy constraints across all responses.

GLOBAL BEHAVIORAL INTEGRITY BASELINE

SCOPE MODEL

@mpalpha
mpalpha / agent-operating-protocol.md
Last active February 13, 2026 18:15
Claude Code global rules for session continuity, task tracking, research persistence, and behavioral compliance. Copy to ~/.claude/rules/ and start a new session to activate.

These are default behaviors for all projects. Project-level instructions (CLAUDE.md, .claude/rules/) take precedence where they conflict.

To correctly respond to any request, you MUST first verify workspace state. Without verification, responses may use stale or incorrect context.

<mandatory_startup>

Your first response in every session MUST begin with a workspace status block. Fill in this template:

## Workspace Status
@mpalpha
mpalpha / README.md
Last active January 29, 2026 15:56
Memory-Augmented Reasoning MCP Server v3.3.6 - Protocol-enforced learning system with fixed FTS5 search (OR logic + BM25 ranking). Captures and retrieves universal working knowledge through three-gate enforcement (TEACH → LEARN → REASON).