cursorrules
9505Cursor rule Cursor
You are connected to krusch-context-mcp, a persistent working memory engine. You MUST follow this lifecycle protocol across all coding sessions.
All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 438,333 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
Cursor rule Cursor
You are connected to krusch-context-mcp, a persistent working memory engine. You MUST follow this lifecycle protocol across all coding sessions.
Cursor rule Cursor
Coding rules for a senior full-stack developer, covering readable, maintainable code and how to organize functions, comments, errors, and changes. Full-stack means work across the user interface and server-side code.
Cursor rule Cursor
Author, edit and check ArchLang .arch floor plans with the archlang CLI.
entropy-cloud/attractor-guided-engineering-template
Skill Claude CodeCodex needs its repo
Daily git discipline for this repository — commits, rebase, history search, and the worktree policy. Use when committing, branching, rebasing, searching history, or when a merge conflict or history question comes up.
elliot35/deterministic-agent-control-protocol
Cursor rule Cursor
Enforce governance on all file and system operations.
Skill Claude CodeCodex
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup.
Skill Claude CodeCodex
Read, write, search, and manage notes in a WebObsidian vault through its Agent REST API (/api/v1). Use whenever the user asks to find, read, create, update, append to, or delete notes in their WebObsidian / Obsidian vault, list tags, get backlinks, or run a vault search. Credentials (base URL + API key) are stored in…
Skill Claude CodeCodex
Build, run, and deploy an AI agent using the aixyz framework. Use this skill when creating a new agent, adding tools, wiring up A2A/MCP protocols, configuring x402 micropayments, or deploying to Vercel.
Plugin Claude Code
Bundles 1 skill · 183 tokens together
OOP architecture planning and progress tracking for software projects. Generates Mermaid UML (class, sequence, component, state, and ER diagrams) inside CLAUDE.md with full typed signatures, visibility markers, and implementation status on every class/method/relationship. Triggers on: 'plan the architecture', 'design…
oculus-samples/voicesdk-samples-whisperer
Cursor rule Cursor
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
Skill Codex
Install, configure, diagnose or explicitly operate Token Router's local CLI. Everyday log retrieval uses its connected readpytestfailures tool directly; this guide is for setup and manual requests.
jhgaylor/node-candidate-mcp-server
Cursor rule Cursor
MCP TypeScript SDK implements the full Model Context Protocol specification, allowing you to build MCP servers and clients using TypeScript.
PriNova/pi-agent-codebase-workflows
Skill Claude CodeCodex
Structured reconstruction workflow for unfamiliar or undocumented codebases. Produces agent-first YAML artifacts only under a resolved structured docs root, with no prose Markdown fallback.
Plugin Claude Code
Bundles 4 commands, 2 hooks · 71 tokens together
Existence is pain — plays a Mr. Meeseeks voice line whenever Claude is waiting for you.
Skill Claude Code
Use when working with the appliku CLI or SDK to manage Appliku-hosted applications, deployments, domains, datastores, servers, teams, or SSH keys. Covers authentication, all CLI commands, Python SDK usage, and common deployment workflows.
MelodyTung888/memory-layers-skill
Skill Claude CodeCodex
A five-layer method for turning experiences into lasting knowledge and personal principles. It is triggered by requests to summarise lessons, identify patterns, or form rules.
Skill Claude Code
A scam-message checker that analyzes suspicious texts, images, or conversation descriptions. It can identify the likely stage of a scam and suggest what the sender may try next.
Plugin Claude Code
Bundles 1 skill, 3 commands · 181 tokens together
Audit your Mac's security posture from Claude Code, understand what each finding means and why it matters, then fix what's safe. Drives the fort CLI over your shell and remediates only what you approve. Read-only by default. Findings map to SOC 2 / ISO 27001 / NIST / CIS when you need audit evidence.
Agent Claude Code
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
Skill Claude CodeCodex
Simultaneous Launch Button - Two-person rule for destructive commands. Use when coordinating dangerous operations between agents, requiring peer review for rm -rf, git push --force, kubectl delete, DROP TABLE, or terraform destroy.
stefanoamorelli/estonia-ai-kit
Skill Claude CodeCodex
Interact with LHV Bank through the lhv CLI — check balances, view transactions, switch accounts, and make SEPA payments.
Skill Claude CodeCodex
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', '.docx', or requests to produce professional documents with headings, tables of contents, page numbers, or letterheads. Also use for extracting content from .docx…
Skill Claude Code
Git commit quality and conventional commits expertise with automatic issue tracking integration. Auto-invokes when the user explicitly asks about commit message format, commit quality, conventional commits, commit history analysis, issue references in commits, or requests help writing commit messages. Integrates with…
Skill Claude CodeCodex
Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: