LLM commands

openpoem/spec-score-mcp

Command Claude Code

Score a spec file and generate a visual radar chart.

bronsonelliott/living-wiki

Command Claude Code

Brain dump mode -- talk about anything, Claude organizes it.

AttendantLion8/provider-fallback-plugin

Command

List available models and their provider-specific identifiers.

Synapsor/Synapsor-Runner

Command

Draft and validate one disabled Synapsor Safe Action for an existing application.

mrboups/xbrain

Command Claude Code

Build, query, and inspect the project knowledge graph in .planning/graphs/.

iamironz/ai-config-bundle

Command

Canonical command playbooks live under ai-kb/commands/. Tool-specific command files (Cursor/OpenCode) should be thin wrappers that delegate here.

ketankhairnar/ai-sales-team-public

Command

Prospect research & AI Action Plan generator for Basalt Consulting AI. Progressive workflow with feedback-driven checkpoints. Both founders can run it. Creates per-prospect directory with research, analysis, TLDR, full report, and diagrams.

albiol2004/trio-agent-loop

Command

Run one or more iterations of the Trio agent loop using the loop/ mailbox files. /trio = one supervised iteration; /trio auto = keep iterating in-session until SHIP, BLOCKED, or NEEDSHUMAN.

conorbronsdon/agent-memory-kit

Command

Walk a dream proposal artifact, review each item, apply accepted ones, commit.

ronmkr/PromptBook

Command

Full discovery & portfolio analysis of a legacy system — inventory, complexity, debt, effort estimation.

videnovnebojsa/personal-ai-os-starter

Command Claude Code

Schedule a prompt or slash command to run automatically at a specific time. One-shot - fires once, then deletes.

pruthvinathJV/nextjs-claude-code-kit

Command

Audit caching configuration in $ARGUMENTS for Next.js 15 correctness.

maysunAI/T00-zh

Command Claude Code

A command that checks a Claude Code setup, including automatically loaded instructions, token use, skills, and hooks. It is described in Chinese and produces a configuration report with optimization suggestions.

coeusyk/inference-x

Command Cursor

Enter explore mode - think through ideas, investigate problems, clarify requirements.

mystilleef/spae-framework

Command

Execute a named subagent with optimized instructions.

dronsv/jdwp-mcp

Command Claude Code

I'm debugging a Java app. Make sure it's running with JDWP enabled: java -agentlib:jdwp=transport=dtsocket,server=y,suspend=n,address=:5005 -jar app.jar.

aryxnsdfs/token-diet

Command Claude Code

Apply the AI's code changes to your files.

CorvidLabs/agent-3md

Command Claude Code

Scaffold a new spec-sync module spec from a module name or a natural-language feature description (full scaffold by default, or minimal with --minimal).

fastslack/kernl

Command Claude Code

Stage the files belonging to the current change theme and propose a commit title (does NOT commit).

eduardoabreu81/livewiki

Command

This page documents how the livewiki batch command is registered with the Commander CLI framework and how it formats batch run reports for human consumption.

Simple4uhq/sae4u-memory

Command

A periodic ritual: read the rolling tick log, propose promotions to permanent memory, and let the user confirm what to keep, archive, or forget.

rubensgomes-org/calculator-mcp

Command Claude Code

Generate a release plan for the project.

nikondrat/cctx-mcp

Command Claude Code

Enter explore mode - think through ideas, investigate problems, clarify requirements.

khalilbenaz/MDAN

Command Claude Code

Perform adversarial code review finding specific issues. Use when the user says "run code review" or "review this code".