LLM commands

638 tagged LLM, measured the same way as everything else here.

Browse within: agent 169agents 155claude-code-plugin 155agentic-ai 142agentic 128agent-memory 118cli 113model-context-protocol 105javascript 87knowledge-graph 81Multi-Agent 80agent-framework 66knowledge-management 66claude-plugin 65

AGENTS

01

langgenius/dify

Command Claude Code

Per-command agent-optimized usage and structure guide.

not rated 159k +575 changed 16d ago A 0 tokens

docs

02

upstash/context7

Command Claude Code

Look up documentation for any library.

not rated 63k +261 changed 3d ago A 6 tokens original MIT

fix-issues

03

can1357/oh-my-pi

Command Claude Code

Diagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds.

not rated 36k +763 today A 0 tokens original MIT

gh-triage

04

mastra-ai/mastra

Command Claude Code

GitHub OSS maintainer lifecycle triage, review, and approval management.

not rated 29k +162 changed 24d ago A 19 tokens

AGENTS

05

promptfoo/promptfoo

Command Claude Code

Commander.js-based CLI commands registered in src/main.ts.

not rated 26k +173 today A 0 tokens original MIT

ask

06

EverMind-AI/EverOS

Command Claude Code

Ask a question about past work. Searches memories and combines with current context to answer.

not rated 13k +54 today A 17 tokens original Apache-2.0

kayba-ai/agentic-context-engine

Command Claude Code

The kayba CLI interacts with the Kayba hosted API (https://use.kayba.ai). Auth: set KAYBAAPIKEY env var or pass --api-key to every command.

not rated 2.6k +11 22d ago A 0 tokens original Apache-2.0

hep-storm

09

agentlas-ai/Agentlas-OS

Command Claude CodeCodex

Run a force-robust Stormbreaker loop — route to real agents, execute a verified pipeline to completion.

not rated 1.6k +13 changed 1mo ago A 22 tokens original Apache-2.0

rem_help

10

openonion/connectonion

Command Claude Code

Each section is printed verbatim by --help for the command it names. The agreed design is issue #1656; change a page there and here together.

not rated 1.5k +1 changed today B 0 tokens original Apache-2.0

AGENTS

11

melandlabs/openloomi

Command Claude Code

CLI subcommands live here.

not rated 1.0k +5 22d ago A 0 tokens original Apache-2.0

update-postman

12

Pipelex/pipelex

Command Claude Code

You update the Pipelex FastAPI collection directly in the user's Postman desktop app via the Postman API. You take an incremental, diff-based approach: read what's already in Postman, compare against the current API state, and only change what's needed.

not rated 945 +3 changed 12d ago A 0 tokens

save-memory

13

0xK3vin/MegaMemory

Command Claude Code

You are saving what you learned this session into the megamemory knowledge graph. This is YOUR memory — record anything valuable for future sessions: what you understood about the project, what you built, decisions that were made, patterns you noticed, or intent the user shared.

not rated 725 +6 5mo ago A 0 tokens original MIT

review

14

Affitor/affiliate-skills

Command Claude Code

Review a skill for quality before merge.

not rated 723 +17 3d ago A 0 tokens original MIT

commit

15

BigSweetPotatoStudio/HyperChat

Command Claude Code

A command for submitting a change, with an optional argument supplied through $ARG.

not rated 709 1mo ago A 0 tokens

trellis-finish-work

16

fy-agent/fyagent

Command Claude CodeCursor needs its repo

Wrap up the current session: archive the active task (and any other completed-but-unarchived tasks the user wants to clean up) and record the session journal. Code commits are NOT done here — those happen in workflow Phase 3.4 before you invoke this command.

not rated 831 +1.4k today A 0 tokens

code-review

17

truffle-ai/dexto

Command Claude Code

Review code for bugs, improvements, and best practices with actionable feedback.

not rated 652 +2 today A 16 tokens

run-daily

19

leiting-eric/DailyBrief

Command Claude Code needs its repo

Trigger the daily digest now (background via OS scheduler) and monitor until completion.

not rated 372 +5 today A 15 tokens original MIT

debug

20

echoVic/blade-code

Command Claude Code

A command for investigating software errors by classifying them, tracing their source, and comparing expected with actual behaviour.

not rated 180 3d ago A 5 tokens original MIT

compact-prep

21

sammcj/agentic-coding

Command Claude Code

Ask the agent to prepare for conversation compaction by updating any relevant state and providing guidance for the compaction agent and to kick off the session there after.

not rated 164 +2 3d ago A 30 tokens original Apache-2.0

CLAUDE

22

nexus-research-lab/nexus

Command Claude Code

Multi-agent collaboration platform for persistent, proactive AI agents across rooms, workspaces, skills, and external services.

not rated 152 +1 today A 0 tokens original Apache-2.0

story

23

Xiaoyangy/novel-studio

Command Claude Code

A Chinese-language command that routes vague writing requests to the appropriate web-novel writing, analysis, or ranking tool.

not rated 138 +6 23d ago A 30 tokens original Apache-2.0

closedloop-ai/claude-plugins

Command Claude Code

You are a release engineer responsible for maintaining the root-level CHANGELOG.md and verifying plugin READMEs. Analyze git changes, update the single CHANGELOG.md following the Keep a Changelog format organized by plugin, and ensure plugin READMEs accurately reflect their contents.

not rated 122 changed 8d ago A 0 tokens original Apache-2.0

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: