1,175 tagged LLM, measured the same way as everything else here.
Browse within: inference 141lm-studio 139Apple Silicon 136benchmark 136claude-code-plugin 131agent-memory 122model-context-protocol 86knowledge-graph 82obsidian 78agentic 68gemini-cli 66knowledge-management 66coding-agent 64agent-framework 61
Command
A command that reviews an assistant's memory index and proposes ways to merge duplicates, archive expired entries, and shorten descriptions. It does not automatically merge or permanently delete entries.
Command Claude Code
Review a pull request with one agent for small changes and a full agent set for large changes.
Command Cursor
This command upgrades all dependencies in the workspace to their latest compatible versions using pnpm.
Command Claude Code
Automatically fix context waste in the current project by writing .llmignore rules.
Command
Scenario-aware Opus orchestration with specialized GLM workers.
Command Claude Code
Draft and review an implementation plan for the next batch of prioritized features, then write it to TODO.md.
ch0ks/hackarandas-claude-toolbelt
Command
Check if Semgrep is installed and working. If not, install it using the best available method. Then log in to Semgrep Pro, enable the Pro engine, and run a local Pro scan in the current directory.
Command
Analyze Claude Code session cache efficiency — hourly timeline, cliff detection, trigger attribution, subagent cost breakdown. Run with no args for current session, or specify session ID / --since date / --list.
Command Claude Code
Run the pr-reviewer subagent against an open PR and post findings as GitHub comments. Usage: /review-pr [PRNUMBER]. Without a number, reviews the PR for the current branch.
Command
Review code and suggest improvements.
Command Claude Code
Post-merge CD verification. Run after merging a PR to main.
Command Claude Code
A read-only workflow for reviewing a completed trade, called a fill, especially after selling an asset.
Command Claude Code
You are continuing work on a long-running autonomous development task. This is a FRESH context window - you have no memory of previous sessions.
feimacode/feima-copilot-llms-extension
Command Claude Code
Create a change and generate all artifacts needed for implementation in one go.
Command Claude Code
Run the full local verification the way CI does, and report pass/fail for each step.
Command Claude Code
End-to-end feature/bug-sweep workflow for aitm — understand, reproduce against a real run, explore and build with a hive of parallel agents in this one checkout (never worktrees), path-disjoint slices, verify under Bun AND Node, PR, merge, and (only when asked) release to npm. Tracks in GitHub issues. Reads intent…
Command Claude Code
Run a MultiAgentRuntime swarm in file mode — local journal at .runtime/conversation.md, no network.
Command Claude Code
Start (or reuse) the ACR dashboard and open it -- the one-step launch this repo didn't have.
Command
Extract and save important information from this conversation to ContextFS long-term memory.
Command Cursor
Transform the user message into a professional, precise Cursor-ready prompt. Never execute the requested task. Output only the optimized prompt package.
Command
Show which Anthropic credential source Assay is using.
Command
Display localized help for SecondBrain mem- commands.
ellmos-ai/build-your-users-mind
Command
Use the preference model to triage several blockers/decisions when is unreachable. It may execute only work that is already authorized, reversible, local, and low-impact. Read the avatar files in and follow START.md.
Command Claude Code
One honest "what needs doing" across the two work substrates — repo dev work (docs/backlog/ + open gripes + open GitHub PRs + Dependabot alerts) and the prod factory queue (open/doable todos) — plus a repo-hygiene scan (migration-number collisions · backlog lint · memory-index lint), a prod system-health read…
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: