Commands

Slash commands. One file, one job, loaded with the rest of your configuration.

bmad-architecture

1609

mmornati/leanproxy-mcp

Command Claude CodeOpenCode

Produce the architecture: a lean spine of invariants that keeps everything built from it consistent, projected into whatever format the work needs. Use when the user says "create the architecture", "create technical architecture", "architecture spine", or "create a solution design".

not rated 5 1mo ago A 52 tokens original MIT

gh-pr-changelog

1610

james-prodopen/emcmd

Command Claude Code

Generate changelog for recent PRs merged into main (args: owner/repo days author). Arguments: $ARGUMENTS.

not rated 5 11mo ago A 0 tokens original MIT

AGENTS

1611

binary16labs/prime-silo

Command Claude Code

Command "AGENTS" from binary16labs/prime-silo, covering agents, purpose, documentation hierarchy, how to document command child docs and contract.

not rated 5 13d ago A 0 tokens copy · 88% MIT

misra

1612

atillab1/embedded-ai-workspace

Command Claude Code

Run a MISRA-C:2012 (AMD4) compliance review on a C file or pasted code, with extra ISR safety checks.

not rated 5 6mo ago A 27 tokens original MIT

default

1614

navig-run/core

Command Claude Code

System prompt for /default slash command.

not rated 5 7d ago A 7 tokens

handle-pr-comments

1615

netanelavr/dotcursor

Command Claude Code

Fetch all PR comments, classify by severity, and present for user approval before acting.

not rated 5 5mo ago A 0 tokens

away

1617

tomzhengy/harness-configs

Command Claude Code

Enable away mode so the agent can place a ringing phone call when it hits a blocker while I am asleep or away. Only I trigger this by typing /away; never enable it on your own.

not rated 5 9d ago A 0 tokens

modernize

1618

laird/agents

Command Claude Code

Description: Orchestrate a team of specialist agents to upgrade a project to be modern, secure, well-tested, and performant.

not rated 5 changed yesterday A 0 tokens

fix-bug

1619

pablomarin/claude-codex-forge

Command Claude Code

Diagnose and fix a reproducible defect through an open PR. The active Claude Code or Codex host is the main agent for this session; there is no permanent main engine.

not rated 5 changed 7d ago A 0 tokens original MIT

debug

1621

joshuavial/_ai.dev

Command Claude Code

Run the bug-investigator agent for systematic bug diagnosis and TDD-driven resolution.

not rated 5 10mo ago A 0 tokens

weekly-review

1622

flying-coyote/claude-code-project-best-practices

Command Claude Code needs its repo

Conduct the weekly review of project status and documentation currency. This prompt is standalone: run it in a fresh session with the working directory at the repo root, and everything it needs is either in this file or derivable from disk. Derive counts and dates from disk every time rather than trusting what a doc…

not rated 5 +1 yesterday A 0 tokens

audit

1623

cslsolucoes/SkillsORM

Command Claude CodeCursor

Gera laudo técnico profissional de um projeto Delphi — 8 dimensões com score e plano de modernização. Quest de clarificação define tipo, escopo, dimensões e finalidade antes de executar.

not rated 5 6mo ago A 43 tokens

git_backup

1624

samartined/mAIcelium

Command Claude Code

Stage, commit, and push all changes in the mAIcelium workspace to GitHub.

not rated 5 2d ago A 18 tokens

_example

1625

hellowind777/helloagents-archive

Command Claude Code

A template for defining custom commands with a name, parameters, function description, and a requirement-understanding check.

not rated 5 7mo ago A 0 tokens

e2e

1627

mh2-lee/everything-claude-code

Command Claude Code

Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts.

not rated 5 9mo ago A 28 tokens

implement-plan.eval

1628

davistroy/claude-marketplace

Command Claude Code

Executes an IMPLEMENTATIONPLAN.md using orchestrated subagents. Each work item is implemented, tested, and committed by a dedicated subagent. Good behavior: items are implemented in order, status markers are updated, tests pass, and a PR is created at the end.

not rated 5 25d ago A 0 tokens original MIT

decide

1629

vijayjoshi24/ea-agent-skills

Command Claude Code

Capture an architectural decision as a formal ADR (Architecture Decision Record).

not rated 5 6mo ago A 0 tokens original MIT

auto-discovery

1630

shwilliamson/automatasaurus

Command Claude Code

Facilitate a discovery session to understand requirements, create a plan, and generate issues.

not rated 5 8mo ago A 0 tokens original MIT

find

1631

colliercoder/forge-methodology

Command Claude Code

Deploy 4 parallel research subagents to analyze a feature before implementation. Creates comprehensive research reports and synthesized BRAINSTORM document.

not rated 5 9mo ago A 0 tokens

web3-audit

1632

x-cookie/cbughunter-k2

Command Claude Code

Smart contract security audit — runs through 10 bug class checklist (accounting desync, access control, incomplete path, off-by-one, oracle errors, ERC4626, reentrancy, flash loan, signature replay, proxy/upgrade). Applies pre-dive kill signals first. Generates Foundry PoC template for confirmed findings. Usage…

not rated 5 5mo ago A 0 tokens

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: