Commands for OpenCode

699 that install into OpenCode. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

recipe-blueprint

26

shinpr/nautilus

Command Claude CodeOpenCode

Define the structural design context needed by a prototype or PRD.

not rated 7 1mo ago A 13 tokens original MIT

goal

27

fredcamaral/drawers

Command OpenCode

Hold this session to a goal — re-prompt on every idle until it is explicitly met.

not rated 7 3d ago A 18 tokens

career-ops

28

FutureSpeakAI/asimovs-mind

Command Claude CodeOpenCode

AI job search command center -- show menu or evaluate job description.

not rated 6 +1 5d ago A 12 tokens

bmad-architecture

29

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 19d ago A 52 tokens original MIT

create-plan

31

ihorkatkov/pantheon

Command Claude CodeOpenCode

Create detailed implementation plans through an interactive, iterative process. You should be skeptical, thorough, and work collaboratively with the user to produce high-quality technical specifications.

not rated 5 7mo ago A 31 tokens original MIT

board

33

markusbegerow/board-of-directors

Command OpenCode

Board of Directors orchestrator. Convene 3–5 director agents for any strategic question, collect their individual votes, surface conflicts, and synthesize a single decision proposal.

not rated 4 6d ago A 35 tokens

skillgen

34

redhat-vmeperf/agent-tasks-template

Command Claude CodeOpenCode

Generate new skills automatically from detected workflow patterns using a 4-gate pipeline with human approval gates.

not rated 3 5mo ago A 19 tokens original Unlicense

sync-claude-skills

35

atman-33/workhub

Command Claude CodeOpenCode needs its repo

Mirror the vault-local Claude skills and agents into .opencode.

not rated 3 changed 1mo ago A 20 tokens original MIT

brn

36

artttj/rapid-stack

Command Claude CodeOpenCode

Alias — lightweight brainstorm via superpowers:brainstorming (with overrides).

not rated 2 3mo ago A 15 tokens original MIT

fr-debugging

37

derio-net/super-fr

Command Claude CodeOpenCode

Debug a bug, test failure, or unexpected behavior INSIDE an isolated workspace and deliver a reviewed fix-PR. Wraps superpowers:systematic-debugging — enters fr-isolation first (reusing an active workspace, else a fresh fix branch), runs the four phases via the exec-bridge, autonomous to a PR with hard stops only at…

not rated 2 +1 yesterday A 130 tokens original MIT

update-docs

38

d-o-hub/github-template-ai-agents

Command Claude CodeOpenCode needs its repo

Auto-update all documentation with command verification and link validation.

not rated 2 changed 18d ago A 0 tokens original MIT

repo-cleanup

39

TuTouPower/repo_template

Command Claude CodeOpenCode

A command that loads and runs the repository-cleanup procedure.

not rated 2 changed 3d ago A 62 tokens

start-feature

40

zahardev/aicontext

Command Claude CodeOpenCode

Run a structured discovery interview before starting a new feature — explores the codebase, asks one question at a time, presents decision packages with options + recommendation, then creates a spec and task file.

not rated 2 17d ago A 38 tokens original MIT

translate

41

roshaw/claude-translation-agency

Command Claude CodeOpenCode

Translate any project or set of files into one or more target languages using the three-tier translator panel (Lead → Senior/Junior with adversarial QA). Works on codebases (i18n message catalogs, WordPress .po/.pot/.json, MDX/HTML content trees) and standalone documents (Markdown, JSON, docx, txt, subtitles, CSV).…

not rated 2 1mo ago A 202 tokens original MIT

bmad-deep-recon

43

bsahane/memory-mcp-server

Command Claude CodeOpenCode

Decision-grade research, three ways: draft a deep-research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), process a finished research report — file it, distill a succinct cited summary with metadata that downstream skills consume without reprocessing — or run the research here…

not rated 1 1mo ago A 160 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: