Tools & Commands

@dietrichgebert/ponytailLazy senior dev mode for AI agents. The best code is the code you never wrote.

@plannotator/opencodePlannotator plugin for OpenCode - interactive plan review with visual annotation

@prevalentware/opencode-goal-pluginOpenCode goal plugin that adds Codex-style long-running goal mode, /goal commands, persistence, and TUI status for AI coding agents.

opencode-ptyOpenCode plugin for interactive PTY management - run background processes, send input, read output with regex filtering

opencode-skills-collectionOpenCode CLI plugin that automatically downloads and keeps skills up to date.

opencode-cmd-providerCommand Code provider + plugin for opencode

opencode-skill-creatorOpenCode plugin for skill creation — custom tools for validation, evaluation, description optimization, benchmarking, and review serving.

opencode-snipOpenCode plugin that prefixes shell commands with snip to reduce LLM token consumption

opencode-landstripOS-level AI command sandboxing for OpenCode with Landstrip

opencode-skills-tuiOpenCode TUI plugin that shows skills and loaded state in the sidebar

jev-guardPrompt-injection and dangerous-action guard for coding agents (Claude Code, Codex, pi, ACP), powered by Jev.

@knownasred/plannotator-opencodePlannotator plugin for OpenCode - interactive plan review with visual annotation

@brainervirus/opencode-commandcodeCommand Code API provider for opencode — use Claude, GPT, Gemini, DeepSeek, Qwen, Kimi, GLM, MiniMax, and Step models via Command Code

opencode-queuePersistent prompt, command and shell queues for OpenCode v2

opencode-datarobot-skillsOpenCode plugin providing DataRobot skills for AI/ML workflows and a DataRobot-branded theme.

dejavu-gatesCross-session error gates for AI coding agents: detects recurring tool-call failures and promotes them into enforced gates. Remind first, block on same-session repeat offense. Works with OpenCode, Claude Code, Codex CLI, Gemini CLI, Cursor, Copilot CLI, a

opencode-auto-permissionsAutomatic, context-aware permission review for OpenCode

@imransyafi/opencode-bgOpenCode plugin for interactive PTY management - run background processes, send input, read output with regex filtering

@opencode-cockpit/shellBackground shells for OpenCode: the agent starts, waits on and drives PTYs; you watch them in a docked TUI panel

@opencode-cockpit/statusA statusline for OpenCode you can actually configure: declarative segments, a typed module, or your existing Claude Code statusline command

@opencode-cockpit/updaterEvery OpenCode plugin you have installed: what actually runs, what is published, and an update that is checked against disk

opencode-atuin-historyOpenCode plugin that records agent bash commands in Atuin shell history

@opencode-cockpit/trustPermissions that learn: approve the same command enough times and it approves itself, visibly

@mynameistito/opencode-usage-limitsOpenCode TUI plugin that shows Codex, DeepSeek, Moonshot/Kimi API balances, Novita AI, OpenRouter, Command Code, OpenCode GO, ZAI, Synthetic, MiniMax Token Plan, and Qwen usage limits in the sidebar and prompt footer.

opencode-tokenwatchReal-time token usage, cache analytics & performance dashboard plugin for OpenCode CLI

opencode-thinking-fixRestores reasoning content dropped from multi-turn OpenCode conversations (DeepSeek, Kimi, GLM, MiMo, MiniMax, InclusionAI/Ling, OpenCode Go, OpenRouter). V1 + V2 plugin, proxy, and watchdog.

korean-report-skills한국어 기술·사업 문서의 자립형 HTML 제작과 문체·프레이밍·정확성 검토를 제공하는 Agent Skills

@kpnpm/homiePersonality layer for coding agents. Same code, different voice: yo / dawg / mafa / off.

@wallbreakerno4/opencode-commandcodeOpenCode provider plugin for the Command Code Go plan: an in-process bridge to the /alpha/generate gateway.

@edo1994/opencode-queueQueue OpenCode prompts and slash commands until the agent is idle

opencode-effect-enforcerOpenCode V2 plugin for Effect v4 skills, guidance, and pattern enforcement

opencode-sidebar-token-metricsOpenCode sidebar plugin showing generation speed (tok/s), cache hit rate, and average time-to-first-token (TTFT).

@ursuciprian/reflexProd-safe AI coding agents for infra teams: terraform AI agent guardrails (plan-aware apply gate), AWS, kubectl and Terraform workspace context, change freezes, a team policy and a SOC 2 / ISO 27001 audit export for Claude Code, Codex CLI, opencode and pi

@prevalentware/opencode-loop-pluginOpenCode loop plugin that adds Claude Code-style /loop recurring prompts: a persistent scheduler that re-injects an instruction into a session on an interval while it is idle.

@telsoncc/opencode-commandcodeCommand Code API provider for opencode — use Claude, GPT, Gemini, DeepSeek, Qwen, Kimi, GLM, MiniMax, and Step models via Command Code

opencode-sidebartmux sidebar launcher for OpenCode

opencode-terminal-progressOpenCode CLI plugin that shows agent progress in terminal tabs (Ghostty, iTerm2, kitty, WezTerm, Windows Terminal)

opencode-seatbeltmacOS Seatbelt (kernel sandbox) for OpenCode. Stops coding agents from reading secrets, enforced by the OS, not by command matching.

opencode-plugin-browserSidebar section listing OpenCode plugins with installed/uninstalled status, below MCPs and Skills.

@reasoning-router/opencodeAdaptive per-step reasoning effort for OpenCode V2

opencode-plugin-loop/loop command for opencode — run prompts on a schedule (fixed, adaptive, or maintenance), modeled after Claude Code's /loop

opencode-seshOpenCode session browser: search, preview, and resume every session across every project from the terminal or TUI.

@warp-dot-dev/opencode-warpWarp terminal integration for OpenCode — native notifications and more

opencode-tmux-indicatorOpenCode CLI plugin that sets a tmux window option when the agent is waiting for input

opencode-zellij-indicatorShow the selected OpenCode 2 session's status and title on its Zellij tab

@rajnandan1/kenThompson-mode systems discipline for AI agents. Try it, and if it doesn't work, throw it out and do it again.

@madsoftwaredev/opencode-direnvOpenCode V2 plugin that applies direnv environments to each shell command.

commandcode-go-opencode-providerCommand Code API provider for opencode — use Claude, GPT, Gemini, DeepSeek, Qwen, Kimi, GLM, MiniMax, and Step models via Command Code

@justsilver/opencode-goal-pluginCodex/OMP-style persistent goals for OpenCode V2: /goal command + goal tool + idle auto-continuation + evidence-based completion + blocked/budget guards

agy-crewDelegate work to Google's Antigravity CLI (agy) across a pool of accounts. A fork of agy-staff.

@geohar/opencode-sharedserverOpenCode plugin: manage shared backend processes via the sharedserver CLI.

@spoons-and-mirrors/subtask2Opencode plugin for enhanced subtask control with return context and prompt chaining

@himanshujangir/frankLocal receipt and pushback guardrails for AI coding agents.

@yuanbopang/frugalCloud cost awareness plugin for coding agents (Claude Code, Codex, Copilot, Qoder, Gemini CLI, OpenCode, pi, Cursor, Windsurf, Cline, Kiro)

@miguelmartens/opencode-cavemanCaveman for OpenCode: terse output mode, always on, with /caveman mode switching. why use many token when few do trick.

opencode-gws-multi-accountMulti-account management for the Google Workspace CLI (`gws`). opencode plugin: a `tool.execute.before` hook and auto-registered skill.

@openspoon/subtask2Opencode plugin for enhanced subtask control with return context and prompt chaining

opencode-usage-reportopencode plugin: /usage command showing subscription quota windows for configured providers

@brutalsystems/birddog-opencodeopencode plugin for birddog — publishes a session's state so birddog can observe it from outside. Read-only: it reports, and never acts on the session.

opencode-opper-budgetOpenCode CLI plugin that shows your Opper spend in the status bar