opencode-use

A guide that helps Claude Code choose how to handle a coding task: directly, with a Claude subagent, or through OpenCode. OpenCode is a separate service that can run coding tasks using other models, including ongoing sessions.

In plain words
What is it for?
It helps route small fixes, tests, documentation, CSS changes, refactors, reviews, and longer-running coding tasks to a suitable execution path.
Why use it?
It reduces guesswork about when to use each execution method, especially when cost, persistent work, or different model abilities matter.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/zhouqingweidev-ops/opencode-mcp/opencode-use
Any agent
npx skills add zhouqingweidev-ops/opencode-mcp --skill opencode-use
Clone the repo
git clone --depth 1 https://github.com/zhouqingweidev-ops/opencode-mcp

Made for: Claude Code, Codex.

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,108 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00089 $0.01108
Opus 5 $0.00044 $0.00554
Sonnet 5 $0.00018 $0.00222
Haiku 4.5 $0.00009 $0.00111

Measured yesterday against content hash f77d08b0a782, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opencode-use scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/opencode-use/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

opencode-use

This Skill is for the Claude Code primary agent. Claude keeps full ability to read, edit, test, reason, use native tools, and use Claude subagents. OpenCode is an optional execution channel, not a replacement for Claude. Do not send every task to OpenCode.

Choose one execution path

  • native_claude: Claude works directly. Choose this for tiny changes, code already understood by Claude, sensitive or high-risk files, frequent user interaction, architecture judgment, review/reasoning, or an explicit request for Claude to do the work. Do not call opencode-router-mcp.
  • claude_subagent: use Claude Code's native subagent for parallel research, independent code/security review, Claude-specific capabilities, or an explicit request for a Claude subagent. Never replace it with OpenCode.
  • opencode_run: use OpenCode for a bounded, one-shot, low-cost/free, mechanically verifiable task when Claude has not already done the full analysis. Prefer small bugs, lint/type fixes, test additions, simple refactors, docs, CSS, and repetitive edits.
  • opencode_session: use OpenCode when persistent status, review, revision, long-running work, retained context, or iterative visual work is genuinely useful. Model failover is handled internally by the MCP in either run or session mode and does not by itself require a session.

User instructions have highest priority: Claude request → native_claude; Claude subagent request → claude_subagent; OpenCode request → an OpenCode path; free-model request → maxTier: cheap, freeOnly: true, and allowTierUpgrade: false; OpenCode prohibition → do not call the MCP.

OpenCode delegation

The Skill decides among the four paths. The MCP only manages OpenCode-internal tier, model, run/session mode, failover, and compact state after Claude has selected OpenCode. MCP mode: auto never chooses Claude or a Claude subagent.

Use only these high-level tools: opencode_delegate, opencode_status, opencode_review, opencode_revise, opencode_abort, opencode_models, and opencode_usage. Do not call or suggest hidden upstream low-level tools.

Read the full file on GitHub · 46 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 46 lines · 89 tokens per session scan A f77d08b0a782

Subscribe to this mod's changes

opencode-use is a skill published in the GitHub repository zhouqingweidev-ops/opencode-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,108 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens