How do I install the Opencode skill?

Run npx skillmds@latest add belentani7/opencode in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Opencode skill do?

Delegate coding to OpenCode CLI (features, PR review). Optimized for token efficiency. It is listed under Coding & Dev Tools on SkillMD.

Is Opencode safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Opencode?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Opencode free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Opencode?

belentani7 (@belentani7) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Opencode by belentani7 — Agent Skill

Name: Opencode
Rating: 4.2 (5 reviews)
Author: belentani7

File contents

OpenCode CLI - Token-Efficient Configuration

Use OpenCode as an autonomous coding worker with Hermes for maximum token savings.

When to Use

User explicitly asks to use OpenCode
You want an external coding agent to implement/refactor/review code
Long-running coding sessions with progress checks
Parallel task execution in isolated workdirs

Prerequisites (Token-Efficient)

OpenCode installed: npm i -g opencode-ai@latest
Auth configured: opencode auth login or set provider env vars
Verify: opencode auth list should show at least one provider
Git repository for code tasks (avoids repo detection overhead)
Use pty=true only when interactive; otherwise use opencode run for one-shot

Token-Saving Modes

One-Shot Mode (RECOMMENDED - Saves 40-60% tokens)

terminal(command="opencode run 'Add retry logic to API calls and update tests'", workdir="~/project")

Runs once, returns result, exits immediately
No conversation history overhead
Best for: bug fixes, single features, code reviews

Background Mode (For iterative work)

terminal(command="opencode", workdir="~/project", background=true, pty=true)
# Returns session_id

# Send prompt (only when needed)
process(action="submit", session_id="<id>", data="Implement OAuth refresh flow")

# Poll for completion, don't log every turn
process(action="poll", session_id="<id>")

Key Token Optimization Tips

Use --model flag to specify cheapest adequate model

opencode run 'fix bug' --model anthropic/claude-3-5-sonnet-20241022

Use --allowedTools to limit tool access and reduce prompt size
```
claude -p 'Add error handling' --allowedTools 'Read,Edit'
```
Set --max-turns to bound conversation length
```
opencode run 'refactor' --max-turns 5
```
Use --json-schema for structured output instead of natural language descriptions
Prefer opencode run over interactive TUI for bounded tasks - avoids PTY overhead and session state
Cache results - if same task repeats, store and reuse successful prompts
Avoid unnecessary context - only pass relevant files, not entire project

Common Workflows

Code Generation (One-Shot)

opencode run 'Create REST API for user management' --model openrouter/anthropic/claude-3.5-sonnet

Debugging (One-Shot)

opencode run 'Why does this return null? Debug and fix' --max-turns 3

Code Review (One-Shot)

opencode run 'Review this code for security vulnerabilities' --allowedTools 'Read'

---name: opencodedescription: Delegate coding to OpenCode CLI (features, PR review). Optimized for token efficiency.license: MIT---# OpenCode CLI - Token-Efficient ConfigurationUse OpenCode as an autonomous coding worker with Hermes for maximum token savings.## When to Use- User explicitly asks to use OpenCode- You want an external coding agent to implement/refactor/review code- Long-running coding sessions with progress checks- Parallel task execution in isolated workdirs## Prerequisites (Token-Efficient)- OpenCode installed: `npm i -g opencode-ai@latest`- Auth configured: `opencode auth login` or set provider env vars- Verify: `opencode auth list` should show at least one provider- Git repository for code tasks (avoids repo detection overhead)- Use `pty=true` only when interactive; otherwise use `opencode run` for one-shot## Token-Saving Modes### One-Shot Mode (RECOMMENDED - Saves 40-60% tokens)```bashterminal(command="opencode run 'Add retry logic to API calls and update tests'", workdir="~/project")```- Runs once, returns result, exits immediately- No conversation history overhead- Best for: bug fixes, single features, code reviews### Background Mode (For iterative work)```bashterminal(command="opencode", workdir="~/project", background=true, pty=true)# Returns session_id# Send prompt (only when needed)process(action="submit", session_id="<id>", data="Implement OAuth refresh flow")# Poll for completion, don't log every turnprocess(action="poll", session_id="<id>")```## Key Token Optimization Tips1. **Use `--model` flag** to specify cheapest adequate model ``` opencode run 'fix bug' --model anthropic/claude-3-5-sonnet-20241022 ```2. **Use `--allowedTools`** to limit tool access and reduce prompt size ``` claude -p 'Add error handling' --allowedTools 'Read,Edit' ```3. **Set `--max-turns`** to bound conversation length ``` opencode run 'refactor' --max-turns 5 ```4. **Use `--json-schema`** for structured output instead of natural language descriptions5. **Prefer `opencode run` over interactive TUI** for bounded tasks - avoids PTY overhead and session state6. **Cache results** - if same task repeats, store and reuse successful prompts7. **Avoid unnecessary context** - only pass relevant files, not entire project## Common Workflows### Code Generation (One-Shot)```bashopencode run 'Create REST API for user management' --model openrouter/anthropic/claude-3.5-sonnet```### Debugging (One-Shot)```bashopencode run 'Why does this return null? Debug and fix' --max-turns 3```### Code Review (One-Shot)```bashopencode run 'Review this code for security vulnerabilities' --allowedTools 'Read'```

Frequently asked questions

Opencode