Comprehensive guide for OpenCode - the open-source AI coding agent.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionopencode-expertExecute the skills CLI command in your project's root directory to begin installation:
Fetches opencode-expert from s-hiraoku/synapse-a2a and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate opencode-expert. Access via /opencode-expert in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
6
total installs
6
this week
2
GitHub stars
0
upvotes
Run in your terminal
6
installs
6
this week
2
stars
Comprehensive guide for OpenCode - the open-source AI coding agent.
| Task | Command/Action |
|---|---|
| Start TUI | opencode |
| Continue session | opencode -c or opencode --continue |
| Run non-interactive | opencode run "message" |
| Start headless server | opencode serve |
| Web interface | opencode web |
| Switch agent | Tab key |
| File search | @ then type filename |
| Undo changes | /undo |
| Redo changes | /redo |
| Share conversation | /share |
| Initialize project | /init |
| Configure API keys | /connect |
OpenCode has two primary agents, switchable with Tab:
ask mode)Invoke subagents with @ mention:
| Key | Action |
|---|---|
Tab |
Switch between Build and Plan agents |
@ |
Fuzzy file search |
Ctrl+C |
Cancel current operation |
| Command | Description |
|---|---|
/connect |
Configure LLM provider API keys |
/init |
Initialize project and create AGENTS.md |
/undo |
Revert recent changes (stackable) |
/redo |
Restore undone changes |
/share |
Create shareable conversation link |
# Start TUI in current directory
opencode
# Start in specific project
opencode /path/to/project
# Continue previous session
opencode --continue
opencode -c
# Use specific session
opencode --session <id>
opencode -s <id>
# Start with specific model
opencode --model <model>
opencode -m <model>
# Start with specific agent
opencode --agent build
opencode --agent plan
# Run single prompt
opencode run "Fix the bug in auth.py"
# Run with file attachment
opencode run "Review this" --file README.md
opencode run "Review this" -f README.md
# Run and share result
opencode run "Explain this code" --share
# Run specific command
opencode run --command "npm test"
# Start headless API server
opencode serve
# With custom port
opencode serve --port 3000
# With mDNS discovery
opencode serve --mdns
# Web interface
opencode web
# Authentication
opencode auth login
opencode auth list
opencode auth logout
# Models
opencode models # List available models
opencode models --refresh # Refresh model cache
# Agents
opencode agent create # Create custom agent
opencode agent list # List agents
# MCP servers
opencode mcp add <server>
opencode mcp list
opencode mcp auth
opencode mcp debug
# Sessions
opencode session list
opencode session list -n 10 # Last 10 sessions
# Statistics
opencode stats
opencode stats --days 7
opencode stats --tools
opencode stats --models
# Export/Import
opencode export <sessionID>
opencode import <file>
# Upgrade
opencode upgrade
opencode upgrade <version>
OpenCode provides these tools to agents:
| Tool | Description |
|---|---|
| read | Read file contents with optional line ranges |
| write | Create new files or overwrite existing |
| edit | Modify files using exact string replacements |
| patch | Apply patch files |
| grep | Search file contents with regex |
| glob | Find files by pattern (**/*.js) |
| list | List files and directories |
| bash | Execute shell commands |
| lsp | Language Server Protocol integration (experimental) |
| todowrite | Create/update task lists |
| todoread | Read current todo state |
| skill | Load skill files into conversation |
| webfetch | Fetch and read web pages |
| question | Ask user clarifying questions |
Skills are discovered from (in order):
.agents/skills/<name>/SKILL.md (project, shared with Codex).claude/skills/<name>/SKILL.md (Claude-compatible project)~/.config/opencode/skills/<name>/SKILL.md (global)~/.claude/skills/<name>/SKILL.md (Claude-compatible global)---
name: my-skill
description: Description of what this skill does and when to use it.
---
# Skill Content
Instructions and documentation here...
--).opencode/ or opencode.json~/.config/opencode/| Variable | Description |
|---|---|
OPENCODE_CONFIG |
Custom config path |
OPENCODE_PERMISSION |
Permission mode |
OPENCODE_SERVER_PASSWORD |
Server auth password |
OPENCODE_DISABLE_AUTOUPDATE |
Disable auto-updates |
OPENCODE_EXPERIMENTAL |
Enable experimental features |
OPENCODE_ENABLE_EXA |
Enable Exa search |
Create agents via opencode agent create or define in:
opencode.json~/.config/opencode/agents/.opencode/agents/Agent config options: description, temperature, model, tool permissions, system prompts.
Switch to Plan agent (Tab) to review implementation strategy before making changes.
Use @filename to fuzzy search and reference files in prompts.
Use /undo liberally - changes are stackable and reversible with /redo.
Use --continue or -c to resume previous sessions and maintain context.
For detailed documentation, see:
references/cli.md - Complete CLI referencereferences/tools.md - Tool details and permissionsreferences/agents.md - Agent configuration guideMake data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
erichowens/some_claude_skills
sickn33/antigravity-awesome-skills
erichowens/some_claude_skills
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
opencode-expert reduced setup friction for our internal harness; good balance of opinion and flexibility.
opencode-expert fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
We added opencode-expert from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Keeps context tight: opencode-expert is the kind of skill you can hand to a new teammate without a long onboarding doc.
opencode-expert reduced setup friction for our internal harness; good balance of opinion and flexibility.
I recommend opencode-expert for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Keeps context tight: opencode-expert is the kind of skill you can hand to a new teammate without a long onboarding doc.
We added opencode-expert from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
opencode-expert is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Solid pick for teams standardizing on skills: opencode-expert is focused, and the summary matches what you get after install.
showing 1-10 of 27