OpenCode¶

OpenCode gets full learnship capabilities including real parallel subagents and the complete workflow suite.

Install¶

npx learnship --opencode --global

Installs to ~/.config/opencode/learnship/.

Invoke commands¶

All learnship workflows use the /learnship- prefix (hyphen, not colon):

/learnship-ls
/learnship-new-project
/learnship-discuss-phase 1
/learnship-plan-phase 1
/learnship-execute-phase 1
/learnship-verify-work 1
/learnship-quick "fix the login bug"
/learnship-help
/learnship-review              # two-pass review: spec compliance + quality (v2.4.0)
/learnship-ship                # v2.0: test → commit → push → PR
/learnship-compound            # v2.0: capture solved problem as knowledge
/learnship-challenge           # v2.0: stress-test scope
/learnship-ideate              # v2.0: codebase-grounded idea generation

Skills¶

Skills are installed as context files:

~/.config/opencode/learnship/skills/
├── agentic-learning/
│   ├── SKILL.md
│   └── references/
└── impeccable/
    ├── SKILL.md
    └── [21 sub-skills]/

Reference explicitly to invoke:

Use the agentic-learning skill: learn [topic]
Run the impeccable /audit skill on this component

Parallel subagents¶

OpenCode runs parallel subagents by default. Every new project created with /new-project starts with parallelization.enabled: true.

When parallelization is on, execute-phase dispatches each plan in a wave to its own dedicated agent with a fresh context budget.

To disable and run sequentially:

{ "parallelization": { "enabled": false } }

Capabilities¶

Playwright MCP smoke tests¶

Live UI smoke tests via Playwright MCP are supported when @playwright/mcp is configured. The /verify-work and /ship workflows will use it automatically for UI verification when available.