opencode — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited opencode (Plugin) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Claude Code skills that enable multi-model AI as subagents via OpenCode.
--worktree enables file editing for subagents| Skill | Use Case |
|---|---|
gemini-flash | PDFs, images, quick tasks |
gemini-pro | Deep reasoning, research |
gpt | Long coding tasks |
Exact model versions are defined in ocw/main.go (flashModel, proModel, gptModel). Run ocw list or check source for current bindings.
As a Claude Code plugin
/plugin marketplace add metrovoc/cc-skill-opencode
/plugin install opencode@cc-skill-opencodeFrom source
# Build ocw wrapper
cd ocw && go build -o ~/.local/bin/ocw .
# Link skills
ln -s $(pwd)/skills/* ~/.claude/skills/new returns hash, chat requires hash--worktree for safe code edits~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.