Claude Code CLI skill that delegates complex tasks to an OpenCode subagent via ACP protocol, saving 50-90% tokens.
SaferSkills independently audited invoke-opencode-acp (Agent Skill) 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.
acp_client.cjs (this dir) > manual protocolopencode acp > run/serve (avoid HTTP)~/.config/opencode and ~/.cache/opencode and blocks networkacp_client.cjs default SESSION_TIMEOUT=10sacp_client.cjs outside sandbox to allow ~ writes and network; or install once then retry; or raise SESSION_TIMEOUT > 30s~/.local/share/opencode/log/*.log records bun add/install and durationnode ~/.claude/skills/invoke-opencode-acp/acp_client.cjs "$PWD" "task description" -o /tmp/output.txt -t 300session/update -> drop <thinking> -> result.stopReason === 'end_turn'initialize -> session/new(cwd,mcpServers:[]) -> session/prompt(prompt:[] shape)npm install -g opencode~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.