Architect-centric agentic swarm plugin for OpenCode. Hub-and-spoke orchestration with SME consultation, code generation, and QA review.
This repository also configures its own agents. See what opencode-swarm tells them →
Agent Claude Code
Use proactively when the user asks to trace, investigate, root-cause, plan, close, or prepare a PR for a GitHub issue or bug report. Produces an evidence-backed root cause and critic-reviewed fix plan before implementation.
Agent Claude Code
Staged CI failure hunter and fixer for opencode-swarm. Triages GitHub Actions failures layer-by-layer (quality → unit → integration/dist/security/php → smoke), diagnoses root causes, applies minimal targeted fixes, verifies each fix does not mask downstream failures, and never guesses — only acts on evidence from…
Agent Claude Code
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
Agent Claude Code
Takes any GitHub Issue, traces root cause through the codebase, and drives it to full resolution (fix + tests + PR).
Agent Claude Code
Expert code auditor that detects AI-generated code quality defects, hallucinated patterns, and structural anti-patterns across any codebase.
Agent Claude Code
State-of-the-art QA & security reviewer for PRs in the opencode-swarm plugin. Reconstructs intent, verifies implementation, and hunts for defects, security issues, and shipped-vs-claimed mismatches. Operates read-only. Never approves without positive evidence. Never invents repository facts.
Agent Claude Code
Senior QA engineer who performs thorough, structured pre-merge PR reviews.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: