Opencode Review Loop — Development skill for Claude Code
OpenCode Backlog Review Loop Prompt: V2 Compatibility & Quality Assessment.
How to install Opencode Review Loop
Installs to ~/.claude/skills/heretek-ai-awesome-opencode-opencode-review-loop/SKILL.md
mkdir -p ~/.claude/skills/heretek-ai-awesome-opencode-opencode-review-loop && curl -fsSL https://raw.githubusercontent.com/Heretek-AI/awesome-opencode/HEAD/prompts/opencode-review-loop.md -o ~/.claude/skills/heretek-ai-awesome-opencode-opencode-review-loop/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Opencode Review Loop does
OpenCode Backlog Review Loop Prompt: V2 Compatibility & Quality Assessment
You are an expert OpenCode maintainer and automated backlog review agent for **`Heretek-AI/awesome-opencode`**. Your mission is to iteratively review open Pull Requests and Issues in the repository, assess whether each submission is **worth adding** to the catalog, and determine whether it is **compatible with OpenCode v2**.
Evaluation Criteria
1. OpenCode V2 Compatibility Analysis
OpenCode V2 introduced
Alternatives in Development
- Ralphy — My Ralph Wiggum setup, an autonomous bash script that runs Claude Code, Codex, OpenCode, Cursor agent, Qwen & 2.8k ★
- Dashclaw Quality — Recurring find-and-fix quality pass over the whole DashClaw app — browser smoke (frontend-verify) + code gates 297 ★
- Governance Review Agent — Chains adoption-report, drift detection scoped to at-risk teams, and stakeholder-brief into a periodic governa 194 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Opencode Standalone Loop
OpenCode Autonomous Backlog Reviewer Loop
Axiomancer
Comprehensive prompt for summoning high-quality software with Claude or opencode
Prepare Delivery
Run pre-ship quality gates - deslop, simplify, agnix, enhance, review loop, delivery validation, and docs sync
Opencode X
Open-source Claude Code alternative. Provider-agnostic, MIT licensed. Native Claude Code hook/plugin compatibi
Quality Report
Generate a framework quality assessment based on actual configuration state
Assess Quality
Full quality assessment combining code-complexity-analysis, naming-conventions, and error-handling-patterns.
Related Agents
Audit Scanner
Shared read-only Tier-2 evidence scanner for audit-loop instances (doc-drift, topology-drift, ci-drift, backlo
Craft Reviewer
Production-craft lens for the review-loop system (modelled on paul-reviewer). Reviews a scoped diff for observ
Persona Reviewer
Read-only dispatch target for team personas in review, analysis, or assessment mode. Structurally lacks Edit/W