Instructions for Brad-Edwards/aptl: Always review for secure coding best practices in addition to other code review. Always ensure modern coding practices and patterns are used.
Instructions for hyperlogue/r3, a project described as: Review coding agents without arguing through chat. Comment directly on plans and diffs, let the agent revise them live, and track every issue to resolution.
Copilot instructions for 0XFF-96/Perth-Agent-Con-Workshop: This is a CopilotKit v2 + A2UI workshop app (Node/TypeScript, React 18, Vite). When reviewing a pull request, prioritise this stack's known pitfalls.
Instructions for riseup-oss/mcp, covering copilot code review instructions — @riseup-oss/mcp, context, what feedback to share, what not to flag and concrete patterns to call out.
Instructions for rainmanjam/poka-yoke, a project described as: Mistake-proofing for software. Shigeo Shingo's poka-yoke method as a Claude Code plugin: audit code for footguns, design APIs that resist misuse, install guardrails, turn incidents into devices.
Instructions for Schr0d/Archon, a project described as: Most tools give AI access to the codebase. Archon gives AI access to the change itself. Structural Analysis tool intergrated for AI planning and review workflow both for ai and human ( Claude Code, Codex, OpenCode and Others).
Instructions for mimfort/rag_for_git, covering ragforgit — codex cli context, install or update rag-reviewer for codex, companion global install for claude code and skills.
Code-review instructions for a repository containing a Model Context Protocol, or MCP, implementation. They tell reviewers to write useful Chinese comments and focus on security, performance, logic, architecture, types, errors, and tests.
Instructions for agent-receipts/obsigna, a project described as: Agent Receipts — cryptographically signed audit trails for AI agent actions. Protocol spec, SDKs (Go, TypeScript, Python), and MCP proxy.
Instructions for yuxiaoji30-lang/ai-maintainer-copilot-skill, covering agents.md, where the skill lives, what this skill is for, hard rules for any agent using this repo and validating changes.