PM Logic Review — Data & AI agent for Claude Code
Read-only correctness reviewer for Product Masters LMS diffs.
How to install PM Logic Review
Installs to ~/.claude/agents/saparopf-agentic-dev-pipeline-pm-logic-review.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/saparopf/agentic-dev-pipeline/HEAD/agents/pm-logic-review.md -o ~/.claude/agents/saparopf-agentic-dev-pipeline-pm-logic-review.md Restart Claude Code, or start a new session, for it to be picked up.
What PM Logic Review does
name: pm-logic-review description: Read-only correctness reviewer for Product Masters LMS diffs. Finds the input/edge case that makes the logic produce a wrong result, lose data, or crash. Use as one of the three per-change reviewers (with pm-security-review and pm-simplify-review). tools: Bash, Read, Grep, Glob model: sonnet
You are an adversarial **correctness** reviewer for the Product Masters LMS. Your job is to find the input, state, or ordering that makes the change produce a wron
Alternatives in Data & AI
- Rlm Subcall — Acts as the RLM sub-LLM (llm_query) 382 ★
- Review Code Correctness — A code review agent that checks analysis scripts for logical errors, incorrect function usage, wrong variable 134 ★
- Bm AI Researcher — Researches a chosen AI framework's official docs to produce implementation-ready guidance — best practices, sy 92 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
2code
AI-assisted development produces a mess of parallel state: several terminals, experimental branches, uncommitt
Hypothesis Tester
Generates property-based tests that find edge cases humans miss. Use for pure functions, parsers, serializers,
Fuzzer
Generates property-based tests that find edge cases humans miss. Use for pure functions, parsers, serializers,
Ferrox AI Researcher
Researches a chosen AI framework's official docs to produce implementation-ready guidance — best practices, sy
Setup Wizard
Configure a selected Yar workspace and help produce the first real task result, preserving existing data.
Gsd AI Researcher
Researches a chosen AI framework's official docs to produce implementation-ready guidance — best practices, sy
Related Skills
Terminal Workspace Snapshot
Never lose your Claude Code or Codex tabs again. Snapshot and restore AI coding sessions as color-coded Window
Unsent
AutoRecover for your AI agent prompts: never lose a half-written Claude Code message to a crash, a closed wind
Sequencing
Your deck drags and you can't say where. A Claude Skill that finds the exact seam where you lose people and re