petri-retry-patterns

Guide per-worker retry wiring in fan-out Petri nets with RetryPolicy or Trial counters.

3|Updated Mar 17, 2026

Search Tags:#anti-pattern #fan-out #LLM orchestration #retry policy #parallel review #workflow retry #petri net

Ready to run

npx skills add https://github.com/transreal/claudecode --skill petri-retry-patterns

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: petri-retry-patterns
Source: https://github.com/transreal/claudecode/tree/main/Claude%20Directives/skills/petri-retry-patterns
Command: npx skills add https://github.com/transreal/claudecode --skill petri-retry-patterns

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents incorrect Petri net wiring that causes fan-out parallel review workflows to get stuck or to re-run already successful workers during retries.

Core Features & Use Cases

Per-worker retry guidance: Ensures retry triggers are attached to individual worker failure paths rather than downstream verdicts.
Anti-pattern avoidance: Explicitly blocks the downstream “rerun-all” design that becomes broken with AND-merge.
Retry decision separation: Distinguishes transient worker execution failures from semantic “merged result needs repair” failures.
Validation checklist: Provides a concrete pre-generation checklist covering RetryPolicy usage, guards, GiveUp transitions, and trial counter correctness.

Quick Start

Ask your AI to generate a fan-out Petri net for individual worker reviews that retries only the failed workers, following the per-worker RetryPolicy pattern and avoiding any retry transition placed after Verdict.

Frequently Asked Questions about petri-retry-patterns

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I retry only the failed worker in a Petri net fan-out parallel review workflow?▼

To retry only the failed worker in a fan-out parallel review workflow, attach per-worker RetryPolicy configurations or explicit retry transitions with Trial counters directly to individual worker failure paths, avoiding downstream rerun-all loops.

Why does a downstream Verdict-triggered rerun-all retry loop break with an AND-merge in Petri nets?▼

A downstream Verdict-triggered rerun-all retry loop breaks with an AND-merge because it forces already successful workers to re-execute, causing the fan-out parallel review workflow to get stuck or redundantly process completed tasks.

What is the correct Petri net wiring for per-worker retry policies in LLM orchestration?▼

Correct Petri net wiring for per-worker retry policies in LLM orchestration requires selecting transition-level RetryPolicy per worker or an explicit per-worker retry transition with Trial counters, while strictly avoiding any retry transition placed after Verdict.

How do I separate transient worker execution failures from semantic review failures in workflow retries?▼

Separate transient worker execution failures from semantic review failures by distinguishing individual worker execution retries from downstream merged result repairs, ensuring retry triggers attach to specific worker failure paths rather than final verdicts.

What validation checklist should I use before generating a fan-out Petri net with workflow retry policies?▼

Before generating a fan-out Petri net with workflow retry policies, validate RetryPolicy usage, verify guards, check GiveUp transitions, and ensure trial counter correctness to prevent incorrect wiring that reruns successful workers.

When should I not use a downstream rerun-all retry design in parallel review workflows?▼

You should not use a downstream rerun-all retry design in parallel review workflows when multiple workers contribute to an AND-merge, as this anti-pattern causes the workflow to get stuck by attempting to rerun already successful workers.