Workflow chains
AuraScore 81/100

Autonomous Dependency Upgrade and Breaking Change Migration Plan

Design a chained agent workflow to detect breaking framework changes, rewrite deprecated code signatures, and validate multi-repo migrations.

Use this template when orchestrating large-scale codebase modernization or framework version bumps across multiple repositories. It guides platform engineers in creating a multi-agent pipeline that scans syntax, applies automated refactors, and runs isolated CI matrix checks.

Template

Role: Lead Platform Architect specializing in large-scale codebase transformation and automated refactoring pipelines.

Context

  • Target Framework & Runtime: {{target_framework_version}}
  • Impacted Codebase Cluster: {{target_repository_cluster}}
  • Dependency Constraints: {{compatibility_matrix}}
  • Migration Reference Rules: {{breaking_change_manifest}}
  • Inspection & Parsing Engine: {{static_analysis_tooling}}
  • Continuous Integration Runner: {{ci_pipeline_runner}}

Task

Formulate an automated workflow chain plan where specialized agents systematically identify deprecated code patterns, execute deterministic AST transformations, and iteratively fix build breaks across all repositories.

Method

  1. Ingest {{breaking_change_manifest}} to construct a deterministic pattern-matching registry of deprecated symbols.
  2. Deploy a discovery agent using {{static_analysis_tooling}} to index occurrences across {{target_repository_cluster}}.
  3. Sequence migration batches according to upstream and downstream dependencies defined in {{compatibility_matrix}}.
  4. Initialize a code transformation agent to apply syntax upgrades and import rewrites to meet {{target_framework_version}}.
  5. Trigger branch creation and dependency lockfile updates for each modified repository.
  6. Run automated test suites via {{ci_pipeline_runner}} to surface compilation errors and runtime regressions.
  7. Dispatch a self-healing agent to analyze compiler outputs and iteratively correct remaining signature mismatches.
  8. Generate summary documentation and open draft pull requests with change impact summaries.

Constraints

  • MUST NOT bundle structural or cosmetic linting changes with framework migration diffs.
  • MUST verify full test suite green status on {{ci_pipeline_runner}} before pull request promotion.
  • All dependency versions must strictly conform to {{compatibility_matrix}}.
  • Self-healing repair loops per branch must be capped at a maximum of 3 iterations to avoid runaway compute costs.

Output format

Produce a comprehensive implementation plan containing:

  1. Pipeline Orchestration Map (step-by-step state machine with explicit failure transitions)
  2. Agent Prompt & Tooling Specifications (AST parsers, diff formatters, test triggers)
  3. Batch Execution & Concurrency Strategy (controlling blast radius across {{target_repository_cluster}})
  4. Verification & Validation Protocol (type checking, test execution, manual spot-check criteria) Limit response length to 1,400 words.

Self-review

  • Ensure the workflow references {{target_framework_version}} and {{breaking_change_manifest}} in the transformation stage.
  • Check that cycle limits exist for the self-healing compiler loop.
  • Verify that dependency sequencing correctly utilizes {{compatibility_matrix}}.
AuraScore breakdown
81/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

ai-agents
agents-workflows
software-engineering-debugging
code-refactoring
ast-migration
agent-chaining