Outcome
Regression-risk review
Identifies directly affected behavior, adjacent behavior, regression-sensitive paths, interface, contract, dependency, configuration, and missing-evidence risks.
Use case
Post-change risk analysis
Use after a supplied implementation, API, schema, configuration, dependency, integration, or runtime-behavior change.
Output
Risk-prioritized findings
Returns direct impact, adjacent impact, regression-sensitive paths, risk-focused verification areas, missing evidence, and confidence.
Scope and best-fit use
Use this prompt to assess regression risk caused by a supplied change. It does not review test coverage, generate tests, write code, create patches, or produce a changeset plan.
Use when
A supplied change may affect existing or adjacent behavior
Use when a code, API, schema, configuration, dependency, integration, or runtime-behavior change may break existing flows, contracts, dependencies, or adjacent behavior.
Primary focus
Regression risk caused by the supplied change
Assess direct impact, adjacent impact, interface or contract risk, dependency risk, configuration risk, and regression-sensitive behavior paths.
Supporting evidence only
Existing tests may support the risk review
Use supplied tests only as optional supporting evidence. Do not turn this workflow into a test-coverage review or claim coverage without supplied test evidence.
Use another workflow when
The task is coverage, generation, patching, or planning
Use a separate workflow for test coverage review, test generation, code writing, patch creation, or changeset planning.
Inputs required
Provide the supplied change and the changed material. Optional module, API, schema, configuration, dependency, integration, runtime, or test context may support the review, but the prompt must not invent missing project state.
Change summary
What changed, why it changed, and which behavior, API, schema, configuration, dependency, integration, or runtime area may be affected.
Changed files or excerpts
The relevant code, configuration, schema, API contract, dependency, integration, or runtime-behavior excerpts needed to assess regression risk.
Copy-ready prompt
Copy the prompt and replace the MATERIALS block with the supplied change, changed files or excerpts, and any optional context.
Run a regression-risk review for the supplied change.
TASK:
Identify behavior, interfaces, flows, dependencies, contracts, configuration, and adjacent paths that may regress because of the supplied change.
SCOPE:
Assess regression risk caused by the supplied change.
Separate direct impact from adjacent impact.
Use existing tests only as optional supporting evidence.
Do not perform a test coverage review.
EVIDENCE RULES:
Base findings only on the supplied materials.
Do not invent architecture, dependencies, runtime behavior, logs, coverage, test results, defects, or pass/fail status.
If the supplied change is not specific enough to assess risk, write INSUFFICIENT_EVIDENCE.
RISK LENSES:
- changed behavior
- directly affected interfaces
- adjacent flows
- contracts / schemas / API boundaries
- dependency and integration points
- shared state
- configuration or runtime behavior
- backward compatibility
- authorization or permission boundaries
- error handling
- data shape or validation
OUTPUT:
A) Change snapshot
B) Directly affected behavior
C) Potentially affected adjacent behavior
D) Regression-sensitive paths
E) Interface / contract / dependency risks
F) Risk-prioritized verification focus areas
G) Missing evidence
H) Out-of-scope requests
I) Confidence
FORBIDDEN:
- do not claim test coverage unless test evidence is supplied
MATERIALS:
"""
Replace this block with:
- change summary
- changed files or excerpts
- affected modules, APIs, schemas, configuration, or runtime settings, if available
- dependency or integration context, if available
- known production constraints, if available
- existing tests, only as supporting evidence, if supplied
"""
Use this as a runtime regression-risk review prompt
Paste the supplied change and relevant technical context into the prompt. Keep stable no-fabrication and project-specific rules in the instruction layer when needed.