- Home
- Skills
- Code Quality & Review
- Change Impact Review
Change Impact Review
Trace code changes through dependencies to identify contract violations and prioritized regression risks.
$2.99
Works with the AI Agents you already use
Change Impact Review
Example session with this skill installed
Review the impact of changing the calculateTax function in src/finance/calculator.ts where we updated the return type from number to TaxResult object.
- Read your context and instructions
- Compiled the change impact review
I have reviewed the change in src/finance/calculator.ts. The transition from a primitive number to a TaxResult object creates several immediate contract violations in the invoicing module.
Change Impact Report
1. Decision Summary
Status: High Risk.
The change breaks the primary calculation contract used by the PDF generator and the checkout API. Immediate refactoring of three callers is required.
2. Prioritized Findings
| Priority | Finding | Impact | Evidence |
|---|---|---|---|
| High | Type Mismatch in InvoicingService | Runtime crash during PDF generation | src/invoice/generator.ts:142 expects a number for total_tax |
| High | Broken API Response | Checkout payload now returns nested object instead of float | src/api/checkout.ts:88 passes raw return to JSON response |
| Med | Test Regression | tax_calc_test.spec.ts uses .toBeLessThan() which fails on objects | tests/finance/tax_calc_test.spec.ts:22 |
3. Dependency & Contract Map
src/finance/calculator.ts(Provider)src/invoice/generator.ts(Consumer: Broken)src/api/checkout.ts(Consumer: Broken)src/reports/eoy_summary.ts(Consumer: Status Unknown - File not provided)
4. Regression Matrix
| Target | Triggering Condition | Expected Behavior |
|---|---|---|
| PDF Generation | Run generateInvoice(orderId) | Property accessor must use .value or .amount |
| API Checkout | POST /v1/checkout | Ensure legacy clients receive flattened numeric value |
| Unit Tests | Run npm test finance/ | Update assertions to validate TaxResult schema |
Next steps
- Provide
src/reports/eoy_summary.tsto check if end-of-year reports are also impacted. - Update the
InvoicingServiceto destructure theTaxResultobject. - Implement a legacy wrapper for the Checkout API to maintain backward compatibility.
Connects securely to your tools. The creator never sees your data.
About this skill
Code changes often break dependencies in ways that unit tests miss. This skill analyzes diffs against project contracts to identify prioritized regressions and broken callers before they hit production.
What it does
- Diff Analysis parses code changes to identify intended behavior versus accidental contract violations.
- Dependency Mapping traces affected callers, shared types, routes, and data consumers connected to the change.
- Impact Verification links specific code changes to user consequences with concrete evidence.
- Risk Prioritization categorizes findings by consequence and reach, distinguishing between code-level contradictions and plausible risks.
- Regression Planning generates a targeted matrix of checks to verify the fix and prevent future regressions.
How it works
- Supply the diff, head/base revisions, or the specific changed files to be reviewed.
- The skill traces implementation details to affected callers and shared data contracts.
- It evaluates findings based on triggering conditions and user consequences.
- It delivers a prioritized report including a dependency map and regression matrix.
Frameworks & tools
This skill is language-agnostic and works with any codebase where diffs and source files are available. It is particularly effective for systems with complex internal APIs, shared types, or strict data contracts.
Why this beats prompting it yourself
Standard prompts often hallucinate side effects or miss deep dependency chains. This skill follows a rigorous evidence-based workflow that requires a concrete trace from change to consequence, preventing "finding fatigue" from hypothetical or trivial issues.
Use cases
- Reviewing PRs for breaking changes in shared library functions or internal APIs.
- Assessing the impact of database schema migrations on existing data consumers.
- Validating type definition changes across large monorepos.
- Generating focused manual QA scripts for high-risk logic updates.
Known limitations
Does not execute tests or perform runtime analysis. Requires access to caller files to provide complete dependency coverage. Findings are limited to supplied artifacts.
Cannot execute code or tests. Dependency coverage is labeled incomplete if only changed files are provided without surrounding context or caller files.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 10 days ago