Add a feature to an unfamiliar codebase
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 agent.
Methods
Add a feature to an unfamiliar codebase
Steps
- Before changing anything, ask the agent to walk you through the part of the code you will touch: the components, routes and services involved and the data flow. Follow up on gaps, such as where a calculation happens and where the new behavior would plug in.
- Switch to plan mode and have the agent outline the feature as an approach and a task list. Trim anything too large for a first release, keep the core flow, then build it.
- If a test still fails after the build, ask the agent to find the root cause of the failure rather than patch the symptom, and ask it to display the old and new values it computes at every stage.
- Have the agent review your whole change for bugs, gaps in error handling, unusual inputs and fit with the existing code. Where cloud agents are available, launch some to probe unusual cases you did not think of.
- Write what you learned into a rule file so the agent follows it next time, for example the order in which discounts should be applied.
- The source walks through adding discount codes to a checkout flow and ends by asking what to do first when a teammate wants gift cards next: explore and plan again.
Run this method with your agent
Download .mdCopied 0
--- name: "add-a-feature-to-an-unfamiliar-codebase-method" description: "Use when you need to Add a feature to an unfamiliar codebase. Add a feature to an unfamiliar codebase" --- # Add a feature to an unfamiliar codebase Job: [Add a feature to an unfamiliar codebase](https://aiagents.org/canai/add-a-feature-to-an-unfamiliar-codebase) ## Need - ai agent: [Cursor](https://aiagents.org/agents/cursor) ## Steps 1. Before changing anything, ask the agent to walk you through the part of the code you will touch: the components, routes and services involved and the data flow. Follow up on gaps, such as where a calculation happens and where the new behavior would plug in. 2. Switch to plan mode and have the agent outline the feature as an approach and a task list. Trim anything too large for a first release, keep the core flow, then build it. 3. If a test still fails after the build, ask the agent to find the root cause of the failure rather than patch the symptom, and ask it to display the old and new values it computes at every stage. 4. Have the agent review your whole change for bugs, gaps in error handling, unusual inputs and fit with the existing code. Where cloud agents are available, launch some to probe unusual cases you did not think of. 5. Write what you learned into a rule file so the agent follows it next time, for example the order in which discounts should be applied. 6. The source walks through adding discount codes to a checkout flow and ends by asking what to do first when a teammate wants gift cards next: explore and plan again. ## Credit Method author Cursor Source: https://cursor.com/learn/putting-it-together
No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/add-a-feature-to-an-unfamiliar-codebase - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "add-a-feature-to-an-unfamiliar-codebase",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}