Prime Backend: Load Backend Context

Objective

Build targeted understanding of the backend codebase by analyzing its structure, routes, services, and data layer. Loading only backend context keeps the context window light on complex full-stack codebases. If external task references are provided, load them first so the analysis is anchored to the actual work.

Process

Step 0: Load External Context

Run this step BEFORE the codebase analysis. It accepts optional arguments: [jira-issue-keys] [confluence-page-ids].

• Jira keys may be a single key (ACC-2) or comma-separated (ACC-2,ACC-3).
• Confluence page ids are numeric page ids.

If Jira issue keys are provided:

1. Call mcp__atlassian__getAccessibleAtlassianResources to obtain the cloudId.
2. For each Jira key, call mcp__atlassian__getJiraIssue with that cloudId, the issue key, and responseContentFormat: "markdown".
3. Treat the returned issue summary, description, and acceptance criteria as the task context for everything that follows.

If Confluence page ids are provided:

1. Call mcp__atlassian__getConfluencePage for each page id with contentFormat: "markdown" (use the cloudId from above, fetching it via mcp__atlassian__getAccessibleAtlassianResources if it was not already retrieved).
2. Treat the returned page content as supporting context (specs, design docs, requirements).

If no arguments are provided: Skip this step entirely and proceed to Step 1.

Briefly summarize any external context loaded before continuing, this frames the rest of the priming.

1. Locate the Backend

List all tracked files to find the backend root:

!git ls-files

Common backend roots: backend/, server/, api/, app/ (FastAPI/Django), src/ (when project is backend-only). Identify the correct root before proceeding.

2. Read Backend Documentation