Agentic Coding & AI Dev Tools5.0 · 0 ratings
Codebase Onboarding Exploration Plan
Gives an agent a structured exploration plan to understand an unfamiliar repo before making changes.
Step-by-StepRole-Based
Prompt
You are a Tech Lead writing an exploration plan for an AI agent newly dropped into the unfamiliar repository [REPO_NAME]. The agent must build a mental model before editing anything. Context: Goal of the eventual change: [EVENTUAL_GOAL]. Known entry points: [ENTRY_POINTS_OR_UNKNOWN]. The agent can read files, run search, and execute read-only commands. Task steps: 1. Identify the top-level structure and likely architectural pattern. 2. Locate the entry point, config, and where core business logic lives. 3. Map the data flow for the feature area touching [EVENTUAL_GOAL]. 4. List the tests covering that area and how to run them. 5. Produce a one-paragraph mental model and a list of open questions. Output format: ### Repo Map (key dirs and their roles) ### Architecture Pattern (inferred + evidence) ### Data Flow for Target Area ### Relevant Tests & Run Commands ### Mental Model Summary ### Open Questions Constraints: Read before concluding; cite file paths as evidence. Make no edits in this phase. Mark every inference as confirmed or assumed.
Recommended models
claudegpt-4ogemini
More in Agentic Coding & AI Dev Tools
Autonomous Coding Agent Task Scoping Brief
Turns a vague feature request into a bounded, verifiable task brief an autonomous coding agent can execute safely.
Read prompt
ReAct Loop Debugging Trace Analyzer
Diagnoses why an agent's ReAct (reason-act-observe) loop stalls, repeats, or hallucinates tool calls.
Read prompt
MCP Server Tool Specification Designer
Designs a clean, well-documented Model Context Protocol tool set with names, schemas, and guardrails.
Read prompt
Pull Request Review Agent Persona
Configures an AI reviewer that comments on diffs with severity-tagged, actionable, non-nitpicky feedback.
Read prompt