Menu
Use before any implementation to understand the codebase structure, existing patterns, dependency graph, and project conventions.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | repo-exploration |
| description | Use before any implementation to understand the codebase structure, existing patterns, dependency graph, and project conventions. |
Use this skill to build a mental model of the codebase before making changes.
ARCHITECTURE.md if it exists. At minimal profile for single-file Small tasks: skip ARCHITECTURE.md unless it is referenced by the task description or appears to contain non-template content (>50 lines of substantive text).CONTRIBUTING.md or equivalent docs if they exist.Read at least one existing file in each layer you will modify and note:
Before cross-file changes:
project/project-manifest.md for project-local constraints.DECISIONS.md if it exists.After discovery, produce a brief summary:
Modules involved: [list]
Existing patterns: [key observations]
Constraints: [project-specific rules that apply]
Files to read before coding: [list]
Before completing codebase exploration, verify:
project/project-manifest.md and DECISIONS.md were checked for constraintsUse for general product implementation work that is not primarily backend architecture, pure integration wiring, or screenshot-driven design-to-code.
Use when the main deliverable is maintainable documentation such as repository rules, onboarding guides, runbooks, ADRs, or architecture notes.
Use on first entry to a new repository to run environment scanning and ask targeted boundary questions before implementation.
Use after writing or modifying code to enforce the mandatory write → test → fix → repeat validation cycle.
Use before committing to a design or plan to force assumption-surfacing. The agent challenges your design, questions edge cases, and flags gaps — you patch vague decisions. Prevents the failure mode where a design "feels explained" but contains hidden flaws that only appear during implementation.
Use to establish and maintain a shared domain glossary (UBIQUITOUS_LANGUAGE.md). Creates a single source of term definitions that all agents, prompts, and documents must use — preventing semantic drift and repeated re-explanation across sessions.