plugins/ed3d-research-agents/skills/investigating-a-codebase/SKILL.md
Use when planning or designing features and need to understand current codebase state, find existing patterns, or verify assumptions about what exists; when design makes assumptions about file locations, structure, or existing code that need verification - prevents hallucination by grounding plans in reality
npx skillsauth add ed3dai/ed3d-plugins investigating-a-codebaseInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Understand current codebase state to ground planning and design decisions in reality, not assumptions. Find existing patterns, verify design assumptions, and provide definitive answers about what exists and where.
Use for:
Don't use for:
Do not use nested subagents. If you are running as a research subagent, perform the investigation directly with Read/Glob/Grep and any other tools already available to you. Do not dispatch or invoke additional subagents.
When given design assumptions to verify:
Why this matters: Prevents implementation plans based on wrong assumptions about codebase structure.
| Task | Strategy | |------|----------| | Where is X | Glob likely names → Grep keywords → Read matches | | How does X work | Find entry point → Follow imports → Read implementation | | What patterns exist | Find examples → Compare implementations → Extract conventions | | Does X exist | Multiple searches → Definitive yes/no → Evidence | | Verify assumptions | Extract claims → Search each → Compare reality vs expectation |
Multiple search approaches:
Don't stop at first result:
Verify everything:
Lead with direct answer:
Provide actionable intelligence:
Handle "not found" confidently:
| Mistake | Fix | |---------|-----| | Assuming file locations | Always verify with Read/Glob before reporting | | Stopping at first result | Explore multiple paths to verify findings | | Vague locations ("in auth folder") | Exact paths (src/auth/index.ts:42) | | Not documenting search strategy | Explain what was checked when reporting "not found" | | Confusing "not found" types | Distinguish "doesn't exist" from "couldn't locate" | | Skipping design assumption comparison | Explicitly report: confirmed/discrepancy/addition/missing | | Reporting assumptions as facts | Only report what was verified in codebase |
development
Use when the user wants to review a Claude Code session for quality — analyzes the current session (or a specified transcript path) for prompting effectiveness, agent performance, and environment gaps, producing actionable recommendations
development
Use when the user wants to review their recent Claude Code sessions for patterns — analyzes the last N sessions (default 5) in the current project, dispatching parallel reviewers per session, then synthesizing cross-session findings
tools
Use when the user wants to export a Claude Code session transcript as a readable Markdown file — converts the current session (or a specified transcript path) into GitHub-flavored Markdown with metadata header, collapsible tool results, and thinking blocks
development
Use when planning features and need current API docs, library patterns, or external knowledge; when testing hypotheses about technology choices or claims; when verifying assumptions before design decisions - gathers well-sourced, current information from the internet to inform technical decisions