Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From mimirs
Builds a mental model of unfamiliar codebases by searching, reading dependencies, and checking git history. Use when onboarding or before editing unknown code.
npx claudepluginhub thewinci/mimirs --plugin mimirsHow this skill is triggered — by the user, by Claude, or both
Slash command
/mimirs:exploreThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Goal: understand the area from real source before touching it. Prefer the mimirs tools over `grep` + reading whole files.
Explores codebase areas: maps files, traces data flows, identifies patterns and dependencies. For 'how does X work', architecture queries, or pre-change analysis.
Read-only codebase exploration for discovering architecture, patterns, tooling, and dependencies. Use before implementing features, fixes, or refactors to understand existing code, trace symbols, and map files.
Produces evidence-cited maps of unfamiliar codebase areas with file:line references for every claim. Use before non-trivial changes, onboarding, or multi-module refactors.
Share bugs, ideas, or general feedback.
Goal: understand the area from real source before touching it. Prefer the mimirs tools over grep + reading whole files.
search "<topic>" for ranked files, then read_relevant "<topic>" to pull the actual functions/sections with line ranges (not just paths). Two chunks from one file can both appear.project_map(focus: <key file>) for its neighborhood; dependents <file> for who relies on it; depends_on <file> for what it pulls in.read_relevant "<specific behavior>" on the key files; follow the helper calls a named file delegates to.git_context for what changed recently; file_history <file> for how a file evolved; search_commits "<topic>" for why past decisions were made.search_conversation "<topic>" and search_checkpoints "<topic>" for earlier discussion and decisions, so you don't re-derive what's already known.get_annotations on the key files for known bugs, fragile spots, or constraints before trusting the code.Finish: summarize in plain language — entry points, key files, data flow, gotchas — each with a file:line citation. Flag anything still unclear instead of guessing.