codebase-exploration
Use when exploring, understanding, or answering questions about a Repowise-indexed codebase, including architecture, where code is implemented, how a module works, or which files are relevant before reading source.
How do I install this agent skill?
npx skills add https://github.com/repowise-dev/repowise --skill codebase-explorationIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill provides documentation for using Repowise MCP tools to explore and analyze codebases. It outlines standard workflows for codebase orientation, searching symbols, and assessing change risks. No malicious patterns, obfuscation, or unauthorized data access behaviors were detected.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Codebase Exploration with Repowise
This project has a Repowise intelligence layer. For an exact identifier, string or file name, Grep, Glob and Read are faster. For how code works, who calls it, what a change breaks and why it is shaped this way, reach for the Repowise MCP tools: they return documentation, ownership, history, decisions, and graph structure that plain file reads don't, usually in one round-trip instead of many.
Which tool for which question
| You want… | Call |
|---|---|
| An exact identifier, string or file name | Grep, Glob and Read. |
| First orientation in an unfamiliar repo | get_answer(question="what are the main modules and entry points?"). For the full map (architecture, git health, knowledge map), add +get_overview to mcp.tools in .repowise/config.yaml and restart the MCP server. |
| How X works or flows end to end | get_answer(question="how does …"), one question per call: synthesised answer with citations + one confidence trust signal. Collapses the search → read → reason loop. |
| Callers before a rename or signature change | get_context(targets=["<symbol>"], include=["references"]): definition, imports and calls; a complete list is the whole edit set. |
| What breaks if X changes | repowise risk --target <file>. |
| Why X is shaped this way, before changing a pattern | get_why(query="why …", targets=["<file>"]). |
| Before finishing a multi-file change | repowise risk <base>..HEAD, then repowise health --score <file you touched> --against <base>. |
A fuzzy concept, or symbol ids and line bounds to feed get_symbol | search_codebase(query="…"): hybrid search. mode="auto" routes an identifier to indexed symbol hits (symbol_id/line bounds → pipe into get_symbol), a path to file pages (→ get_context), and prose to semantic wiki search (each hit's sources lists what matched it: fts, symbol or vector). Force a branch with mode=symbol|path|concept|hybrid; narrow symbols with symbol_kind. |
| A triage card for specific files/symbols | get_context(targets=[…]): title, summary, signatures, hotspot bit, top callers, decision titles, symbol_ids (a row without one is path::name). Batch many targets in one call. |
| The actual source of one symbol | get_symbol("path/to/file.py::Name"): exact bytes with line bounds. Cheaper than Read + offset math. Use a symbol_id from get_context. |
Recommended flow
- New area you don't know → one orientation
get_answercall. - A specific question →
get_answer(question=…)first.- High confidence → answer it, cite the paths.
medium/lowconfidence → followbest_guesses[0].fileorfallback_targets[0]intoget_context, thenget_symbolfor bytes.
- A named symbol or a path you only need to find → Grep, Glob or Read. When
you need its callers or history, pass it to
get_contextorget_whyinstead; for its risk,repowise risk --target <path>. - More files around a concept →
search_codebase, thenget_contexton the hits (batched), thenget_symbolonly for the bodies you actually need.
Read source directly for details the indexed context doesn't cover.
Trust signals — verify when
_meta.stale_warningis present (the index has diverged from HEAD), orconfidenceismedium/low, or- a concept result's
sourcesis onlyfts(a keyword match, no semantic hit).
Otherwise the response is current — act on it.
Error handling
- "No repositories found. Run 'repowise init' first." → suggest
/prompts:repowise-init. Add--no-editor-setupif this repo is a scratch clone, a fixture, or a worktree, soinitwrites nothing outside.repowise/(no editor config, agent hooks or git hook). - MCP tools unavailable → prefer the matching CLI slash commands when the
plugin is installed (
/prompts:repowise-ask,/prompts:repowise-context,/prompts:repowise-symbol,/prompts:repowise-search) rather than grepping blind. get_answer/search_codebasecome back empty → the repo may have a template-rendered wiki. Fall back toget_contextwith explicit paths, and note that model-written pages (repowise generate, or/prompts:repowise-initwith an LLM provider) unlock richer docs + semantic search.- Tools fail to connect at all → the
repowisebinary may not be installed; suggest/prompts:repowise-init.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/repowise-dev/repowise/codebase-exploration">View codebase-exploration on skillZs</a>