ask
Ask a codebase question and get a cited, synthesised answer with a confidence rating (costs an LLM call).
Why the code is shaped this way — decisions, rationale, and git archaeology (question, path, or decision-health dashboard).
> /plugin marketplace add repowise-dev/repowise > /plugin install repowise@repowise
How it fires
How this command gets triggered: by you, by Claude, or both.
/whyContext preview
What this command does when you run it.
Why the code is shaped this way — decisions, rationale, and git archaeology (question, path, or decision-health dashboard).
description: Why the code is shaped this way — decisions, rationale, and git archaeology (question, path, or decision-health dashboard). allowed-tools: Bash, Read
Answer *why* the code looks the way it does: decision records, rationale, and git archaeology. This is the CLI adapter over `get_why`. Worth running before a refactor or a deliberate divergence from a pattern.
`/repowise:decision` manages decision records (list / add / confirm). This command **queries** why something is shaped a certain way.
1. If `.repowise/` doesn't exist: "This repo isn't indexed yet. Run `/repowise:init` first." Stop. 2. Map `$ARGUMENTS` to a mode (below), run `repowise why`, and present decisions, alignment, and archaeology. Never invent rationale — if the command falls back to git archaeology, say that plainly.
(`--target` is repeatable)
like passing the path, several get a card each
proposed / ungoverned hotspots)
repowise why "why is auth using JWT?" repowise why src/api/auth.py repowise why "why the retry cap?" --target src/api/client.py repowise why
Shared targeting flags (`--path`, `--repo`, `--no-workspace`) match the other tool-adapter commands.
never empty — call that out so the user knows it is reconstructed, not recorded.
sentence on why, and a pointer to the tool that fits the question's shape. Relay the redirect rather than filling the gap: an empty result there means the decision store has nothing, not that the question is unanswerable.
`/repowise:decision`.
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Repo: repowise-dev/repowise
Ask a codebase question and get a cited, synthesised answer with a confidence rating (costs an LLM call).
Triage card for files, modules, or symbols — layer, hotspot, fix history, freshness (relationships, not source bytes).
Ingest or inspect test-coverage reports — LCOV, Cobertura/Clover, or coverage.py .coverage (builds the per-test map when contexts are present).
Report unreachable files, unused exports, and zombie packages, tiered by confidence.
Work with architectural decisions — list, inspect health, add, or confirm auto-proposed decisions.
Diagnose the Repowise setup — install, API keys, index/store drift — and optionally repair it.