repo-onboarding-maplisted
Install: claude install-skill Contexory/skills
# Repo onboarding map
The question behind "what is this codebase" is almost never "describe every directory". It
is: where does execution start, how do I run it, which parts are alive, and what do I need
to know before I touch anything.
A generated tour that walks the directory tree answers none of those. This one is ordered
by what a newcomer needs first.
## Procedure
### 1. Get the mechanical map
`<skill-dir>` is the directory this SKILL.md was loaded from — the skill installs outside
your project, so its script is named by full path, never relatively.
```
python3 <skill-dir>/scripts/repo_map.py # whole repo
python3 <skill-dir>/scripts/repo_map.py --top 25 # widen the hot-files list
```
The script detects the stack from its manifests, lists workspace packages, extracts the
declared run/test/build commands, finds entry points, ranks files by commit count, and
locates docs and agent-instruction files. It reports what it found, not what it expected
to find — a missing test command is reported as missing rather than guessed.
### 2. Read the instruction files first, if there are any
`AGENTS.md`, `CLAUDE.md`, `CONTRIBUTING.md`, `.cursorrules`. These are the highest-value
files in an unfamiliar repository and newcomers routinely miss them: they encode the
conventions that are not derivable from the code, and they are usually the only written
record of *why* the layout is what it is. Read them before forming any opinion about the
structure.
### 3. Follow the hot