Skip to main content

vulkro ctx

Read code for any AI coding agent that can run a shell command: each answer is just the code that answers the question, as numbered lines.

vulkro ctx read FILE            # small file whole, large file as an outline
vulkro ctx read FILE:NAME       # one declaration (FILE:Type.method works)
vulkro ctx read FILE:120-180    # a line range
vulkro ctx search NAME          # every definition, call and use, with code
vulkro ctx body NAME            # one function plus the lines that call it
vulkro ctx impact NAME          # everything that depends on NAME
vulkro ctx map                  # the most central functions, for orientation
vulkro ctx check                # after an edit: what it broke
vulkro ctx init                 # tell the repo's agents to use these

callers and callees list a symbol's direct callers and callees. The graph commands use a background server per repository that starts on first use, listens only on a local socket and exits after 15 idle minutes (serve, stop, status manage it; --no-server skips it). Everything is offline and read-only.

vulkro ctx check​

Compares the working tree with HEAD and reports call sites still on an old signature, removed names still in use, what depends on the change, the tests to run, and security findings on the changed lines. It exits 1 when it finds a problem. vulkro install-hook --pre-commit runs it on every commit.

FlagDescription
--base <REF>Check REF...HEAD instead of the working tree.
--stagedCheck only staged changes.
--fastSkip the security scan.

vulkro ctx init​

Adds a short block to AGENTS.md and to any agent instruction file the repo already has. --agents picks files: agents, claude, gemini, copilot, cursor (comma-separated). Running it again updates the block in place.

search --lines prints locations only.

Exit codes​

0 answered, 1 check found problems, 2 error (unknown file or symbol, IO).

See also: vulkro mcp serve (the read_code and check_change tools).

Last updated on