From justokenmax
Queries a lightweight symbol index to find function, class, or method definitions by name, returning file:line and signature without reading entire files.
How this skill is triggered — by the user, by Claude, or both
Slash command
/justokenmax:code-indexThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Reading entire files to find one function is the biggest avoidable input cost in
Reading entire files to find one function is the biggest avoidable input cost in a coding session. jusTokenMax keeps a lightweight symbol index of the repo so you can jump straight to a definition.
Before grepping or reading files to find where something lives, query the index:
justokenmax query parse_config # substring match on symbol name
justokenmax query Engine --kind class # filter by kind (func|class|method|...)
justokenmax query render --limit 10
Each hit is file:line [kind] signature — docstring. Read just that line
range; don't open the whole file.
justokenmax index # index the current repo -> .justokenmax/index.json
justokenmax index path/to/repo
Python is parsed precisely (via ast: functions, classes, methods, signatures,
docstrings); JS/TS/Go/Rust/Java/Ruby/C++ use fast regex heuristics. Re-run
justokenmax index after substantial code changes — the index is a snapshot, not
live. If a query says the index is missing, build it first.
Fallback if justokenmax isn't on PATH: python3 -m justokenmax query <term> /
python3 -m justokenmax index with the plugin's python/ dir on PYTHONPATH.
For exact-string or regex searches across file contents (not symbol names), plain grep is still right. The index is for "where is this symbol defined?".
npx claudepluginhub kalmantic/justokenmax --plugin justokenmaxNavigates codebases using .codemap/ structural indexes to find symbol definitions (classes, functions, methods), explore file structures, and locate code by name. Enables targeted line-range reads to reduce token consumption.
Searches indexed code structures to find definitions, references, callers, call graphs, implementations, dependents, and file outlines without opening files, reducing token usage vs grep or reading source.
Guides token-efficient code navigation using ctags index to find symbol definitions and references instead of broad grep searches.