From supp
Read source files with dependency context — use INSTEAD OF the Read tool when you need file contents plus imports/exports/dependency graph. TRIGGER when: you need to read, view, or understand any source code file (.rs, .py, .js, .ts, .go, .c, .cpp, .java, etc.), before editing a source file, or when the user asks to look at code. DO NOT TRIGGER when: reading non-code files (.toml, .json, .md, .yaml, .lock, .txt, .env)
How this skill is triggered — by the user, by Claude, or both
Slash command
/supp:ctxThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run the following command and show the user the output:
Run the following command and show the user the output:
supp --json $ARGUMENTS
--map (or -m) for just signatures and type definitions — useful for scanning large directories--slim to strip comments and collapse blanks for a compact view--budget <tokens> to auto-fit context within a token limit — supp picks per-file compression (full/slim/map) to maximize signal within the budget/sym — it searches definitions across the project/why/tree/diffnpx claudepluginhub andrewpberg/supp --plugin suppReplaces cat/head/tail/ls/tree/find with AST-aware file reading via tilth MCP. Shows file contents, directory listings, line ranges, and dependencies without shell fallbacks.
Builds a mental model of unfamiliar codebases by searching, reading dependencies, and checking git history. Use when onboarding or before editing unknown code.
Token-optimized structural code search using tree-sitter AST parsing. Use instead of reading full files to understand code structure, find functions, or explore a codebase efficiently.