hexum_shrink
Last updated 29 August 2026
When to call
Before reading a repo or a wide file set.
Arguments
files as path+content blobs, and/or paths.
Optional: user_prompt, active_file, stderr, max_token_budget.
What comes back
A smaller view of those files, plus token counts for the call.
Example
{
"name": "hexum_shrink",
"arguments": {
"files": [{ "path": "src/ui/App.tsx", "content": "…" }]
}
} What the agent does next
Read that view. Do not dump the originals into the prompt.
All five tools: Hexum MCP tools. Contract file: architecture.hexum.
FAQ
What is hexum_shrink?
The model is sent this turn, not the whole tree. Token counts come back on the call so /app can show usage.
When should the agent call hexum_shrink?
Before reading a repo or a wide file set.
Does Hexum replace Cursor or Claude Code?
No. Hexum is a hosted MCP server. You keep Cursor, Claude Code, Antigravity, Codex, or Grok. Hexum is not an IDE and not a model.
Is hexum_check an LLM?
No. hexum_check is deterministic. It maps files to layers in architecture.hexum and reports forbidden imports. It does not call a model.
Does Hexum store my repo?
No. Zero Data Retention is on Usage and Teams. MCP payloads are not stored. Hexum does not train on your code. Policy: /zdr.