hexum_shrink

Last updated 12 September 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. You keep Cursor, Claude Code, Antigravity, Codex, or Grok. Hexum is not an editor and not a model. You paste a key into the agent you already use.

Does the architecture check use an AI?

No. It reads a rules file in your repo and reports forbidden imports. It does not call a model, so it does not guess.

Does Hexum store my repo?

No. We do not keep the code your agent sends. We do not train on it. Policy: /zdr.