Tools

Last updated 29 August 2026

ToolWhenWhat comes backNext
hexum_skillFirst Hexum use this session if SKILL.md is missing, or when intensity changes.Skill file body, write path, whether to update architecture.hexum.Write body to path if missing. Follow that file.
hexum_shrinkBefore reading a repo or a wide file set.A smaller view of those files, plus token counts for the call.Read that view. Do not dump the originals into the prompt.
hexum_expandWhen one folded function, class, or method is the thing to patch.The full source of that symbol.Edit from that body. Do not expand the whole file just in case.
hexum_spliceWhen applying the patch.The updated region, still valid source.Keep the write small: one symbol or one line. You keep Git.
hexum_checkBefore claiming the turn is done.healthy, drift_detected, or ARCHITECTURE_CONFIG_MISSING, plus violations.On drift, follow hint and check again. Do not ship a red check.

FAQ

How does Hexum reduce tokens?

The agent calls hexum_shrink before it reads widely. The model is sent this turn, not the repository. On MBPP, measured context dropped about 85% with the same tests passing. Example turn: 18.2k → 3.1k tokens, 41 files → 6. See /benchmarks and /methodology.

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.

What is Hexum?

Hexum is an MCP server for Cursor, Claude Code, and other coding agents. It sits between the agent and the model: hexum_shrink sends this turn instead of the repository, hexum_check fails the turn when architecture.hexum is broken, and you keep your editor. On MBPP, context dropped about 85% with the same tests passing.