Skip to content

Evidence

The maintainer’s own projects.

These figures are observed use and co-movement. They are not a controlled study, and nothing here claims fewer repeated failures.

Tool use

4 August to 10 October 2026 UTC.

OpenState tool uses in OpenCode35,579
Structural tool uses30,782
AST searches10,420
Text edit previews8,102
Text edit applies6,694
Bounded text-region reads2,467
Sessions that used it243
Projects20
Store records (10 October)82,586
Resume capsule sizemedian about 500, at most about 1,600 tokens

Direct calls count once; a Code Mode program using a tool counts once for that tool. The named structural categories are a subset of the structural total. Method and evidence on GitHub →

Reads

A definition is a small part of its file.

These are bytes returned per read in the maintainer’s sessions. How small a definition is next to its file depends on the code, and a careful agent can also read a range of lines.

Completion cost

Observed co-movement, not a controlled study.

In the maintainer’s OpenCode history, tokens per completed work item in the openstate project fell from about 16M to 10.6M (34%) and per commit from 16.0M to 11.05M (31%) between August and September 2026 while completions rose. A repo adopting the tools via Claude Code fell from 14.3M to 0.9M per commit. Non-adopting repos were flat or worse except one that improved in a lighter work phase.

No measurement yet shows fewer repeated failures. What OpenState guarantees is the record and its delivery to the agent.