Semantic answers in one MCP call instead of letting the agent read your repo to guess — across 138 grammars. The Engineering tier adds the safety net that verifies every change the agent makes.
Ask your agent "is this function safe to delete?" It greps, reads 12 files looking for callers, opens 4 more to check effects. ~80K input tokens, per task.
~80K tokensOne effect_closure MCP call returns the transitive effect
signature, frontier, and call sites. ~3K tokens. 27× less.
Twenty of those a day is real money back in your Claude bill — every working day.
Per-task figures above are measured from our agent-task benchmark. For aggregate savings across 10 operations, see the 166-sample savings benchmark — median 85% fewer tokens.
unsafe_surface, effect_summary, data_flow across 138 grammars.
The verify_* suite — every refactor your agent runs comes with a receipt that proves contract, effects, and behavior survived.
Claude Code, Cursor, Cline, Codex, your own Agent SDK build.
What verify_contract_preserved returns for a single change — the hunk classified, each contract dimension checked, the effect delta named.
hunk Behavior (not Rename / Move / Signature / Format) contract Preserved ├─ control preserved same branch / loop / return shape ├─ raises preserved {ValidationError} unchanged ├─ guards changed added: qty > 0 (new precondition) └─ effects preserved reads:[cart] writes:[] — no new I/O verdict review 1 dimension changed — surfaced, not blocked
A representative verify_contract_preserved receipt.
One native binary, every grammar, zero setup. Builder Edition is free.
Download — install in 60sShip notes and new capabilities, occasionally. No spam; unsubscribe anytime.
Architectural concerns? Tools for tech leadership → /for/architects.