Engineering Edition

Verify every refactor
your agent makes.

An agent edit you can't classify is a guess you're merging. The Engineering tier is the safety net: every change checked and receipted — contract, effects, behavior — across 138 grammars, in any MCP agent. And it answers in one call instead of a dozen file reads.

What you get

Free to understand. A safety net you can trust.

Builder Edition, free, forever for non-commercial projects.

unsafe_surface, effect_summary, data_flow across 138 grammars.

Engineering Edition — the safety net.

The verify_* suite — every refactor your agent runs comes with a receipt that proves contract, effects, and behavior survived.

Works with anything that speaks MCP.

Claude Code, Cursor, Cline, Codex, your own Agent SDK build.

Sample receipt

A receipt that proves behavior survived.

What verify_contract_preserved returns for a single change — the hunk classified, each contract dimension checked, the effect delta named.

verify_contract_preserved · src/orders.ts → applyDiscount
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.

The side effect

And it runs leaner, too.

Without act101

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 tokens

With act101

One effect_closure MCP call returns the transitive effect signature, frontier, and call sites. ~3K tokens. 27× less.

~3K tokens

A clean context window isn't just cheaper — an agent that isn't drowning in file reads reasons better and writes better code.

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.

The toolkit

Everything in the kit.

Builder Edition — 138 grammars
effect_summary data_flow unsafe_surface
Engineering Edition — the safety net
secret_surface verify_side_effects verify_contract_preserved verify_diff_semantics verify_test_impact generate_test_harness summarize_pr /verify-refactor /safe-to-merge /refactor-receipt

Download act101

One native binary, every grammar, zero setup. Builder Edition is free.

Download — install in 60s

Stay in the loop

Ship notes and new capabilities, occasionally. No spam; unsubscribe anytime.