I.A rational operator for context

Open source / provider-neutral core / evidence-gated claims

Spend context on the work, not the workflow.

STOLZ A.I. is a set of five focused skills that selects the smallest sufficient route, loads context only when needed, reuses verified results, and keeps unchanged state outside the model — without lowering the bar for correctness.

Open the repository See the route
Surface
5 scoped skills
License
MIT
Claim policy
Evidence first
stolz.route / 01verified route
  1. 01routesmallest sufficient pathpass
  2. 02contextrequired sources onlypass
  3. 03reuseidentity-matched resultpass
  4. 04verifyoutcome gate preservedpass

§ 1No numerical savings claim without paired evidence.

The literary source is part of the product idea

Andrei Ivanovich. Artificial Intelligence.

In Goncharov's novel, Stolz is active, educated, practical, and systematic — a counterweight to inertia. STOLZ A.I. translates that character into agent engineering: plan before loading, act without fuss, and spend resources only where they move the task forward.

«Движений лишних у него не было» — “He made no unnecessary movements.”

Ivan Goncharov, Oblomov, part II

III.Five skills, one discipline

Install only what the route needs

A small system for the waste around agent work.

Each skill has a narrow trigger and a safe fallback. STOLZ A.I. is not a catch-all prompt and does not replace the model, the runtime, or project-specific verification.

01

stolz-route

Chooses one smallest sufficient route and falls back safely when capabilities are missing.

decide
02

stolz-context

Validates the route manifest, then loads only immutable, route-required context.

load
03

stolz-reuse

Reuses a result only when its identity and verification still match the task.

reuse
04

stolz-quiet-state

Keeps unchanged polls outside model narration and reports material transitions.

observe
05

stolz-benchmark

Accepts an efficiency comparison only after outcome and verification gates pass.

prove

IV.Smallest sufficient route

Keep the outcome. Edit the waste.

The red editor's line does not cross out reasoning or verification. It crosses out work that adds no new information: broad reads, duplicate commands, stale results, and narration of unchanged state.

Unmanaged routeSTOLZ route
Load the whole repositoryLoad the manifest and required sources
Repeat a verified readReuse only with matching identity
Narrate every unchanged pollReport material transitions
Celebrate a lower countCompare only equivalent verified outcomes

V.The claim has a gate

Fewer tokens are not a win if the result is weaker.

A published saving requires paired baseline and optimized runs on the same versioned fixture, equivalent required outcomes, and passing verification for both routes.

Read the benchmark report
  1. 01
    Same fixture

    Baseline and optimized routes receive the same versioned task.

    required
  2. 02
    Equivalent outcome

    Both routes must satisfy the same required result.

    required
  3. 03
    Verification passes

    A lower count with failed checks is rejected.

    required
  4. 04
    Only then compare

    Record the measured delta and its evidence boundary.

    compare

VI.Compatibility without borrowed authority

Provider-neutral core. Explicit evidence boundary.

SurfaceCurrent statusMeaning
Codex localC0 / C1

Fixture and CLI certification are available.

Claude CodeC0 / C1

Adapter and isolated profiles are included.

Qwen CodeC0 / C1

Adapter and isolated profiles are included.

Provider overlaysC2 / C3 — withheld

Declarative selection is not provider-call or savings certification.

VII.Start with the route

Inspect, test, then install the skill you need.

Clone a tagged or reviewed revision, run the test suite, and start with `stolz-route` unless the task already has one clear concern.

Open GitHub Installation guide
terminal / install
$ git clone https://github.com/Sergey360/stolz-ai.git
$ cd stolz-ai
$ npm install
$ npm test
✓ verified before install

VIII.Reader's notes

Questions worth asking before adoption.

Does STOLZ A.I. make the model think less?

No. It targets waste around reasoning: unnecessary context, repeated operations, stale reuse, noisy monitoring, and ungated comparisons.

How many tokens will it save?

There is no provider-wide percentage claim. Savings depend on the task, runtime, fixture, and route. STOLZ A.I. publishes a number only with paired evidence and equivalent verified outcomes.

Is it only for Codex?

The core contracts are provider-neutral. Current C0/C1 support includes Codex local, Claude Code, and Qwen Code; stronger provider claims remain withheld where evidence is missing.

Why is the literary reference important?

The character defines the product ethic: educated action, planning, resource discipline, and movement toward a concrete result — not saving at any cost.