CARBON — Engineering ConfidenceUser Guide
CHAPTER 55 / 60 Pro

/carbon-auto

Run a bounded, durable CARBON validation loop over a current change, feature, local app, or URL.

Jay · Your AI test managerTesting operations

When to use it

A bounded repeated check loop fits a changing local feature.

Before you start

Agree on scope, budget and stop conditions. The loop proposes fixes; code mutation and consequential actions need the required scoped approval. A budget stop must retain remaining gaps.

Try this in your coding agent.

/carbon-auto Run a bounded validation loop for src/cart using local tests only.

Replace sample paths with your project. Slash names are shorthand; your host may use a plugin prefix or a skill picker. Invocation help →

ILLUSTRATIVE WALKTHROUGH

Bounded cart validation loop

An expanded teaching example, not a recorded or live execution. The report stays visible while the replay explains how to read it.

  1. 01Assess
  2. 02Check
  3. 03Review
  4. 04Next cycle
  5. 05Budget stop

Coding-agent conversation

Assess

I’m reviewing bounded cart validation loop. I’ll keep the scope and permissions explicit.

Check

Check: Run a bounded validation loop for src/cart using local tests only.

Review

Review: Run a bounded validation loop for src/cart using local tests only.

Next cycle

I’m choosing the next uncovered state transition rather than repeating the same happy path.

Budget stop

The loop stops at its budget and records the remaining gap. Scope, budget and stop controls constrain a real run.

CARBON

Example report

Illustration
Follow the cart state
Follow the cart state — TestBucks teaching screen

TestBucks course screen with illustrative analysis. The screenshot supplies context; the demo does not establish a newly observed bug.

  1. Cart input
  2. Totals & state
  3. Checkout evidence

Illustrated outcome

The loop stops at its budget and records the remaining gap.

Evidence to inspect

Assess change → local check → inspect failure → next check → budget stop.

Still untested / not established

Scope, budget and stop controls constrain a real run.

Ready. Read the full example or play its steps.

What a useful result contains

A bounded claim

For bounded cart validation loop, state the target, revision, environment and actual work performed. Keep planned, executed, blocked and untested work separate.

An inspectable trail

Assess change → local check → inspect failure → next check → budget stop. In a real run, retain the source, trace, screenshot or fixture behind the conclusion.

The qualification

Scope, budget and stop controls constrain a real run.

The next decision

Decide whether the evidence calls for a focused check, a reviewed fix or more context. Do not convert a plausible example into a verified finding.

Adapt the example to your project

  1. Replace bounded cart validation loop with a real feature, path or decision in your project.
  2. State the expected rule and its source. Include safe fixtures, constraints and a budget where appropriate.
  3. Ask for exact evidence and remaining gaps. Approve consequential actions separately.
/jay Review the /carbon-auto result. Separate observed evidence, assumptions and untested scope, then recommend the next useful check.

Where to go next

/carbon-settings →/carbon-full-report →

Content checked against the local command definition: skills/carbon-auto/SKILL.md. Examples adapted from the homepage’s TestBucks walkthroughs. Availability is edition- and host-dependent.