CARBON — Engineering ConfidenceUser Guide
CHAPTER 57 / 60 Pro

/carbon-forever

Continuously expand test coverage and investigate bugs until stopped or an optional limit is reached.

Jay · Your AI test managerTesting operations

When to use it

You explicitly want ongoing discovery across successive coverage gaps.

Before you start

Two separate confirmations precede start or resume. Use optional time/cycle limits and inspect checkpoints. The host performs the work; the report is not a daemon that continues after quota or session interruption.

Try this in your coding agent.

/carbon-forever Keep investigating the disposable demo until I stop you; stay within that project.

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

Continuous disposable-demo investigation

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

  1. 01Scope
  2. 02First cycle
  3. 03Next gap
  4. 04Next cycle
  5. 05Stop

Coding-agent conversation

Scope

I’m reviewing continuous disposable-demo investigation. I’ll keep the scope and permissions explicit.

First cycle

The first example cycle inspects cart quantities and totals.

Next gap

Refresh and retry paths follow the initial cart-total check.

Next cycle

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

Stop

Each cycle follows the next useful gap until stopped. This short illustration stops; real execution still respects permissions and stop controls.

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

Each cycle follows the next useful gap until stopped.

Evidence to inspect

Cycle 1 cart totals → cycle 2 state recovery → cycle 3 next hypothesis.

Still untested / not established

This short illustration stops; real execution still respects permissions and stop controls.

Ready. Read the full example or play its steps.

What a useful result contains

A bounded claim

For continuous disposable-demo investigation, state the target, revision, environment and actual work performed. Keep planned, executed, blocked and untested work separate.

An inspectable trail

Cycle 1 cart totals → cycle 2 state recovery → cycle 3 next hypothesis. In a real run, retain the source, trace, screenshot or fixture behind the conclusion.

The qualification

This short illustration stops; real execution still respects permissions and stop controls.

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 continuous disposable-demo investigation 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-forever result. Separate observed evidence, assumptions and untested scope, then recommend the next useful check.

Where to go next

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

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