CARBON — Engineering ConfidenceUser Guide
CHAPTER 07 / 60 Core + Pro

/carbon-issues

Hunt reproducible bugs with protected stateful multi-step journeys, persona-led exploration, directed AI-code probes, and evidence confirmation. No automatic fixes or issue-tracker writes.

Richard · FormsStart & investigate

When to use it

You want bug discovery, including surprising multi-step journeys.

Before you start

Give an exploration boundary, not only a checklist. The default investigation protects time for stateful journeys and persona-led exploration; require a reproduction or source-level justification for each finding.

Try this in your coding agent.

/carbon-issues Explore sign-in and account recovery; find reproducible bugs.

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

Account recovery journey

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

  1. 01Read context
  2. 02Investigate
  3. 03Show evidence
  4. 04Report

Coding-agent conversation

Read context

I’m reviewing account recovery journey. I’ll keep the scope and permissions explicit.

Investigate

Follow the weakest evidence link and record what remains blocked.

Show evidence

Here is the evidence trail to inspect: Enter email → Forgot password → Back → email field empty.

Report

Returning from recovery clears the typed sign-in email. This is one exploratory path, not exhaustive coverage.

CARBON

Example report

Illustration
Inspect the identity boundary
Inspect the identity boundary — TestBucks teaching screen

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

  1. User action
  2. Identity / validation
  3. Allowed outcome

Illustrated outcome

Returning from recovery clears the typed sign-in email.

Evidence to inspect

Enter email → Forgot password → Back → email field empty.

Still untested / not established

This is one exploratory path, not exhaustive coverage.

Ready. Read the full example or play its steps.

What a useful result contains

A bounded claim

For account recovery journey, state the target, revision, environment and actual work performed. Keep planned, executed, blocked and untested work separate.

An inspectable trail

Enter email → Forgot password → Back → email field empty. In a real run, retain the source, trace, screenshot or fixture behind the conclusion.

The qualification

This is one exploratory path, not exhaustive coverage.

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 account recovery journey 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-issues result. Separate observed evidence, assumptions and untested scope, then recommend the next useful check.

Where to go next

/carbon-generate →/carbon-test →

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