Cheatcode_
Feedback

Front page / By role / Model threats

Model threats

Map how data flows and decide how to stop likely attacks.

For Security engineer · Parallel readers, one writer

What should be reviewed?

One line is enough. Step 1 asks the rest in your AI app, and nothing is done until you approve the brief it writes.

It never leaves this computer: not uploaded to Cheatcode, never used to train a model. Your AI app reads it from the case folder.

Add details (optional)
Start

Step 1 asks anything else it needs, in your AI app. Nothing you write here or put in the case folder comes to Cheatcode.

In the case folder's materials/: The thing to review, and your playbook, checklist or standard if you have one.

The 3 steps

  1. 01

    Set the standard

    Then you approve, before the next step starts.

  2. 02

    Review in parallel

  3. 03

    Merge the findings

How it does this well

Independent reviewers per dimension against a stated standard, one integrator. Not found and out of scope are valid answers here: it says so instead of guessing.

How the field does this well
  • Write the check first: a failing test, a typecheck or a command that comes back pass or fail.
  • Work one unit at a time and show the command that ran and its output as evidence.
  • Have a reader who did not write the change review it against the written spec, and skip style.
  • Keep state in files: a list of checks whose status may only flip to passing, and a progress note.
Ground it first

Ask for, or look in materials/ for: the repository or files to change, how its tests run, and the coding standards. If there is none, say plainly that the result rests on general defaults, and name them.

What stays with the person

Scoping ambiguous work, architecture choices, and the final merge or release. Prepare these; never decide them.

The check that makes it trustworthy

A failing check written first, a passing run shown as output, and an independent review of the change against the spec.

The person's own data

If the person has connected GitHub, Linear, Jira + Confluence, Postgres, read their data through that connector instead of asking for exports, and say which source each number or fact came from. Without one, work from materials/.

The agents

reviewer
Reviews one dimension of an artifact in a Cheatcode case against a stated checklist and records findings with exact quotes.

Where things stay

On your computer
Your files in materials/, every result in outputs/, the work itself. It runs in your AI app, on the plan you already pay for.
With Cheatcode
The steps, the gates and how far each case has come, so a case survives closing the app. See your cases.