Does CrewScore upload my prompt?

No. Scoring happens locally in your browser and prompt text never leaves the page.

Does a high result prove an AI agent is safe?

No. CrewScore checks whether published guardrails are written down, not whether an agent follows them at runtime.

Can I use CrewScore in CI?

Yes. The open-source CLI and GitHub Action can report controls, protect a prompt-free baseline, require specific controls, and emit SARIF.

Browser-local guardrail checklist

Find the safety rules your AI agent prompt forgot.

Paste your AI instructions. CrewScore checks them against 23 public guardrail controls in your browser — no prompt upload, signup, API key, or model call.

Runs locally23 public controlsOpen sourceNo API key

Written-control coverage, not runtime proof. It checks whether guardrails are written down — not whether an agent follows them.

CrewScoreLocal check

23 public controls

Synthetic instructions

Ready

Checking locally

—of—

First gapWaiting for local check

Before —After —

The demo runs once and stops.

A synthetic example is checked locally. CrewScore reports written-control coverage and the first control to review; it does not test runtime behavior.

What are you checking?

I use

Pick where your AI instructions live — or paste them below.

System prompt / AI instructions Coding-agent instructions

AI assistant instructions

Paste ChatGPT custom instructions, a Claude Project prompt, a support-bot prompt, or another system prompt.

Supported: public github.com/.../blob/... and raw.githubusercontent.com files only.

Scoring happens locally.

Your result will appear here

Start with a demo or paste instructions. CrewScore will show written controls it detected and suggested controls to review.

Review suggested wording

Select only wording that belongs in this prompt. These are editable text suggestions, not runtime enforcement.

Pair written guardrails with runtime approvals, tool restrictions, and evaluation. See runtime next steps.

How it works

Paste instructions, find missing written guardrails, then improve the wording or add a recurring repository check.

Open rules

Every control, regex, and ruleset version is public. Developer mode shows exact matches and IDs.

Read the scoring catalog

Keep controls from regressing

Use the CLI or Action to protect specific written controls and generate prompt-free SARIF findings.

Set up CI policies

Methodology

Coverage helps identify omitted written controls. It is not a quality ranking, a certification, or a runtime test.

Read validation and limitations

Questions, answered plainly

Does CrewScore upload my instructions?

No. Scoring happens locally; prompt text never leaves this browser.

Does a high result prove an agent is safe?

No. It means public text patterns for written controls were detected. Runtime enforcement and testing remain separate.

Can I make this a recurring check?

Yes. Use the open-source CLI or GitHub Action to require particular controls, protect a prompt-free baseline, and emit SARIF.