<div align="center"
<img src="docs/github-banner.png" alt="CrewScore — find the safety rules your AI agent prompt forgot. 23 public controls. Offline. No API key." width="100%"
CrewScore
Find missing written safeguards before your AI assistant goes live.
CrewScore finds missing written guardrails in agent system prompts — injection defense, human approval, cost limits, stop conditions — offline, no API key, open rules.
It is a checklist of 23 published controls, not a quality ranking and not runtime red-teaming. Low coverage is actionable; high coverage only means the text is present.
Public-good thesis: written safeguards should be inspectable with an offline, open ruleset before teams depend on runtime claims that are harder to reproduce or independently review.
We scanned 356 publicly collected agent prompts: 83 production-labeled prompts and 273 general-purpose prompts. Among the production-labeled subset, median coverage was 10 of 100. GPT-Store median: 0 of 100. Numbers → · Shareable card → · Live checker →
<br/
Example: control coverage 8/23 written · first gap to review: A human must approve. CrewScore checks whether controls are written down, not whether an agent obeys them.
Try it live, no install: crewscore.ai
<img src="docs/demo.svg" alt="Before and after: the fictional Northstar Clinic demo fixture covers 8 of 23 written controls, with 'a human must approve' as the first gap to review; after adding the selected wording it covers 9 of 23. Coverage is not runtime proof." width="720"
</div
Created and maintained by Sarosh Hussain. Pendoah is the company operating context for this project. Technical claims are grounded in the code, tests, and cited validation material.
Roadmap · Governance · Contributing · Security
pip install crewscore
crewscore scan .
# Gate the one control that matters:
crewscore scan . --require human_gate.approval_requiredDeterministic regex over prompt text and SYSTEMPROMPT / systemprompt string literals in .py / .ts / .js source. Offline, no API key, no LLM.
---