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.

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 →

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

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.

pip install crewscore
crewscore scan .
# Gate the one control that matters:
crewscore scan . --require human_gate.approval_required

Deterministic regex over prompt text and SYSTEM_PROMPT / system_prompt string literals in .py / .ts / .js source. Offline, no API key, no LLM.

---

Read this first

CrewScore is a checklist, not a benchmark. The number is the share of 23 published controls your prompt states — nothing about whether they are well specified, mutually consistent, or obeyed at runtime.

What the prompt does	What it scores
Nothing written down	0
One control in each of the 8 dimensions	36
All 23 controls	100
One control restated five different ways	same as stating it once

So a low score is actionable — you probably have not written down an injection policy, a human gate, or a safe-stop rule, and those are worth writing. A high score means the text is present, not that the agent obeys it. Don't rank prompts, teams, or vendors by this number, and don't treat a threshold as a safety bar. Prefer the findings to the total.

Three dimensions — Cost, Compliance, Audit — ship with known-thin construct validity and say so. Ruleset 0.6.0 tightened their patterns against measured corpus false positives; Compliance is still not lawful handling.

📄 The validation study → — including the arithmetic showing our own scale was broken through 0.1.0, which we published before fixing.

📊 Measured against 356 publicly collected prompts → — Cliff's δ = 0.614 separating production-labeled agent prompts from general-purpose ones, generated by a committed harness rather than typed by hand.

---

Usage

crewscore scan .                          # prompts + AGENTS.md + inline SYSTEM_PROMPT=...
crewscore scan . --no-inline              # file discovery only
crewscore init .                          # prompt-free regression baseline + PR workflow
crewscore scan . --fail-on-regression --baseline .crewscore-baseline.json
crewscore scan . --require human_gate.approval_required   # one-control CI habit
crewscore test --prompt-file ./prompt.md  # coverage N/23 + first gap to review
crewscore fix  --prompt-file ./prompt.md --plan   # what's missing, no writes
crewscore rules --concepts                # the 23 controls, and the rules behind them

Full CLI reference → · How scoring works →

---

CI

Start report-only — it never fails a build:

- uses: shmindmaster/crewscore@v2
  with:
    scan-path: "."

When you know which controls your workflow actually needs, name them — the build then fails only when a named control is missing, never on the coverage average:

- uses: shmindmaster/crewscore@v2
  with:
    scan-path: "."
    required-controls: "human_gate.approval_required,safe_stop.stop_condition"
    sarif: "crewscore.sarif"

Posts a sticky PR comment with the open rule findings (give the job permissions: pull-requests: write; without it the action logs a warning and moves on). Failed gates surface as ::error annotations naming the control. Guard downstream steps on the scored output, not on score — an empty score casts to 0.

Action inputs, outputs, and the CLI variant →

---

Two artifacts, two rulesets

CrewScore judges two kinds of file, and tells you which it thinks it is looking at. Detection is by filename and path — never by sniffing content.

Artifact	Examples	Judged on
Coding-agent config	AGENTS.md, CLAUDE.md, .cursorrules	Configuration smells
Agent system prompt	system-prompt.md, anything under prompts/ or agents/	The 8 governance dimensions

A file saying "always use pnpm" is telling a coding agent how to work in your repo. It has no reason to contain HIPAA language, and scoring it against that is a category error.

We know the size of that error because we measured it: against the 100 most-starred repos with an AGENTS.md (arXiv:2606.15828), the governance ruleset put all 100 in the worst tier. A scale the entire population fails carries no information. So config files get a smell verdict instead — and in --json, no governance grade at all.

crewscore test --prompt-file AGENTS.md
# -> CONFIG: NO SMELLS DETECTED   (not "0/100 CRITICAL GAPS")

---

Configuration smells

Problems in the shape of an instruction file rather than its content, from a published catalog — Configuration Smells in AGENTS.md Files (dos Santos et al., 2026), which found 91 of 100 popular projects carried at least one.

Smell	Heuristic	Found in
Context Bloat	≥ 200 lines	42% of studied projects
Lint Leakage	Style rules a configured linter already enforces	62%
Init Fossilization	Tracked by git with exactly one commit	24%

The paper's other three smells need an LLM to detect. We would rather ship three honest detectors than six approximate ones. Lint Leakage is an approximation of the paper's detector and says so in its output; Init Fossilization cannot tell "never needed revising" from "never got revised."

Smells never change the score. Folding them in would silently change what every existing --threshold means.

---

Development

git clone https://github.com/shmindmaster/crewscore.git
cd crewscore
pip install -e ".[dev]"
pytest

Development guide → · AGENTS.md · CONTRIBUTING.md

---

Docs

Validation	What the number does and does not measure
Corpus validation	Generated result over 356 publicly collected prompts
Scoring and controls	Formula, 23 controls, charter, governance
CLI	Every command and flag
GitHub Action	Action inputs/outputs and CLI-in-CI
Policies and SARIF	Regression and required-control CI without score gating
Architecture	Modules, data flow, lean target
Development	Local setup, rules, packaging, media
Live eval handoff	Promptfoo / garak after structural gate
Roadmap	Available work and deliberately deferred capabilities
Security	Private vulnerability reporting
Community discussions	Questions, adoption feedback, and open-ended ideas
Comparison	Other tools, and what to use after this one
CHANGELOG	Including every scoring change and its measured delta

What this is not

Live adversarial red-teaming · runtime tool-gate enforcement · a security or compliance certification · proof the model will obey the text.

Roadmap: framework adapters that extract prompts from LangGraph / CrewAI / AutoGen graphs; optional live adversarial testing (post-traction, not the default path).

MIT licensed.