Bernstein Quality

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkUndeclared4 observations, not in its own description
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

curl -sf "${HEADERS[@]}" "$API/quality/metrics" || echo '{"error": "API not reachable"}' >&2

curl -sf "${HEADERS[@]}" "$API/quality/pass-rates" || echo '{"error": "API not reachable"}' >&2

curl -sf "${HEADERS[@]}" "$API/quality/completion-times" || echo '{"error": "API not reachable"}' >&2

API="${BERNSTEIN_API_URL:-http://127.0.0.1:8052}"

network use found in code, not declared in the description

Audit 0.4.1 · source sha 6ba64a7d2489 · 14 Oct 2026Report an issue or request a re-scan

• Publishersipyourdrink-ltd GitHub organizationOwner of the repository this skill is read from
• Source foldersipyourdrink-ltd/bernstein/packages/cursor-plugin/skills/bernstein-qualityThe exact folder we audited
• LicenceApache-2.0As the repository states it
• Commit pinned for this verdict6ba64a7d2489A new audit runs when the source changes
• Repository statusNot archivedPushed today
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Show quality metrics for Bernstein runs - success rates per model, lint/test pass rates, completion time distributions. Use when the user asks about quality, reliability, which model performs best, or pass rates.

---
name: bernstein-quality
description: >
  Show quality metrics for Bernstein runs - success rates per model,
  lint/test pass rates, completion time distributions. Use when the user
  asks about quality, reliability, which model performs best, or pass rates.
---

# Bernstein Quality Metrics

Analyze quality and reliability of agent-generated code.

## When to Use

- User asks "how reliable are the agents?" or "which model is best?"
- User wants success rates, pass rates, or completion time stats
- User asks about test failures or lint issues across models
- User says "show me quality metrics"

## Instructions

1. Run `scripts/quality.sh metrics` for overall quality metrics.
2. Run `scripts/quality.sh pass-rates` for lint/typecheck/test pass rates by model.
3. Run `scripts/quality.sh times` for completion time distributions.

4. Present a quality dashboard:

```
## Quality Dashboard

### Success Rate by Model
| Model | Tasks | Success | Fail | Rate |
|-------|-------|---------|------|------|
| claude-sonnet-4 | 24 | 22 | 2 | 91.7% |
| gpt-4.1 | 12 | 10 | 2 | 83.3% |

### Pass Rates
| Check | Overall | claude-sonnet-4 | gpt-4.1 |
|-------|---------|-----------------|---------|
| Lint | 96% | 98% | 92% |
| Type-check | 88% | 91% | 83% |
| Tests | 85% | 89% | 75% |

### Completion Times
| Percentile | Time |
|------------|------|
| p50 | 3m 20s |
| p90 | 8m 45s |
| p99 | 15m 12s |
```

5. Highlight any models with significantly lower pass rates.
6. Recommend model routing adjustments if one model consistently underperforms.

Excerpt, first 1,548 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/sipyourdrink-ltd/bernstein
git -C bernstein checkout 6ba64a7d2489

Works in

1. 2026-10-14
   !CAUTION B 89 / 100

   first audit · source 6ba64a7d2489

Questions about Bernstein Quality

• github.com/sipyourdrink-ltd/bernstein/tree/main/packages/cursor- — the audited source at commit 6ba64a7d2489 and every finding aboveObserved · 14 Oct 2026

Spotted something wrong? Report a correction · Methodology