Bernstein is an open-source governance layer for AI agents that applies written policies, schedules agent work deterministically, controls approvals, and records verifiable execution history. It is used to coordinate CLI coding agents and other agent workloads, including parallel runs and offline review, while the catalogue entries provide its agent workflows and controls.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sipyourdrink-ltd/bernstein --skill bernstein-qualitygit clone --depth 1 https://github.com/sipyourdrink-ltd/bernsteinWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/bernstein-quality)<a href="https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/bernstein-quality"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/bernstein-quality/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/bernstein-quality"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/bernstein-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.00422 |
| Opus 5.5 | $0.00018 | $0.00169 |
| Sonnet 5.5 | $0.00009 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
bernstein-quality scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
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
-
Run
scripts/quality.sh metricsfor overall quality metrics. -
Run
scripts/quality.sh pass-ratesfor lint/typecheck/test pass rates by model. -
Run
scripts/quality.sh timesfor completion time distributions. -
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 |
- Highlight any models with significantly lower pass rates.
- Recommend model routing adjustments if one model consistently underperforms.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 54 lines · 44 tokens per session scan A cadd98f2ea7d
bernstein-quality is a skill published in the GitHub repository sipyourdrink-ltd/bernstein (1,384 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 422 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Agent Audit Trail
Append-only, hash-chained audit log for AI agents. Records agent actions, tool calls, decisions, and external writes with provenance, timestamps, and sha256 chain integrity. Designed for compliance with EU AI Act Article 12 automatic event recording requirements for high-risk AI systems.
akf-trust-metadata
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing.
data-cleaning
Use when a raw table is too dirty to trust — nulls, sentinels, duplicate rows, category sprawl, mixed types, bad dates — and you need a re-runnable clean() plus a schema gate that fails loud. NOT emitting .xlsx (that is spreadsheet-ops), NOT acquiring rows (that is data-scraper), NOT parsing PDF/HTML into rows (that…
ai-research-reproduction
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted…
create-pipeline
Convert an existing repo with ad hoc scripts into a fully reproducible Calkit pipeline. Use when the user invokes /calkit:create-pipeline or asks to make a project reproducible end-to-end.
add-pipeline-stage
Add a single new stage to an existing Calkit pipeline. Use when the user invokes /calkit:add-pipeline-stage or asks to add a script, notebook, or command to the pipeline.