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-alertsgit 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-alerts)<a href="https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/bernstein-alerts"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/bernstein-alerts/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-alerts"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/bernstein-alerts.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 | $0.00043 | $0.00328 |
| Opus 5 | $0.00022 | $0.00164 |
| Sonnet 5 | $0.00009 | $0.00066 |
| Haiku 4.5 | $0.00004 | $0.00033 |
Grade A, and why
bernstein-alerts 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 9d 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 Alerts
Surface problems that need attention right now.
When to Use
- User asks "any problems?" or "what needs my attention?"
- User asks about errors, failures, or warnings
- Something seems wrong and user wants a diagnostic
- User says "is anything broken?"
Instructions
- Run
scripts/alerts.shto fetch current alerts. - Categorize and present by severity:
## Alerts
### Critical
- Task TASK-042 FAILED: "TypeError in auth middleware" - agent ses-a1b2 (backend)
→ Fix: Review the error, create a follow-up task, or retry
### Warning
- Budget at 85% ($4.25 / $5.00) - consider increasing budget or pausing low-priority tasks
- Agent ses-e5f6 stalled for 3m 20s - consider killing it with /bernstein-agents
### Info
- 2 tasks blocked, waiting for human approval - use /bernstein-approve to review
- For each alert, suggest a concrete action:
- Failed task → offer to create a retry task or inspect the error
- Stalled agent → offer to kill it
- Budget warning → show cost breakdown
- Blocked task → link to approval flow
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.
- 9d ago First seen · 45 lines · 43 tokens per session scan A aedae3576bf2
bernstein-alerts is a skill published in the GitHub repository sipyourdrink-ltd/bernstein (1,126 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 328 once invoked, about $0.0002 per session on Opus 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
safe-debug
Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated from research…
verify
Execution verification for CLI/script features — runs commands and captures output for human review. Use after /exec for script changes.
debugging
Systematic root-cause investigation before any fix attempt. Four phases — Root Cause → Pattern Analysis → Hypothesis → Implementation. If 3+ fixes fail, question the architecture.
agent-runtime-proof
Use when a local Agent runtime process must be inspected or verified against an explicit runtime expectation, especially after an install or upgrade.
systematic-troubleshooting
Use when experiments produce unexpected results, analyses fail, or findings contradict expectations — before proposing explanations or re-running.
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.