agent toolingby sipyourdrink-ltd
Bernstein Alerts
sipyourdrink-ltd/bernstein-alerts
Show active alerts from Bernstein - failed tasks, stalled agents, budget warnings, blocked tasks needing human intervention.
What it changes
Passed 15 of 19 test cases with the skill, and 8 of 19 without it.
Without skill41%
With skill77%
Checks it passed that the model alone missed
- Places failed task alerts under Critical severity.
- Lists Warning severity issues before Info severity issues.
- Places tasks blocked for human approval under Info severity.
and 8 more in the full report
9 fixed8 passed either way4 still failing1 broke
- Pass-rate lift
- +36 pp
- Tokens
- -48%
- Agent turns
- 0%
- Response time
- -66%
Model gemini-3.6-flashMeasured 8/14/2026v117 of 22 cases passed with skill · 19 comparable
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptI want an overview of active system problems. What exact Markdown top-level section header should introduce the grouped diagnostic list?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Introduces the diagnostic overview with the `## Alerts` header. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md36 lines2 filesincludes scripts
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.sh to 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
Track record
Benchmark
15 / 19
test cases passed, vs 8 / 19 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
Importedsipyourdrink-ltd / bernstein
packages/cursor-plugin/skills/bernstein-alerts/SKILL.md
License Apache-2.0Imported 8/3/2026Version v1Bundled 1 file · scripts