agent toolingby sipyourdrink-ltd
Bernstein Status
sipyourdrink-ltd/bernstein-status
Show Bernstein orchestrator status - active agents, task progress, costs, and alerts.
What it changes
Passed 17 of 22 test cases with the skill, and 11 of 22 without it.
Without skill52%
With skill76%
Checks it passed that the model alone missed
- Advises the user to run bernstein run
- Includes Runtime in the table headers
- Recommends executing scripts/status.sh
and 5 more in the full report
8 fixed11 passed either way4 still failing2 broke
- Pass-rate lift
- +24 pp
- Tokens
- -41%
- Agent turns
- 0%
- Response time
- -61%
Model gemini-3.6-flashMeasured 8/14/2026v119 of 25 cases passed with skill · 22 comparable
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptIf the connection to the Bernstein API fails when running `scripts/status.sh`, what exact fallback command should be suggested to start the service?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Advises the user to run bernstein run | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md41 lines2 filesincludes scripts
Bernstein Status
Show the current state of the Bernstein orchestrator.
When to Use
- User asks "what's the status?" or "how's the build going?"
- User wants to see active agents, open tasks, or costs
- User asks about progress, failures, or alerts
- User wants a quick overview of the orchestration run
Instructions
- Run
scripts/status.sh to fetch the full dashboard data from the Bernstein API.
- Parse the JSON output and present a clear summary:
Summary format
## Bernstein Status
**Agents:** {active_count} active | **Tasks:** {done}/{total} done | **Cost:** ${cost_usd}
### Active Agents
| Agent | Role | Model | Runtime | Task | Cost |
|-------|------|-------|---------|------|------|
| {id} | {role} | {model} | {runtime}m | {task_title} | ${cost} |
### Tasks
- {open} open, {claimed} claimed, {done} done, {failed} failed
### Alerts
- {alert messages if any}
### Cost Breakdown
- Budget: ${budget} | Spent: ${spent} ({percentage}%)
- Per model: {breakdown}
- If the API is not reachable, tell the user to start Bernstein with
bernstein run.
Track record
Benchmark
17 / 22
test cases passed, vs 11 / 22 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-status/SKILL.md
License Apache-2.0Imported 8/3/2026Version v1Bundled 1 file · scripts