bernstein-agents
Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user…
Show detailed cost breakdown and budget status for the Bernstein orchestrator. Use when the user asks about spending, budget, cost per model, cost per agent, or wants a cost projection.
Claude Code
$ npx -y skills add sipyourdrink-ltd/bernstein --skill bernstein-cost --agent claude-code
Codex
$ npx skills add sipyourdrink-ltd/bernstein --skill bernstein-cost -a codex -y
Cursor
$ npx skills add sipyourdrink-ltd/bernstein --skill bernstein-cost -a cursor -y
Gemini CLI
$ npx skills add sipyourdrink-ltd/bernstein --skill bernstein-cost -a gemini-cli -y
GitHub Copilot
$ npx skills add sipyourdrink-ltd/bernstein --skill bernstein-cost -a github-copilot -y
OpenCode
$ npx skills add sipyourdrink-ltd/bernstein --skill bernstein-cost -a opencode -y
Windsurf
$ npx skills add sipyourdrink-ltd/bernstein --skill bernstein-cost -a windsurf -y
name: bernstein-cost description: > Show detailed cost breakdown and budget status using Bernstein's cost reporting. Use when the user asks about spending, budget, cost per model, cost per agent, or wants a cost projection.
Show detailed cost analysis and budget status.
1. Run `scripts/costs.sh` to fetch cost data. 2. Run `scripts/costs.sh projection` for cost forecast. 3. Present a clear cost report:
## Cost Report
**Total spent:** $X.XX / $Y.YY budget (Z%)
**Status:** {OK | WARNING | OVER BUDGET}
### Per Model
| Model | Tasks | Cost | Avg/Task |
|-------|-------|------|----------|
| claude-sonnet-4 | 12 | $1.84 | $0.15 |
| gpt-4.1 | 5 | $0.62 | $0.12 |
### Per Agent
| Agent | Role | Tasks Done | Cost |
|-------|------|------------|------|
| claude-backend-01 | backend | 3 | $0.45 |
### Projection
At current rate, this run will cost ~$X.XX total.
Estimated completion: Y tasks remaining, ~Z minutes.4. If budget warning is active, highlight it prominently. 5. If over budget, note that Bernstein has paused new task claims.
The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user…
Show active alerts from Bernstein - failed tasks, stalled agents, budget warnings, blocked tasks needing human intervention. Use…
Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent…
Create a new task in the Bernstein orchestrator. Use when the user wants to add a task, delegate work to an agent, file a bug…
Create and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when…
Show quality metrics for Bernstein runs - success rates per model, lint/test pass rates, completion time distributions. Use when…
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…
Create a new Architecture Decision Record with sequential numbering and AgentDB registration