Provides a runtime control plane for operating evaluated agents in production, including versioning, staged rollout, authority controls, fallback, escalation, disablement, budgets, health monitoring, and trace-to-eval feedback.
Operate an evaluated agent with tools and authority in production through a runtime control plane covering versioning, staged rollout, fallback, cost and latency budgets, tool health, human escalation, disablement, and trace-to-eval feedback. Do not use for building agents, designing evals, or general release, SRE, security, or platform engineering — those methods stay with their specialist skills.
AGENTS.md
Markdown
Other
evals/evals.json
JSON
Other
manifest.yaml
YAML
Other
README.md
Markdown
Other
templates/service-condition-record.md
Markdown
Reference
references/agent-production-contract.md
Markdown
Reference
references/discovery-brief.md
Markdown
Reference
references/runtime-control-plan.md
Markdown
Reference
references/service-conditions.md
Markdown
Reference
references/tool-authority-health.md
Markdown
Reference
references/trace-to-eval-feedback.md
Markdown
SKILL.md
SKILL.md
Markdown
Guides safe administration and troubleshooting of remote Linux, BSD, and macOS hosts using SSH, Ansible, or Paramiko, with platform discovery, controlled changes, rollback plannin…
Enables agents to design and operate software release processes, CD pipelines, progressive delivery, versioning, quality gates, rollback plans, compliance evidence, and DORA metri…
Helps agents inspect and operate PostgreSQL safely, including configuration, query plans, vacuum, WAL/PITR, replication, failover, extensions, upgrades, and read-only diagnostics.
Helps agents design and improve reliable production systems using SLOs, observability, error budgets, incident command, on-call practices, postmortems, and operational templates.
Provides a Python CLI for querying a running Jellyfin server, including media search, recently added items, library browsing, series navigation, next-up episodes, server informati…
Deploy, configure, and troubleshoot Traefik v3 reverse proxy installations, including providers, routing, TLS/ACME, middleware, Kubernetes, observability, and production patterns.
Transforms incident, near-miss, and exercise evidence into owned follow-up work across product, engineering, testing, operations, and governance, with explicit uncertainty and ver…
Guides agents in designing, exercising, and documenting system resilience, graceful degradation, disaster recovery, restore testing, failover drills, RTO/RPO decisions, data integ…