OpenSRE is an open-source framework for building AI agents that investigate and resolve production incidents using operational data and tools. It is for site reliability engineers who want customizable incident-response workflows, training, and evaluation on their own infrastructure.
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 Tracer-Cloud/opensre --skill toolsgit clone --depth 1 https://github.com/Tracer-Cloud/opensreWrote 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/tracer-cloud/opensre/tools)<a href="https://agentmods.dev/skills/tracer-cloud/opensre/tools"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/tools/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/tracer-cloud/opensre/tools"><img src="https://agentmods.dev/badge/skills/tracer-cloud/opensre/tools.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 | $0.00073 | $0.02903 |
| Opus 5.5 | $0.00029 | $0.01161 |
| Sonnet 5.5 | $0.00015 | $0.00581 |
| Haiku 4.5 | $0.00007 | $0.00290 |
Grade A, and why
querying-yandex-cloud 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
querying-yandex-cloud
Three rules first, because they are the ones that waste a whole investigation when they are missed.
Read kubernetes_get_events before naming a cause for any pod that is not
Running. The pod list shows only that it is stuck. Every reason looks
identical there — out of memory, unschedulable, an image that will not pull, a
volume that will not mount. The event carries the actual message, and guessing
between them produces a confident wrong answer that sends someone to check node
capacity when the registry was refusing the pull. Pending with no events about
resources is an image or volume problem, not a scheduling one.
A pod is not a Yandex Cloud resource. The Yandex Cloud API knows the
Kubernetes cluster — version, health, node groups, read with
execute_yc_operation on /managed-kubernetes/ — and nothing about what runs
inside it. Neither execute_yc_operation nor find_yc_api can reach a pod, an
event or a container log, and no /managed-kubernetes/ path returns one. Read
those with kubernetes_list_pods, kubernetes_get_events,
kubernetes_get_pod_logs and kubernetes_list_nodes, which talk to the
cluster's own API server. If those tools are absent, Managed Kubernetes access
was not connected during setup — say so rather than trying the Yandex Cloud API
instead.
Never run yc via a shell tool. It is normally not installed, it needs its
own separate authentication, and it can mutate. If you catch yourself writing
yc ... to answer a question, use execute_yc_operation instead.
But do write the yc ... command out when something should change. These
tools only read. When the finding calls for an action — resize, restart,
rebalance, change a setting — end with the exact yc ... command an operator
can paste, not a description of what to do. Writing the command is correct;
running it is not.
Everything else reaches Yandex Cloud over its REST API with the configured credential. There is no CLI step and no shell step.
What ships with it
9 files 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.
- __init__.py 1.1 KB runs code
- yc_api_lookup_tool/__init__.py 4.8 KB runs code
- yc_db_logs_tool/__init__.py 8.5 KB runs code
- yc_db_tool/__init__.py 17 KB runs code
- yc_instances_tool/__init__.py 8.8 KB runs code
- yc_lb_tool/__init__.py 18 KB runs code
- yc_logs_tool/__init__.py 10 KB runs code
- yc_metrics_tool/__init__.py 13 KB runs code
- yc_operation_tool/__init__.py 8.0 KB runs code
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.
- 1mo ago Changed · +2 tokens per session db6ee0440d70
- 1mo ago Changed 2cb5dcc00a69
- 1mo ago First seen · 233 lines · 71 tokens per session scan A 77b2c077746c
querying-yandex-cloud is a skill published in the GitHub repository Tracer-Cloud/opensre (12,513 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 2,903 once invoked, about $0.0003 per session on Opus 5.5. 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
grafana
Build operable Grafana dashboards with template variables, provisioning-as-code, and unified alerts wired to Prometheus/Loki; avoid high-cardinality panels agents love to ship.
Observability with Prometheus & Grafana
Production-grade observability stack with Prometheus metrics, Grafana dashboards, PromQL query language, alerting rules, and AI-powered anomaly detection for modern cloud-native applications.
monitoring-alerting-commerce
Track store health in real time with dashboards for checkout success rate, payment failures, cart errors, and custom SLO alerting.
grafana-expert
Expert-level Grafana dashboards, visualization, data sources, alerting, and production operations. Use when the user mentions dashboards, visualization, monitoring, observability, or alerting, or when the task involves Grafana Architecture, Installation on Kubernetes, Data Sources, or Dashboard JSON.
k8s-monitoring-alerting
A Kubernetes diagnostic and repair method for Prometheus and Grafana monitoring problems, including alerts that do not trigger. Prometheus collects measurements, while Grafana displays them in dashboards.
monitoring-expert
Expert-level monitoring and observability with Prometheus, Grafana, logging, and alerting. Use when the user mentions observability, Prometheus, Grafana, logging, metrics, or alerting, or when the task involves The Three Pillars of Observability, Monitoring Fundamentals, Prometheus Configuration, or Alert Rules.