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 agentmods add skills/tracer-cloud/opensre/toolsnpx skills add Tracer-Cloud/opensre --skill toolsgit clone --depth 1 https://github.com/Tracer-Cloud/opensreWhat 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 | $0.00071 | $0.02901 |
| Opus 5 | $0.00036 | $0.01451 |
| Sonnet 5 | $0.00014 | $0.00580 |
| Haiku 4.5 | $0.00007 | $0.00290 |
Grade A, and why
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 today.
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.
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.
- today Changed 2cb5dcc00a69
- 2d ago First seen · 233 lines · 71 tokens per session scan A 77b2c077746c
yandex-cloud is a skill published in the GitHub repository Tracer-Cloud/opensre (10,985 stars, last pushed today), licensed Apache-2.0. It adds 71 tokens to every session and 2,901 once invoked, about $0.0004 per session on Opus 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
host_bash
设备上跑只读 shell 命令做诊断探索（沙箱化 / read-only policy）.
host_restart_service
重启允许列表内的 systemd service（mutating，触发 reviewer 二审）.
file_inspector
Inspect files on the host filesystem.
edge_disk_audit
Audit disk usage on edge devices.
future_skill
A skill that uses fields ongrid does not yet recognize.
hello-world
Skill whose name uses a dash, expected to be normalized.