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 atretyak1985/swarmery --skill sre-operationsgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/sre-operations)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/sre-operations"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/sre-operations/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/atretyak1985/swarmery/sre-operations"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/sre-operations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00054 | $0.00673 |
| Opus 5.5 | $0.00022 | $0.00269 |
| Sonnet 5.5 | $0.00011 | $0.00135 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
sre-operations 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Operate production responsibly: four SRE workflows with the same two invariants — evidence before action, and a human gate before anything destructive (rollbacks, restarts, scaling, config changes in shared envs).
The four workflows
- SLO definition — user journeys → 3–5 SLIs (availability, latency p95/p99, throughput, correctness) → targets with error budgets (never 100%) → instrumented metrics → alerts, each linked to a runbook (an alert without a runbook is incomplete).
- Incident response — classify severity; check the last 24h of deploys and the error logs in parallel; human gate before mitigation (fix or rollback); document the timeline; blameless post-mortem (5 Whys) within 48h.
- Capacity planning — measure current utilization, analyze growth trends, forecast 3–12 months with confidence levels, recommend horizontal vs vertical with cost.
- Toil reduction — inventory operational tasks by frequency × duration ×
automatability; automate the top items as scripts with safety checks and
rollback (the
automationskill carries the script standards).
Platform specifics (runtime CLI, env aliases) come from project.json →
cloud; never hard-code providers. Artifacts go to
{task-dir}/sre/{action}-{target}.md when a task dir is in play. Details per
workflow: resources/workflows.md.
How to use
What it does
Carries the SRE operating discipline: SLOs with error budgets and runbook-linked alerts, gated incident response with blameless post-mortems, evidence-based capacity forecasts, and prioritized toil automation — with humans approving every destructive step.
When to use it
When the task is operating the system rather than changing its code: defining reliability targets, responding to an incident, planning capacity, or automating recurring ops chores.
How to invoke
Load the skill and name the workflow and target: "define SLOs for the ingest service", "incident: API 5xx spike since 14:00", "capacity review for the DB". @core:tech-lead routes production-risk escalations here.
What ships with it
1 file 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.
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 First seen · 58 lines · 54 tokens per session scan A 179bb05a9a64
sre-operations is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 673 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
dependency-versions
MUST consult this skill before answering whenever the user's task involves external versioned dependencies — even if you think you can handle it directly. This applies to: checking if packages/tools are up to date, upgrading npm/pip/cargo/go dependencies, planning or writing CI/CD workflows (GitHub Actions, CircleCI…
finish
Ship phase — merge, PR, keep, or discard with pre-merge verification.
gws-quick-ref
Quick reference for gws CLI syntax — core patterns, key flags, pagination, field masks, and output formats.
excalidraw
Create or extend editable Excalidraw diagrams from descriptions or repository evidence using a local skeleton-to-scene converter.
style-ops
Maintain, validate or report on the Fakoli principles ledger, checking evidence pointers and keeping its Markdown projection synchronized.
gws-events-subscribe
Google Workspace Events: Subscribe to Workspace events and stream them as NDJSON.