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/microsoft/sre-agent/cost-analysisnpx skills add microsoft/sre-agent --skill cost-analysisgit clone --depth 1 https://github.com/microsoft/sre-agentWhat 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 | $0.00057 | $0.00883 |
| Opus 5 | $0.00028 | $0.00441 |
| Sonnet 5 | $0.00011 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
cost-analysis 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 2d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zava Learning — Cloud Cost Analysis
Resource Group: @@RG@@. Read-only audit — never resize, deallocate, or delete a resource.
This is a weekly spend posture review. Recommend optimisations for a human to apply; change nothing.
1. Pull actual spend (preferred path)
Use Cost Management for real billed amounts, scoped to the RG:
- This week vs. last week by resource:
az costmanagement query --type ActualCost --timeframe Custom --time-period from=<start> to=<end> --scope "/subscriptions/<sub>/resourceGroups/@@RG@@" --dataset-grouping name=ResourceId type=Dimension --dataset-aggregation totalCost.name=Cost totalCost.function=Sum(run it for the current 7-day window and the prior 7-day window, then diff per ResourceId). - Or month-to-date by service: same query grouped by
ServiceName. Ifaz costmanagementis missing or returns an auth error (the agent identity lacks Cost Management Reader), FALL BACK toaz consumption usage list --start-date <d> --end-date <d>filtered to the RG. Record which data source you used so the report is honest about provenance.
2. If billing data is unavailable, estimate from inventory
As a last resort (no Cost Management and no consumption access), build an estimate:
- Inventory the RG:
az resource list -g @@RG@@ --query "[].{name:name,type:type,sku:sku}". - Note the cost-bearing resources (PostgreSQL Flexible Server SKU, the reporting VM SKU + managed disks, Container Apps environments + per-app replicas/scale, Application Gateway tier + capacity units, Log Analytics ingestion, Key Vault, ACR SKU, public IPs).
- Use
microsoft-learn_microsoft_docs_search/ known Azure retail pricing to produce a rough, clearly-labelled estimate, not a billed figure. State the assumption explicitly.
3. Find waste and right-sizing opportunities (read-only signals)
- Idle/oversized: VMs that are deallocated yet still incurring disk cost; disks not attached to
any VM (
az disk list -g @@RG@@ --query "[?managedBy==null]"); over-provisioned VM/DB SKUs vs. observed CPU/memory; Container Apps with high min-replicas but low traffic. - Orphaned: unattached public IPs, empty App Gateway backend pools, unused NICs, old ACR images.
- Trend: any ResourceId whose week-over-week cost rose sharply — flag it with the Δ%.
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.
- 2d ago First seen · 60 lines · 57 tokens per session scan A 4fbbef252474
cost-analysis is a skill published in the GitHub repository microsoft/sre-agent (149 stars, last pushed 9d ago), licensed MIT. It adds 57 tokens to every session and 883 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…