microsoft/sre-agent is the community repository for Azure SRE Agent, an AI assistant for diagnosing and resolving production problems and reducing routine operations work. It is for teams working on service reliability and includes documentation, discussions, videos, and hands-on labs for using the product. The catalogue skills relate to the agent's official plugins and resources.
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 microsoft/sre-agent --skill performance-investigationgit clone --depth 1 https://github.com/microsoft/sre-agentWrote 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/microsoft/sre-agent/performance-investigation)<a href="https://agentmods.dev/skills/microsoft/sre-agent/performance-investigation"><img src="https://agentmods.dev/badge/skills/microsoft/sre-agent/performance-investigation/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/microsoft/sre-agent/performance-investigation"><img src="https://agentmods.dev/badge/skills/microsoft/sre-agent/performance-investigation.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 | $0.00084 | $0.01986 |
| Opus 5.5 | $0.00034 | $0.00794 |
| Sonnet 5.5 | $0.00017 | $0.00397 |
| Haiku 4.5 | $0.00008 | $0.00199 |
Grade A, and why
performance-investigation scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
error in the response `detail` field (it is NOT written to the logs): `curl` the lane's `/health` How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zava Learning — Application Incident Runbook
Resource Group: @@RG@@. Services (Container Apps): learner-portal, course-api, assessment-api.
Quiz launch path: portal -> assessment-api -> course-api.
Confirm the network/edge is healthy first (App Gateway backend healthy, NSG clean) so you don't misattribute an app fault. Then:
- Query App Insights failures/exceptions filtered by the failing
cloud_RoleName. - Check Container App revision health and replica counts — an API with zero replicas serves no
requests and surfaces as quiz launch / 502 failures with a clean network path. A revision can hit
zero replicas two ways: scaled to zero, OR the active revision was deactivated (an inactive
revision runs zero replicas).
az containerapp revision listshows only ACTIVE revisions, so a deactivated lane looks like it has "no revisions" — list with--alland inspectproperties.active/properties.latestRevisionName. The latent cause is often a scale floor of zero in IaC (appLaneMinReplicas: 0); the durable fix restores a non-zero minimum. - Inspect recent revisions/config changes.
- For LATENCY regressions (slow quiz responses / the latency alert) on a clean network path: pull assessment-api request durations from Log Analytics console logs (each request logs
ms=<duration>), find the step-change in latency and align it to the most recent assessment-api revision/image deployment, then inspectsrc/assessment-api/server.jsfor expensive synchronous work added on the request path (e.g. a synchronous KDF/crypto call). This is a code regression — mitigate live by rolling back to the prior revision, then fix durably with a code PR.
Reporting-worker grade-export failures
If the symptom is the nightly grade-export job failing (no quiz/portal impact — this is a back-office
batch job on a dedicated VM vm-zava-reporting-*):
- Query Log Analytics
SyslogforProcessName == "zava-export"— the worker logs a heartbeat on success and aFAILEDline plus the raw OS error (export write error: ...) on failure. Read the raw error to identify the failure mode. - Correlate with disk telemetry: the
Perftable carries Logical Disk% Used SpaceandFree Megabytesfor the worker. A data volume (/data) at ~100% used / near-zero free is the signal that the export writes are failing for lack of space. - Confirm on the VM with a read command (
az vm run-command invoke ... --scripts "df -h /data"). - Mitigate live: free space on the worker's data disk (remove the accumulated backlog file under
/data/exports) viaaz vm run-command. Re-check that the next export run logs a success heartbeat. - Durable fix: the worker's export retention/rotation lives in
src/reporting-worker/cloud-init.yaml— a PR that enforces retention (or grows the data disk ininfra/modules/vm.bicep) is the lasting fix.
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 · 111 lines · 84 tokens per session scan A 2d482efaadfd
performance-investigation is a skill published in the GitHub repository microsoft/sre-agent (179 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 1,986 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.