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 agentmods add skills/microsoft/sre-agent/evidence-before-afternpx skills add microsoft/sre-agent --skill evidence-before-aftergit 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/evidence-before-after)<a href="https://agentmods.dev/skills/microsoft/sre-agent/evidence-before-after"><img src="https://agentmods.dev/badge/skills/microsoft/sre-agent/evidence-before-after.svg" alt="Measured on agentmods" 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 | $0.00098 | $0.01311 |
| Opus 5 | $0.00049 | $0.00656 |
| Sonnet 5 | $0.00020 | $0.00262 |
| Haiku 4.5 | $0.00010 | $0.00131 |
Grade A, and why
evidence-before-after 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 6d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zava Learning — Before / After Evidence
Prove impact and recovery with the right visual for the fault — not a chart by reflex. Resource
Group: @@RG@@. Services: learner-portal, course-api, assessment-api. Retrieve zava-brand
and zava-report-template with SearchMemory and apply the house style. Use the windows and
root cause confirmed by rca-analysis.
Step 1 — Decide the visual FIRST (do not skip)
Classify what actually changed, then pick the visual that explains that. Plotting a smooth metric for a binary/config fault (e.g. "availability before/after" for an NSG block) is misleading and adds no insight — don't do it.
| Fault class | What changed | Primary visual | Secondary (only if telemetry shows it) |
|---|---|---|---|
| Connectivity / config / NSG / App Gateway probe / RBAC | a path or permission was closed → open (binary) | before→after path/topology diagram (ASCII or Mermaid) + a config-state delta table | one short recovery curve (e.g. 502-rate → 0) |
| Performance / latency / saturation | a metric degraded → recovered (gradual) | time-series before/during/after + percentile delta table | before-vs-after summary bars |
| Availability / reliability (5xx, restarts, replica loss) | error/health rate rose → fell | time-series + delta table | summary bars |
If a fault has both a binary cause and a metric symptom (common), lead with the diagram that explains the cause and use one metric chart only as supporting recovery proof.
Step 2 — Capture the before/after STATE (config & binary faults)
For connectivity/config/RBAC faults, the evidence is the changed configuration, not a metric:
- Read the relevant config with
RunAzCliReadCommands(e.g. NSG effective rules, App Gateway backend health, Container Apps revision/ingress, role assignments) at the mitigated state, and reconstruct the pre-fix state fromrca-analysis/ change history. - Build a state delta table:
item · before · after · effect, e.g.NSG rule block-appgw (prio 100 DENY) · present · removed · AppGW→apps unblocked;AppGW backend health · Unhealthy · Healthy · probes pass;GET /api/quiz · 502 · 200. - Render a before→after path diagram showing the broken hop and the fixed hop. Author it as
ASCII (preferred for chat/PagerDuty notes) and/or a Mermaid graph; for a polished report image
use
ExecutePythonCode(graphviz/matplotlib). Example shape:
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.
- 6d ago First seen · 86 lines · 98 tokens per session scan A 23f5929fad64
evidence-before-after is a skill published in the GitHub repository microsoft/sre-agent (151 stars, last pushed 3d ago), licensed MIT. It adds 98 tokens to every session and 1,311 once invoked, about $0.0005 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
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.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
azsdk-common-pipeline-analysis
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
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…