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 pagerduty-incident-updategit 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/pagerduty-incident-update)<a href="https://agentmods.dev/skills/microsoft/sre-agent/pagerduty-incident-update"><img src="https://agentmods.dev/badge/skills/microsoft/sre-agent/pagerduty-incident-update/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/pagerduty-incident-update"><img src="https://agentmods.dev/badge/skills/microsoft/sre-agent/pagerduty-incident-update.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 | $0.00100 | $0.01268 |
| Opus 5 | $0.00050 | $0.00634 |
| Sonnet 5 | $0.00020 | $0.00254 |
| Haiku 4.5 | $0.00010 | $0.00127 |
Grade A, and why
pagerduty-incident-update 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zava Learning — PagerDuty Incident Update & Closure
Keep the PagerDuty incident that triggered this investigation current, and close it out cleanly.
Resource Group: @@RG@@. Services: learner-portal, course-api, assessment-api. Operate on
the PagerDuty incident id from the triggering event (confirm details with
GetPagerDutyIncidentById if needed). Capture the incident's html_url from the
GetPagerDutyIncidentById response — that is the operator-facing PagerDuty link the
zava-reporting Artifacts & links section surfaces as [Incident #<n>](<html_url>). The bare
incident key (e.g. Q1LXN8LVWLS9L6) is NOT clickable — always pass the html_url.
Acknowledge on engagement
As soon as you start working the incident, call AcknowledgePagerDutyIncident so responders see it
is owned and stop escalating. This must be a REAL tool call that returns success — do not write
"acknowledged" unless AcknowledgePagerDutyIncident actually executed in this thread. If that tool
is not available, this skill is not loaded: load pagerduty-incident-update and retry before doing
anything else.
Mark MITIGATED immediately after the live fix
The moment the live mitigation is applied and the symptom clears (endpoint returns 200), post a
plain-text note with Status: Mitigated via AddNoteToPagerDutyIncident, summarising the live
fix in one or two lines. This marks the incident as mitigated for on-call while the incident stays
acknowledged — do NOT resolve here. The lifecycle is always: mitigate → mark Mitigated →
RCA + summary → resolve. (If zava-reporting or a triage skill swapped the active toolset and the
PagerDuty tools are gone, reload pagerduty-incident-update first.)
Post the status / summary note
Use AddNoteToPagerDutyIncident to add a concise, factual note. PagerDuty notes are PLAIN TEXT
only — they do not render HTML or markdown, and they have a practical length cap. Never paste the
zava-reporting HTML email, the deck, or the Teams Adaptive Card into a note; those rich
deliverables go through their own channels. Instead post a short text summary and link out to
the rich artifacts. Keep it symptom-only — never put the root cause in a heading or opening line
(the alert is symptom-only by design). Pull the agreed summary from the completed rca-analysis
(and zava-reporting) via SearchMemory; do not re-derive it. Post (plain text):
- Symptom & impact: one line on what users experienced and the blast radius.
- What we found / did: the confirmed diagnosis and the live mitigation applied, in plain text.
- Links: the GitHub pull request (durable fix), the ServiceNow Change Request, and the full report/deck location if available.
- Status: Mitigated / Monitoring / Resolved.
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.
- 9d ago First seen · 80 lines · 100 tokens per session scan A 3bb50fa334b1
pagerduty-incident-update is a skill published in the GitHub repository microsoft/sre-agent (154 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 1,268 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…