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/zava-audit-reportnpx skills add microsoft/sre-agent --skill zava-audit-reportgit 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/zava-audit-report)<a href="https://agentmods.dev/skills/microsoft/sre-agent/zava-audit-report"><img src="https://agentmods.dev/badge/skills/microsoft/sre-agent/zava-audit-report.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 | $0.00101 | $0.02354 |
| Opus 5 | $0.00051 | $0.01177 |
| Sonnet 5 | $0.00020 | $0.00471 |
| Haiku 4.5 | $0.00010 | $0.00235 |
Grade A, and why
zava-audit-report 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
first lines of `main` may `import subprocess, sys; subprocess.run([sys.executable, "-m", "pip", How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zava Learning — Branded Weekly Audit Report (PowerPoint)
This is the packaging layer for the proactive weekly audits. It is NOT for incidents — there is
no PagerDuty, no 5-Whys, no before/after recovery. It turns the calling agent's audit findings into
one downloadable, executive-ready .pptx deck in the Zava house style.
The three audit agents that call this skill are zava-nsg-auditor, zava-rbac-auditor, and
zava-cost-analyst. Each hands you: the audit type, a 3–5 bullet posture summary, the findings rows
(each with an impact-based severity SEV1/SEV2/SEV3), and a prioritized recommendations list.
Always load the standard first
Retrieve zava-brand (palette, typography, layout, footer) and zava-audit-report (the audit deck
order and the per-type table columns) with SearchMemory and apply them exactly. The deck order
is: Title → Posture summary → Findings at a glance (chart) → Findings detail (table) → Trend/context
(optional) → Recommendations & next steps → Closing.
Redact before emitting (mandatory)
Sensitive data must never reach the deck. Retrieve the scrubber with
SearchMemory("zava-redaction") and run its redact() function over every slide's text (titles,
bullets, and every table cell) before writing the file. Resource names, NSG/rule names, role
names, scopes, and resource IDs are NOT secret — keep them; they are needed for the narrative. Never
place a Key Vault secret value, connection string, token, or learner PII on a slide.
Write the deck so it actually persists as a download
The .pptx is written into THIS thread's files directory — tmp/ThreadFiles/<threadId>/ — and the
runtime persists it to blob storage so the operator can download it. The single most common defect is
a link that 404s because the file was not actually on disk when persistence ran. The reliable recipe:
- Create the directory FIRST:
mkdir -p tmp/ThreadFiles/<threadId>/before writing the deck. - Write the
.pptxinto that directory, then confirm it is really on disk and non-empty (e.g.ls -lshows a non-zero byte count). Never announce a deck you have not verified exists. - Surface the link as
/api/files/tmp/ThreadFiles/<threadId>/<file>.pptx— this/api/files/...path IS the correct, working download URL once the file has persisted.
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 · 144 lines · 101 tokens per session scan A d21e344c6dab
zava-audit-report is a skill published in the GitHub repository microsoft/sre-agent (152 stars, last pushed 3d ago), licensed MIT. It adds 101 tokens to every session and 2,354 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…