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-reportingnpx skills add microsoft/sre-agent --skill zava-reportinggit 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 | $0.00119 | $0.02338 |
| Opus 5 | $0.00060 | $0.01169 |
| Sonnet 5 | $0.00024 | $0.00468 |
| Haiku 4.5 | $0.00012 | $0.00234 |
Grade A, and why
zava-reporting 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 3d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zava Learning — Executive Reporting & Packaging
Assemble the final, branded incident deliverables. This is the packaging layer: it consumes the
RCA (rca-analysis), before/after evidence (evidence-before-after), recommendations
(recommendations-next-steps), and the PR / Change Request (pr-delivery,
servicenow-change-management), and renders them in the Zava house style.
Deliverable-only: produce the artifacts and content; do not auto-send. Hand the email body and Teams card to the operator to send. Scope: by default produce all three deliverables; if the calling agent asks for a subset (e.g. only the HTML report), produce only those and skip the rest.
Always load the standard first
Retrieve zava-brand (style) and zava-report-template (structure, deck order, email/Teams
formats) with SearchMemory and apply them exactly. Reuse the visual evidence already produced by
evidence-before-after — whether that is a before/after path diagram or comparison charts — rather
than re-rendering it.
Present the in-thread executive summary FIRST
The incident thread renders markdown + inline images, not raw HTML — so do not paste the HTML email into the thread. Instead, write the executive summary directly in the thread as brand-styled markdown so the operator sees the full story in place:
- Use markdown structure: a symptom-only title line, then Summary, Customer impact,
Timeline (compact table), Root cause (the rendered 5-Whys ladder from
rca-analysis), What we did, Before/After, Recommendations, and an Artifacts & links section (see below). Apply thezava-brandtone and severity labels. - Show the visuals inline. The
Plot*tools post their image straight into the thread — reuse theevidence-before-aftercharts (or callPlotBarChart/PlotPieChartfor a summary visual) so they render inline next to the narrative. For a connectivity/config fault, include the before→after path diagram as a fenced code block (ASCII) directly in the markdown. - Keep every heading symptom-only; the root cause appears in the body, never in a title.
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.
- 3d ago First seen · 141 lines · 119 tokens per session scan A 75eb52c65c3b
zava-reporting is a skill published in the GitHub repository microsoft/sre-agent (149 stars, last pushed 9d ago), licensed MIT. It adds 119 tokens to every session and 2,338 once invoked, about $0.0006 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
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…
notion
Notion API for creating and managing pages, databases, and blocks. Use when the user wants to create a Notion page, query a Notion database, update Notion properties, search Notion, add content to Notion, manage Notion blocks, or interact with Notion data sources and workspaces via the API.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
sn-da-large-file-analysis
万行以上 Excel 数据集的高性能分析引擎。提供 openpyxl readonly 流式读取（iterrows 支持 10 万行以上）、Parquet 转换加速、内存优化、分块处理和大文件写入模式。遇到以下任一情况就主动使用本 skill：①数据行数 ≥ 10k（由 sn-da-excel-workflow 的行数评估步骤触发）；②用户出现触发词：大文件 / 大数据量 / 性能优化 / 内存不足 / OOM / 百万行 / 十万行 / 流式读取 / Parquet / 分块处理 / large file / big data / streaming read / chunked processing；③直接使用…
resilient-document-pipeline
Unified document generation with tool failure detection, domain knowledge fallback, progressive conversion, and Unicode safety.
category-filtering-and-difficulty-analysis
对Excel数据进行自定义分类统计、交叉分析与可视化，并基于多维度指标（如文本长度、术语密度、正则匹配等）进行综合评分与分级，适用于多类别数据分布统计及文本内容难度/质量评估场景。.