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 vinayaklatthe/microsoft-security-skills --skill purview-generalgit clone --depth 1 https://github.com/vinayaklatthe/microsoft-security-skillsWrote 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/vinayaklatthe/microsoft-security-skills/purview-general)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-general"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-general/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/vinayaklatthe/microsoft-security-skills/purview-general"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-general.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00139 | $0.02154 |
| Opus 5.5 | $0.00056 | $0.00862 |
| Sonnet 5.5 | $0.00028 | $0.00431 |
| Haiku 4.5 | $0.00014 | $0.00215 |
Grade A, and why
purview-general 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 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.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Purview (Overview)
Microsoft Purview is a unified suite for data security, data governance, and risk & compliance, managed from the Microsoft Purview portal. This skill is the router: it helps decide which Purview solution (and which deeper skill in this repo) addresses a goal, in what order, and what to verify before building anything.
When to use
Use this skill first when the user is unsure which Purview capability fits, is starting a Purview programme from scratch, is evaluating licensing, or asks "where do I begin". Once the route is clear, hand off to the specific skill (DLP, classification, eDiscovery, etc.).
Do not use this skill when the user already knows the solution they need - go straight
to that skill (e.g. purview-dlp-policy, purview-ediscovery).
Map the goal to a solution
Pick the row that matches the question, then load the named skill.
| If the goal is... | Primary solution | Deeper skill |
|---|---|---|
| Find and tag sensitive data | Information Protection + Data Classification (SITs, trainable classifiers, EDM) | purview-data-classification |
| Stop sensitive data leaving M365, endpoints, or browsers | Data Loss Prevention | purview-dlp-policy, purview-advanced-dlp |
| Retain or delete content for legal / regulatory reasons | Data Lifecycle Management, Records Management | purview-data-lifecycle |
| Catalogue and curate enterprise data estate (lakehouses, DBs, SaaS) | Unified Catalog + Data Map | purview-data-catalog, purview-data-map |
| Detect insider data theft, sabotage, or policy violations | Insider Risk Management | insider-risk-baseline |
| Detect harassment, regulated comms, or info leakage in messaging | Communication Compliance | purview-communication-compliance |
| Run legal hold, collection, review for litigation/HR | eDiscovery (Premium for advanced) | purview-ediscovery |
| Tenant-wide audit trail of user/admin activity | Purview Audit (Standard or Premium) | purview-audit |
| Understand AI prompt data flow (Copilot, custom agents) | DSPM for AI | purview-dspm-ai |
| Fix oversharing before Copilot rollout | SAM + restricted content discovery + sensitivity labels | purview-copilot-oversharing |
| Govern data used by AI agents (Copilot Studio, custom) | Agent security + classification + DLP for AI | purview-agent-365-security |
| Privacy programme (subject rights, GDPR) | Microsoft Priva (separate product) | microsoft-priva |
| Tour Purview for a specific workload (Exchange/SharePoint/Teams) | Workload-scoped Purview controls | purview-for-m365 |
| Information governance programme (Know→Protect→Govern→Manage) | Cross-solution programme | purview-information-governance |
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 · 138 lines · 139 tokens per session scan A 63e4760ba5a6
purview-general is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (178 stars, last pushed 4mo ago), licensed MIT. It adds 139 tokens to every session and 2,154 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
power-automate
Use when operating Microsoft Power Automate cloud flows from code — create, enable, update, list or delete via the Dataverse Web API (workflow table, category 5) with Entra ID OAuth2, plus run-history debugging. NOT designing the flow definition (that is automation-flows), NOT picking a platform by billing model (that…
rfp-response-compliance-review
Reviews a draft proposal against the firm's configurable compliance rules — prohibited language, required disclosures, role and positioning boundaries, and procurement-submission requirements. Logs all findings to the Review Findings SharePoint list and annotates the draft document for salesperson and reviewer…
carta-witness-signatures
Status of witness and spousal-consent signature requests on option grants, RSAs, PIUs — who still needs to sign, and what's awaiting signature, signed, or expired. Covers one award, one company, or a whole portfolio. Read-only.
carta-hmrc-limits
Report a UK company's HMRC EMI/CSOP limit usage. Use when asked how much EMI allowance is left, whether the company is near the £6m EMI limit, who is close to or over their £250k individual limit, CSOP headroom, or whether a planned grant fits.
patentforge-provisional
Use this skill when the user wants to turn an invention idea into a structured invention disclosure, prior art search strategy, claim candidates, and provisional patent draft package. This skill is for patent drafting assistance only and must not provide legal advice or guarantee patentability.
carta-interaction-reference-core
Retired. Do not load. Carta's answer rules are in carta-cap-table:carta-cap-table.