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-for-m365git 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-for-m365)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-for-m365"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-for-m365/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-for-m365"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-for-m365.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 | $0.00107 | $0.01249 |
| Opus 5 | $0.00053 | $0.00624 |
| Sonnet 5 | $0.00021 | $0.00250 |
| Haiku 4.5 | $0.00011 | $0.00125 |
Grade A, and why
purview-for-m365 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Purview for Microsoft 365
This skill coordinates Purview controls across the core Microsoft 365 workloads - Exchange Online, SharePoint, OneDrive, and Teams - so labelling, DLP, retention, and Copilot data protection are applied coherently per workload, recognising that each workload has distinct behaviour.
When to use
Operationalising Purview specifically across Microsoft 365 collaboration and email, accounting for each workload's quirks (Teams chat retroactivity, container vs item labels, mail flow).
Do not use this skill for the multicloud Data Map (use purview-data-map) or for end-to-end
strategy sequencing (use purview-information-governance).
Per-workload picker
| Workload | Labels | DLP | Retention | Notes |
|---|---|---|---|---|
| Exchange Online | Item + OME | Transport-level | Policy + label | Mail-flow rules; encryption (OME) |
| SharePoint | Item + container | Service-side | Policy + label | Container labels for sites; auto-label at rest |
| OneDrive | Item | Service-side | Policy + label | Auto-label at rest |
| Teams | Container + item (chat scoped) | Chat/channel, post-creation only | Policy + label | Meeting recordings retained in OneDrive/SharePoint |
Rule of thumb: each workload is its own location for DLP and retention; selecting one does not cover the others. Design per-workload first, harmonise second.
Per-workload considerations
- Exchange Online - Email DLP, encryption (sensitivity labels / OME), retention, mail-flow considerations; transport-level enforcement and connector behaviour matter.
- SharePoint & OneDrive - Sensitivity labels (incl. container labels for sites), service-side auto-labelling, DLP, retention, and oversharing controls via SharePoint Advanced Management.
- Teams - Chat/channel DLP (post-creation only), container labels for teams, retention for messages, and meeting/recording considerations (recordings live in OneDrive or SharePoint).
Approach
- Baseline classification & labels across all workloads first; confirm the label set is published to all relevant user groups and shows in each app. Verify: a pilot user sees the label menu in Outlook, Word, SharePoint, and Teams.
- Apply DLP per workload location with simulation before enforcement; one policy per workload (or per workload + severity tier) is easier to tune than one mega-policy. Verify: simulation reports per workload reviewed; false-positive rate within target.
- Apply retention/records via policies and adaptive scopes; map workloads to retention schedules. Verify: each workload has retention coverage; disposition review configured for label-based deletion.
- Protect Copilot interactions - pair with oversharing controls and DSPM for AI so Copilot honours both permissions and labels. Verify: a test user cannot retrieve labelled-restricted content via Copilot.
- Monitor with Activity Explorer, alerts, and audit; build per-workload incident SLAs. Verify: weekly per-workload incident triage cadence in place.
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 · 90 lines · 107 tokens per session scan A 19b23c5d4cd4
purview-for-m365 is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 1,249 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 2026-09-03.
Other skills, from other repositories
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…
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…
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.
carta-interaction-reference-core
The non-negotiable half of Carta's AI agent interaction rules — financial precision, data provenance, the AI-computation gate, how to confirm, and trust & safety. Loaded ONCE per conversation, before any response that presents or writes Carta financial data. Sufficient on its own for write flows; a flow that also…
compliance-verifier
Use this agent to validate deployments against GDPR, HIPAA, SOC2, and other regulatory compliance frameworks and generate audit reports.