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-information-governancegit 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-information-governance)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-information-governance"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-information-governance/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-information-governance"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-information-governance.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 | $0.00103 | $0.01190 |
| Opus 5 | $0.00051 | $0.00595 |
| Sonnet 5 | $0.00021 | $0.00238 |
| Haiku 4.5 | $0.00010 | $0.00119 |
Grade A, and why
purview-information-governance 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Purview Information Governance (Strategy)
Information governance ties Purview classification, protection, lifecycle, and insider risk into one coherent program so sensitive data is known, protected, governed, and defensibly retained - anchored to the Zero Trust Data pillar. This skill is about sequencing, not feature deep-dives.
When to use
Planning a multi-workstream Purview rollout, building a maturity roadmap, or rationalising an in-flight deployment that is delivering features in isolation rather than outcomes.
Do not use this skill for individual feature configuration - jump to the specific Purview skill (labels, DLP, lifecycle, IRM, DSPM for AI) once the sequencing question is settled.
Pick the right entry point for the program
| Current state | Start here |
|---|---|
| No classification, no labels | Phase 1: Know - SITs + sensitivity label taxonomy in audit mode |
| Labels exist but adoption is low | Phase 1.5: auto-labelling in simulation + user training |
| Labels adopted, no DLP | Phase 2: Protect - DLP per workload in simulation, then enforce |
| DLP live, no retention | Phase 3: Govern - retention policies + records (file plan) |
| All of the above, Copilot rolling out | Phase 4: Manage AI risk - DSPM for AI + oversharing remediation |
| All above + insider concerns | Phase 5: IRM + Adaptive Protection |
Rule of thumb: each phase requires the previous one to be at "audit/simulation works" maturity. You cannot block what you cannot classify.
Approach
- Know your data - Deploy classification: SITs, trainable classifiers, EDM, and use Content/Activity Explorer to understand what sensitive data exists and where. Verify: Content Explorer shows non-trivial counts for your top SITs across SharePoint/OneDrive/Exchange.
- Protect your data - Roll out a sensitivity label taxonomy with marking/encryption, then layer DLP to prevent exfiltration of labelled/SIT content. Verify: top-tier label adoption visible; DLP audit-mode policies producing real (not noise) matches.
- Govern your data - Apply retention and records policies for defensible retain/delete; prefer adaptive scopes so policies stay current. Verify: retention policies show coverage stats per workload; disposition review running.
- Manage risk - Add Insider Risk Management and Communication Compliance for people-centric risk; add DSPM for AI as Copilot/genAI adoption grows. Verify: IRM alerts being triaged; DSPM for AI recommendations being actioned.
- Operate as a program - Establish stewardship per business unit, monthly review cadences, and a metrics dashboard (coverage, label adoption, DLP incident trends, time-to-disposition). Verify: a named exec owner reviews metrics quarterly and approves the next-phase scope.
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 · 85 lines · 103 tokens per session scan A fbaaa30e9840
purview-information-governance is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 1,190 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.