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-data-lifecyclegit 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-data-lifecycle)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-data-lifecycle"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-data-lifecycle/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-data-lifecycle"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-data-lifecycle.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 | $0.00095 | $0.01171 |
| Opus 5.5 | $0.00038 | $0.00468 |
| Sonnet 5.5 | $0.00019 | $0.00234 |
| Haiku 4.5 | $0.00010 | $0.00117 |
Grade A, and why
purview-data-lifecycle 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Purview Data Lifecycle & Records Management
Data Lifecycle Management (retention policies and labels) and Records Management govern how long content is retained and when it is deleted across Microsoft 365 - meeting regulatory, legal, and business requirements while reducing risk and cost from over-retention.
When to use
Implementing retention and disposition for Exchange, SharePoint, OneDrive, and Teams, and managing formal records (including regulatory records) with a defensible file plan.
Do not use this skill for legal-hold preservation tied to a specific matter (use
purview-ediscovery) or for audit log retention (use purview-audit).
Pick the right control
| Need | Use |
|---|---|
| Retain or delete content at a location level (whole mailbox/site) | Retention policy |
| Item-level retain/delete, label-driven workflow | Retention label |
| Immutable, regulator-grade record | Regulatory record (label-based) |
| Triggered retention (start clock on event, e.g., contract end) | Event-based retention |
| Policies that adapt as users move/leave | Adaptive scopes (query-based) |
| One-time targeted scope | Static scope |
Rule of thumb: policies for breadth, labels for precision, adaptive scopes by default so the policy follows the org, not the org chart of two years ago.
Approach
- Define requirements - Map regulatory/legal/business retention rules to content types and locations; build a retention schedule / file plan with the records manager. Verify: each retention rule cites a regulation or business owner approval.
- Retention policies vs labels - Use retention policies for broad location-level retain/delete; use retention labels for item-level control and records declaration. Verify: each rule in the file plan is mapped to either a policy or a label, not both.
- Adaptive scopes - Prefer adaptive scopes (query-based on user/site/group attributes) over static scopes so policies stay current as the org changes. Verify: scope queries return expected user/site sets in preview.
- Records management - Declare records / regulatory records where immutability is required; build the file plan with retention triggers (event-based where needed). Verify: records cannot be edited or deleted outside the disposition workflow.
- Auto-apply labels - Configure auto-apply rules based on SITs, classifiers, or keywords in simulation first; review impact before broad rollout. Verify: simulation shows expected match coverage and few false positives.
- Disposition - Configure disposition review so reviewers approve deletion of labelled content; capture proof of disposition for audit. Verify: disposition queue populates and reviewer notifications fire.
- Operate - Quarterly review of policy coverage, disposition backlog, and file plan drift against new regulations.
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 · 92 lines · 95 tokens per session scan A ec5a067e0a0b
purview-data-lifecycle is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (178 stars, last pushed 4mo ago), licensed MIT. It adds 95 tokens to every session and 1,171 once invoked, about $0.0004 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.