What is conditional-access-mfa?

Guidance for Microsoft Entra Conditional Access and multifactor authentication. Entra is Microsoft's cloud identity service; Conditional Access decides whether access is allowed based on signals such as the user, device, location, app, or risk, while multifactor authentication requires more than one proof of identity.

Use it to design and roll out policies for administrator MFA, user MFA, blocking older sign-in methods, requiring managed devices, and other Entra-connected apps.

It helps enforce access rules that adapt to sign-in conditions and reduces reliance on passwords alone.

conditional-access-mfa — Skill for Claude Code and Codex by vinayaklat

Install

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.

Any agent

npx skills add vinayaklatthe/microsoft-security-skills --skill conditional-access-mfa

Clone the repo

git clone --depth 1 https://github.com/vinayaklatthe/microsoft-security-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/conditional-access-mfa/github.svg)](https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/conditional-access-mfa)

Your own site

<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/conditional-access-mfa"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/conditional-access-mfa/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/conditional-access-mfa"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/conditional-access-mfa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 180 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,659 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00180	$0.01659
Opus 5	$0.00090	$0.00830
Sonnet 5	$0.00036	$0.00332
Haiku 4.5	$0.00018	$0.00166

Measured 10d ago against content hash e2592810939f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

conditional-access-mfa 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 10d 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.

skills/conditional-access-mfa/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conditional Access & MFA

Conditional Access (CA) is the Zero Trust policy engine in Entra. It evaluates signals - user /group, device state, location, application, sign-in risk - and enforces grant, block, or grant-with-controls (MFA, compliant device, session controls). MFA without CA is rare; the two are designed together.

When to use

Enforcing adaptive, identity-centric access controls across Microsoft 365 and any Entra- integrated app. Use this skill for the baseline policy set and any new policy rollout.

Do not use this skill for risk detection (entra-id-protection), just-in-time admin elevation (azure-pim), or app-side OAuth permissions (entra-id).

The baseline 6-policy set

Every Entra tenant in 2026 should have these six policies as the minimum, in this order.

#	Policy	Scope	Grant control
1	Require MFA for admins	All Entra admin roles	MFA + phishing-resistant strength
2	Require MFA for all users	All users (excl. break-glass)	MFA
3	Block legacy authentication	All users	Block
4	Require compliant device for M365	All users, M365 apps	Compliant OR hybrid-joined
5	Risk-based CA - sign-in risk High	All users	MFA (requires EID P2)
6	Risk-based CA - user risk High	All users	Secure password change (requires EID P2)

Rule of thumb: if a tenant doesn't have all 6, it is below the 2026 Microsoft baseline. Policies 5 and 6 require Entra ID P2; substitute with risk-based authentication strength on E3 if needed.

Approach

Inventory before authoring — Export current sign-in logs to understand baseline: per-app MFA usage, legacy auth volume, device compliance, named locations in use. Don't author policies on assumed traffic patterns. Verify: Sign-ins workbook shows per-app MFA % and legacy auth count.
Use authentication strengths, not just "Require MFA" — Authentication strengths let you require phishing-resistant methods (FIDO2 passkey, Windows Hello for Business, certificate-based) for high-value scopes. Plain "Require MFA" accepts SMS - still phishable. Verify: admin policy grant control uses the built-in Phishing-resistant MFA authentication strength, not generic MFA.

Read the full file on GitHub · 115 lines

Changes

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.

10d ago First seen · 115 lines · 180 tokens per session scan A e2592810939f

Subscribe to this mod's changes

conditional-access-mfa is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (172 stars, last pushed 2mo ago), licensed MIT. It adds 180 tokens to every session and 1,659 once invoked, about $0.0009 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.

Security ai-agents copilot defender entra entra-id microsoft

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…

ericrisco/rsc-harness · 82 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

conditional-access-mfa