agent-identity-governance

agent-identity-governance is a skill for Claude Code, Codex from vinayaklatthe/microsoft-security-skills. It costs 241 tokens per session (2,303 once invoked), scanned A, original, MIT.

A governance skill for AI agents and other non-human identities, such as service accounts and managed identities. It covers who owns them, what they can access, how they are reviewed, and how they are retired.

In plain words
What is it for?
Use it to inventory agents and service identities, assign owners, limit permissions, manage credentials, schedule reviews, and plan decommissioning. It applies to Microsoft Copilot Studio, Microsoft Foundry, custom AI agents, and related service identities.
Why use it?
It helps organizations control identities that can authenticate and act without a person directly using them. This reduces unclear ownership, excessive permissions, stale credentials, and weak incident response.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inventory agents and service identities, assign owners, limit permissions, manage credentials, schedule reviews, and plan decommissioning. It applies to Microsoft Copilot Studio, Microsoft Foundry, custom AI agents, and related service identities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vinayaklatthe/microsoft-security-skills/agent-identity-governance
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 agent-identity-governance
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.

agentmods badge for agent-identity-governance

README.md
[![agentmods](https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/agent-identity-governance/github.svg)](https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/agent-identity-governance)
Your own site
<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/agent-identity-governance"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/agent-identity-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.

agentmods 80×15 button for agent-identity-governance

Your own site · 80×15
<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/agent-identity-governance"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/agent-identity-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 241 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,303 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00241 $0.02303
Opus 5 $0.00120 $0.01151
Sonnet 5 $0.00048 $0.00461
Haiku 4.5 $0.00024 $0.00230

Measured 12d ago against content hash f937233b29ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-identity-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 12d 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/agent-identity-governance/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent & Non-Human Identity Governance

AI agents — Microsoft 365 Copilot Studio agents, Microsoft Foundry agents, custom-built ones, plus traditional service principals and managed identities — are now the fastest-growing identity population in most tenants. They authenticate, hold permissions, act on behalf of users (or themselves), and are usually under-governed.

This skill is the lifecycle governance layer for those identities: ownership, scoping, credential hygiene, reviews, decommissioning, and incident response.

When to use

Establishing or maturing governance for the agent / NHI population — Copilot Studio agents, Foundry agents, custom LLM agents, and the service principals that back them.

Do not use this skill for workload identity federation patterns alone (entra-workload-identity), human identity governance (entra-id-governance), or generic agent build guidance.

Agent identity inventory — know what you're governing

Class Identity model Surface
Copilot Studio agent (M365) Tenant-scoped agent identity + per-user delegated permissions M365 admin center / Copilot Studio
Microsoft Foundry agent Service principal + managed identity + per-user OBO Azure portal / Foundry
Custom AI agent (your code) App registration + workload identity federation / managed identity Entra admin center
Plugin / connector Service principal + delegated/app Graph permissions Entra admin center
Legacy automation service principal App registration, often with secret Entra admin center

Approach

  1. Inventory and tag. Pull every app registration, service principal, and Copilot Studio / Foundry agent. Tag each with:
    • Owner (person + group).
    • Sponsor / business owner.
    • Purpose (one sentence).
    • Data scope (which tenants/sites/mailboxes/resources).
    • Lifecycle stage (pilot / production / sunset).
    • Criticality (tier 0 / 1 / 2). Orphaned identities → freeze them; require owner re-claim.

Read the full file on GitHub · 170 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.

  1. 12d ago First seen · 170 lines · 241 tokens per session scan A f937233b29ae

Subscribe to this mod's changes

agent-identity-governance is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 241 tokens to every session and 2,303 once invoked, about $0.0012 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.

Related

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…

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

generate-run-commands

Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.

microsoft/vscode · 36 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

skill-writing-plans

Create zero-context implementation plans with bite-sized tasks — use for multi-step feature planning.

nyldn/claude-octopus · 21 tokens

bf-to-agents-sdk-dotnet-migration

Use when migrating a Bot Framework .NET SDK bot to Microsoft 365 Agents SDK. Triggered by projects that depend on packages: Microsoft.Bot.Builder or Microsoft.Bot.Builder.Integration.AspNet.Core that want to migrate to Agents SDK.

microsoft/Agents · 56 tokens