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 Youngmaidainon/Agent-Level-Up --skill attacking-entra-id-with-roadtoolsgit clone --depth 1 https://github.com/Youngmaidainon/Agent-Level-UpWrote 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/youngmaidainon/agent-level-up/attacking-entra-id-with-roadtools)<a href="https://agentmods.dev/skills/youngmaidainon/agent-level-up/attacking-entra-id-with-roadtools"><img src="https://agentmods.dev/badge/skills/youngmaidainon/agent-level-up/attacking-entra-id-with-roadtools/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/youngmaidainon/agent-level-up/attacking-entra-id-with-roadtools"><img src="https://agentmods.dev/badge/skills/youngmaidainon/agent-level-up/attacking-entra-id-with-roadtools.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 | $0.00071 | $0.02077 |
| Opus 5 | $0.00036 | $0.01038 |
| Sonnet 5 | $0.00014 | $0.00415 |
| Haiku 4.5 | $0.00007 | $0.00208 |
Grade A, and why
attacking-entra-id-with-roadtools 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 8d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attacking Entra ID with ROADtools
Authorized use only: ROADtools interacts with live Microsoft Entra ID (Azure AD) tenants and can register devices, mint and exchange tokens, and enumerate directory objects. Use it solely against tenants you own or are explicitly authorized in writing to test. Unauthorized access to a cloud tenant is illegal.
Overview
ROADtools (by Dirk-jan Mollema) is the de facto offensive toolkit for Microsoft Entra ID. It has two main components:
- ROADrecon — authenticates to Entra ID, gathers the full directory into a local SQLite database via the Azure AD Graph API, and serves an Angular GUI to explore users, groups, roles, applications, service principals, conditional-access policies, and device objects offline. A plugin system exports to BloodHound and analyzes CA policies.
- roadtx (ROADtools Token eXchange) — acquires and exchanges Entra-issued tokens across the many OAuth flows (ROPC, device code, auth-code, refresh-token exchange, app/federated app), performs device registration, and handles Primary Refresh Token (PRT) operations including PRT-based SSO and cookie minting. Its FOCI (Family of Client IDs) awareness lets a refresh token for one first-party client be redeemed for another resource.
Together they cover the Discovery phase against cloud identity: enumerate the tenant (T1087.004 Account Discovery: Cloud Account) and obtain/manipulate the tokens needed to reach Microsoft Graph, Azure Resource Manager, and other resources. ROADrecon's offline database makes recon stealthy and fast; roadtx makes token theft, PRT abuse, and cross-resource pivoting practical.
When to Use
- During an authorized Azure / Entra ID red-team or cloud penetration test.
- When you have a foothold credential, refresh token, or PRT and need to enumerate the tenant.
- When you must pivot a token from one resource (e.g., Azure CLI) to another (e.g., Microsoft Graph).
- When validating that conditional-access, device-compliance, and token controls actually constrain an attacker.
- When mapping Entra attack paths (export to BloodHound for graph analysis).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 207 lines · 71 tokens per session scan A cfdc1d07240f
attacking-entra-id-with-roadtools is a skill published in the GitHub repository Youngmaidainon/Agent-Level-Up (3 stars, last pushed 17d ago), licensed MIT. It adds 71 tokens to every session and 2,077 once invoked, about $0.0004 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
detecting-oauth-token-theft
Detects and responds to OAuth token theft and replay attacks in cloud environments, focusing on Microsoft Entra ID (Azure AD) token protection, conditional access policies, and sign-in anomaly detection. Covers access token theft, refresh token replay, Primary Refresh Token (PRT) abuse, and pass-the-cookie attacks.…
database-migrations-migration-observability
Migration monitoring, CDC, and observability infrastructure.
database-migration
Execute database migrations across ORMs and platforms with zero-downtime strategies, data transformation, and rollback procedures. Use when migrating databases, changing schemas, performing data transformations, or implementing zero-downtime deployment strategies.
cloudflare-d1
Cloudflare D1 serverless SQLite on edge. Use for databases, migrations, bindings, or encountering D1ERROR, statement too long, too many requests queued errors.
cloudflare-vectorize
Cloudflare Vectorize vector database for semantic search and RAG. Use for vector indexes, embeddings, similarity search, or encountering dimension mismatches, filter errors.
bun-redis
Use when working with Redis in Bun (ioredis, Upstash), caching, pub/sub, session storage, or key-value operations.