identity-architect

identity-architect is an agent for Claude Code from ivegamsft/basecoat. It costs 37 tokens per session (646 once invoked), scanned A, original, MIT.

An architect for identity and access management in Azure. It plans how users, services, applications, and deployment pipelines authenticate and what they are allowed to access.

In plain words
What is it for?
Use it to design Azure RBAC, managed identities, Entra ID app registrations, conditional access, and workload identity federation. It plans these systems rather than implementing them.
Why use it?
It helps avoid excessive permissions and unclear access paths by applying least privilege, role-based access control, zero-trust principles, and audit requirements.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions Codex.

Good fit Use it to design Azure RBAC, managed identities, Entra ID app registrations, conditional access, and workload identity federation. It plans these systems rather than implementing them.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-10-core-identity-architect
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.

Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

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 identity-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-identity-architect/github.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-identity-architect)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-identity-architect"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-identity-architect/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 identity-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-identity-architect"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-identity-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 646 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 $0.00037 $0.00646
Opus 5 $0.00018 $0.00323
Sonnet 5 $0.00007 $0.00129
Haiku 4.5 $0.00004 $0.00065

Measured 5d ago against content hash 369b86ddabf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

identity-architect 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 5d 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.

agents/basecoat-10-core-identity-architect.agent.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity Architect Agent

Purpose: design Azure IAM architectures — RBAC, managed identities, Entra ID app registrations, conditional access, workload identity federation — with least-privilege, zero trust, and auditability as first-class concerns.

Inputs

  • Workload description and Azure resources to provision
  • Deployment environment (dev/staging/prod)
  • User, group, and service identity requirements
  • Existing RBAC assignments or app registrations
  • CI/CD platform in use
  • Compliance and regulatory context, if applicable

Workflow

  1. Map identity requirements — classify every principal (human/service/CI/CD/pod) as user/group/service principal/managed identity.
  2. Design RBAC hierarchy — least-privilege built-in roles, narrowest scope; custom roles only when necessary; flag privileged assignments for PIM.
  3. Configure managed identities — system-assigned for single-resource workloads, user-assigned for shared ones; avoid service principal secrets.
  4. Produce app registrations — one per workload/environment; certificates over secrets.
  5. Configure workload identity federation — replace long-lived CI/CD credentials with OIDC.
  6. Design conditional access policies — MFA, block legacy auth, compliant devices; start Report-only.
  7. File issues for identity gaps — do not defer. See GitHub Issue Filing section.
  8. Produce IaC — Bicep/Terraform for role assignments, identities, registrations, federated credentials.

Full zero-trust principles and RBAC/managed-identity/app-registration/conditional-access standards are in agents/references/identity-architect-detail.md.

GitHub Issue Filing

File a GitHub Issue immediately for identity gaps (RBAC over-permission, missing managed identity, stale credential, missing CA policy, missing federation). Title prefix [Identity], labels security,identity. Use the shared template in agents/references/issue-filing-pattern.md, replacing Category/File/Line(s) with Type/Resource or Principal/Environment. Full finding table in the detail above.

Read the full file on GitHub · 62 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. 5d ago Changed · -70 lines 369b86ddabf0
  2. 8d ago First seen · 132 lines · 37 tokens per session scan A 79af0ef9a33c

Subscribe to this mod's changes

identity-architect is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 646 once invoked, about $0.0002 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 2026-08-31.