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 Cratis/AI --skill cratis-arc-authentication-authorization-and-identitygit clone --depth 1 https://github.com/Cratis/AIWrote 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/cratis/ai/cratis-arc-authentication-authorization-and-identity)<a href="https://agentmods.dev/skills/cratis/ai/cratis-arc-authentication-authorization-and-identity"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-arc-authentication-authorization-and-identity/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/cratis/ai/cratis-arc-authentication-authorization-and-identity"><img src="https://agentmods.dev/badge/skills/cratis/ai/cratis-arc-authentication-authorization-and-identity.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 | $0.00040 | $0.03685 |
| Opus 5.5 | $0.00016 | $0.01474 |
| Sonnet 5.5 | $0.00008 | $0.00737 |
| Haiku 4.5 | $0.00004 | $0.00368 |
Grade A, and why
cratis-arc-authentication-authorization-and-identity 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 2d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authentication, authorization and identity in Arc
Arc separates three things that are easy to conflate: authentication decides who the caller is, authorization decides whether that caller may run this command or query, and the identity provider decides what the frontend is told about them. Each has its own extension point.
Verified product sources
Read references/product-sources.md when you need the owning package for an identity type.
Authorization capabilities arrived over time: named policies, schemes, fallback baselines, guest policies and Microsoft-attribute enforcement all need a recent Arc. authorization lists the requirements; check them if you run an older version.
Read this first: what is and is not trusted
Arc's shipped authentication reads a forwarded principal from HTTP headers.
x-ms-client-principal is base64, not a signature, and Arc does not check
who sent it. Any caller that can reach the application can author the entire
serialized principal.
That is not a defect — it is the EasyAuth/reverse-proxy model, where the ingress is the trust boundary. But it means:
- the application must be unreachable except through the ingress that sets those headers, and that ingress must authenticate callers, strip any caller-supplied identity headers, write its own trusted replacements, and block direct access to the backend;
- nothing Arc gives you makes the forwarded values authentic;
- Arc ships no OpenID Connect and no JWT bearer integration. If you need the application itself to validate a token, that is ordinary ASP.NET Core authentication you configure yourself.
Requires Arc 22.43.0 for secure forwarded-header handling. On an older Arc the unsigned identity headers are trusted from any caller who can reach the host; upgrade, or make the ingress the only path to the backend.
Forwarded identity headers are ignored unless the host opts
in with Cratis:Arc:TrustForwardedIdentityHeaders=true or
builder.AddCratis(options => options.TrustForwardedIdentityHeaders = true).
Header-only requests otherwise remain anonymous. AddCratis() still registers
the header scheme; it does not make the headers trusted. Opt in only behind the
ingress above, otherwise configure a credential-validating scheme. The old
Introspection:TrustForwardedIdentityHeaders setting is obsolete and enables the
same host-wide flag. See authentication.
Source: secure defaults.
What ships with it
10 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.
- LICENSE 142 B
- references/authentication.md 9.2 KB
- references/authorization.md 18 KB
- references/authproxy.md 5.1 KB
- references/frontend.md 5.0 KB
- references/identity-endpoints.md 2.7 KB
- references/local-development.md 3.7 KB
- references/observable-emission-guards.md 6.1 KB
- references/product-sources.md 610 B
- references/tenancy.md 4.7 KB
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.
- 2d ago Changed · -89 tokens per session a430fdde20ac
- 3d ago Changed · +8 lines a535732e321b
- 12d ago Changed · +5 lines 7d7378fe374b
- 15d ago Changed · -71 lines 38b59aec6daf
- 16d ago Changed · -4 lines 9352444ef84b
- 20d ago Changed · +4 lines e72ede6ddc9d
- 27d ago Changed · +111 lines · +22 tokens per session e68ee1709c42
- 1mo ago Changed · +2 lines 23bbbac062d9
- 1mo ago First seen · 234 lines · 107 tokens per session scan A ecc33a5d4e9c
cratis-arc-authentication-authorization-and-identity is a skill published in the GitHub repository Cratis/AI (4 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 3,685 once invoked, about $0.0002 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 2026-09-06.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…