Wendy Aaa Interop logo

Wendy Aaa Interop

Organization
wendylabsinc
wendy-aaa-interop

Expert guidance on the AAA contract between the wendy stack and the SaaS stack (wendy-auth, Wendy Cloud, pki-core, wendy-proxy). Use when developers mention: (1) AAA contract or two-key authority, (2) interop between wendy-agent/wendyos and pki-core, cloud, or wendy-auth, (3) who owns authentication vs authorization vs issuance, (4) SPIFFE identities or credential shapes, (5) signed grants, SETs, or operator-signed requests, (6) the inter-service fabric or SSF signal channel, (7) correlation_id propagation, (8) platform cap or tenant ceiling.

Overview

Publisherwendylabsinc
Repositoryclaude-skills
Skill namewendy-aaa-interop
Stars
62
Forks
5
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by wendylabsinc on GitHub. Read the source before you install it.

Installation

Install the Wendy Aaa Interop AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/wendylabsinc/claude-skills/tree/main/wendy-aaa-interop
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/wendylabsinc/claude-skills.git /tmp/claude-skills
mkdir -p .claude/skills
cp -r /tmp/claude-skills/wendy-aaa-interop .claude/skills/wendy-aaa-interop
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wendy Aaa Interop in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wendy Aaa Interop on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wendy Aaa Interop is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Wendy AAA Interop

The AAA contract defines who is trusted for what across the control-plane services (wendy-auth, Wendy Cloud, pki-core, wendy-proxy) and the cryptographic invariants that hold even when one of them is compromised. It exists because Wendy serves critical-infrastructure partners: a breach of the SaaS control plane must never translate into the ability to act on a customer's fleet (§1).

Responsibility Split

ServiceOwnsDoes NOT own
wendy-authAuthentication; the identity graph (tenant + user + group(s)); IdP federation; issuance of identity assertions (tokens/SETs); the realm's own lifecycle (creation, tenant-identity minting, suspension, deletion) and exclusive ownership of a verified email domainAuthorization decisions; certificates; entitlements
Wendy CloudAuthorization (group→role→entitlement mapping) + org-native lifecycle within a tenant + orchestrationAuthentication of humans; minting any private key or certificate; minting tenant identity; initiating realm creation, suspension, or deletion
pki-coreCertificate issuance/revocation; enforcement of the platform + per-tenant policy ceiling; the cryptographic root of tenant isolationDeciding who a principal is (defers to wendy-auth) or what they may do (defers to cloud), except as bounded by policy caps
wendy-proxyPure enforcement: fronting the image registries, deriving tenant scope from the device cert, enforcing a live per-device image assignmentAny issuance; any authorization decision of its own

(§1)

Two-Key Authority

authority(action) = identity(wendy-auth) ∩ authorization(cloud) ∩ policy-cap(pki-core)

No single party manufactures authority (§3):

Party alone has……and is missingResult
Cloud: the authorization decisionthe principal's key / signaturecannot get a credential issued that acts as the principal
Principal: identity + keyauthority beyond what cloud grantscannot self-escalate past cloud's grant
pki-core: issuance powerboth proofs (it refuses without them)mints only under identity ∩ authorization, capped by policy

The Two Guarantees

  • (A) Non-impersonation — strong, cryptographic. No single service can act as a user, operator, or device.
  • (B) Non-escalation of a present principal — bounded, not absolute. Cloud is the authorization authority, so a compromised cloud can inflate a legitimately-authenticating principal's authority, but only up to the platform hard cap.

State guarantee (B) honestly; never claim more (§2).

Authority Is Never Transport-Derived

Transport (mTLS peer, or GCP-WI-OIDC on the inter-service fabric) names the service making the call — never a principal's authority. Principal authority always rides as an in-message signed artifact: a wendy-auth token, an operator signature + CSR, a cloud grant, a TSA token, or a SET. A relay (e.g. cloud carrying an operator request to pki-core) can withhold that artifact, but never forge it (§4.3, §11.1).

Two Credential Shapes

  • Cloud-facing = identity-only. Carries the SPIFFE identity, no entitlements. Cloud authorizes live against its own mutable state — more containable than a baked-in snapshot; embedding entitlements here would only make a stolen key harder to contain.
  • Entitlement-bearing operator credential, obtained through cloud = for direct operator→device access (field/USB). An operator never holds a device certificate; cloud attaches an authorization grant and pki-core embeds the entitlements in this operator cert, used only when no cloud is in the loop at use time. The offline enforcement point has no live authz to consult, so entitlements travel with the credential: grammar entitlement:{category}:{permission}:{effect}, deny-wins, vocabulary = the wendy-agent gRPC method set ∪ cloud-defined entitlements. The cloud-mediated device path (postbox polling §5.3, image pull §5.7) uses an identity-only device cert + operator-signed requests / live checks instead.

(§4.2)

correlation_id

One id per end-to-end flow, not per service and not per mutation: each service adopts the inbound id if the request already carries one, mints a fresh id only when it is the true origin, and propagates it unchanged on every downstream call — persisting it into every audit record and every emitted signal for that flow. Never regenerate mid-flow (§11.2).

Self-Hosted Rule (mandatory)

The wendy stack (wendyos / wendy-agent) must ALWAYS be able to run without the SaaS stack. Before shipping any interop change, consult the wendy-self-hosted skill: keep the self-hosted path intact, or create it where it doesn't exist yet. A SaaS-only feature is an incomplete feature.

Source of Truth

This skill distills the AAA Contract v0.21 (Approved 2026-08-29). The living contract lives in Linear: AAA Contract — Authentication, Authorization, Accounting. It is versioned and evolving: check it for flow-level detail, and if it disagrees with this skill, the contract wins — then update this skill.

Related Skills

  • wendy-certificates — requesting and holding certificates.
  • wendy-device-enrollment — device lifecycle (first touch through recovery).
  • wendy-device-interop — agent runtime behavior against the postbox and image pull.
  • wendy-security-baselines — invariants any interop PR must respect.
  • wendy-self-hosted — the mandatory dual-path (SaaS + self-hosted) rule.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Wendy Aaa Interop AI skill do?

Expert guidance on the AAA contract between the wendy stack and the SaaS stack (wendy-auth, Wendy Cloud, pki-core, wendy-proxy). Use when developers mention: (1) AAA contract or two-key authority, (2) interop between wendy-agent/wendyos and pki-core, cloud, or wendy-auth, (3) who owns authentication vs authorization vs issuance, (4) SPIFFE identities or credential shapes, (5) signed grants, SETs, or operator-signed requests, (6) the inter-service fabric or SSF signal channel, (7) correlation_id propagation, (8) platform cap or tenant ceiling.

Why use Wendy Aaa Interop on TypingMind?

Because you install it once and use it with any model. Wendy Aaa Interop is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wendy Aaa Interop in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wendylabsinc/claude-skills/tree/main/wendy-aaa-interop. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Wendy Aaa Interop?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wendy Aaa Interop?

As many as you like. As long as a model supports skills, you can use Wendy Aaa Interop with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wendy Aaa Interop AI skill free?

It is published on GitHub by wendylabsinc. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇