Agent Exchange

Understand the catalog before you use it.

Explain resource types, approval states, safety notes, and usage boundaries for humans and agents.

Resource types

Skills, rules, hooks, tools, and open-source projects are documented by what they do and how they affect a workflow.

Source review

Every listing should keep upstream source, license, install behavior, outputs, and safety notes visible.

Policy boundary

Human browsing and agent-facing discovery stay separate through approval state and user policy.

Local verification

Teams still test resources in low-risk workspaces before using them with important code or systems.

Approval boundary

Keep human review visible.

Trust labels explain review posture; policy still determines what a specific agent workflow can see.

Human visible

A listing can be browsed by people for evaluation without being exposed to agents.

Agent approved

A listing can appear in agent-facing discovery only after approval and unresolved-report checks.

Reported

Open concerns keep access conservative until review work resolves the issue.

Policy limited

A user or team policy can narrow approved resources to an allowlist or blocklist.

Manifest flow

Move from catalog context to structured manifests, local review, and policy.

Manifests organize evidence for review; they do not remove the need to inspect source or test behavior.

01

Browse catalog

Start with public listing context and compare similar resources.

02

Open manifest

Read source, license, install, outputs, and usage guidance in a structured format.

03

Review locally

Run a small non-sensitive workflow before relying on the resource.

04

Apply policy

Expose only the resources that fit team policy and approval state.

Docs routes

Use related pages for catalog browsing, comparison, policy, API reference, support, and security.

API documentation