Terminal
Terminal/Skill
Walks you through connecting Agent Security, reviewing native tool access, adding blocks in the Ory Console, and moving to enforce.
By Ory
Works with
npx skills add ory/claude-plugins --skill ory-permissions-onboardingHelp the user connect Agent Security and roll out explicit native-tool blocks without treating missing grants as denials.
The plugin only reads permissions. It never writes them. The permission model, native-tool blocks, MCP grants, and observe/enforce posture are managed in the Ory Console (Agent Security).
Native policy is simple:
AgentTool and ShellTool have no users relation.use permit is !blockedSubjects.includes(subject).observe logs the block and proceeds; enforce vetoes the call.PermissionMode#enforcedSubjects remain grant-based.Copy the connection details shown in the Ory Console under Agent Security:
npx -y -p @ory/claude-code ory-claude configure --project-url <URL> --agent-security-url <URL>
Then inspect the resolved configuration:
npx -y -p @ory/claude-code ory-claude status
Confirm that Agent Security is connected and the public OAuth2 login client is resolved. The plugin needs no workspace privilege or project API key.
npx -y -p @ory/claude-code ory-claude permissions
The report shows:
allowed, blocked, or errored.A fresh project normally reports native tools as allowed. There is no grant
coverage step and the local seed writes no baseline AgentTool or ShellTool
grants.
To block a native tool, write a blockedSubjects relation in the Ory Console:
namespace: AgentTool
object: <tool name> e.g. WebFetch
relation: blockedSubjects
subject: User:<id>
To block a command word reached through a shell tool:
namespace: ShellTool
object: <command word> e.g. curl
relation: blockedSubjects
subject: User:<id>
Blocks can also target the project, an agent credential, an agent session, a sub-agent credential, or a sub-agent spawn. Group/SubjectSet expansion is supported. A native deny is always an explicit block, never a missing grant.
MCP is intentionally different: continue granting MCP server/tool access with
its existing users/use and invoke relations.
While the project is in observe, run normal sessions and inspect:
npx -y -p @ory/claude-code ory-claude permissions
npx -y -p @ory/claude-code ory-claude watch
Matching blocks emit permission.block_observed but the tool still runs. Review
those events, then promote the project or selected principals to enforce in
the Ory Console. Every gate reads the project-controlled posture.
Under enforce:
ShellTool word blocks the outer shell command and names the word.If a tool is unexpectedly blocked, use npx -y -p @ory/claude-code ory-claude permissions to identify the
block and remove or narrow its blockedSubjects relation in the Console.
| Command | Effect |
|---|---|
npx -y -p @ory/claude-code ory-claude configure --project-url <URL> --agent-security-url <URL> | Connect Agent Security. |
npx -y -p @ory/claude-code ory-claude configure --disconnect | Disconnect sign-in and permission checks. |
npx -y -p @ory/claude-code ory-claude permissions | Print live mode plus native allowed/blocked state. Read-only. |
npx -y -p @ory/claude-code ory-claude status | Print configuration, identities, native tool access, and recent activity. |
For authentication and subject-resolution details, see /project:ory-auth-setup and
/project:ory-login-flow.