merge: AgentProject membership — the junction is now load-bearing

Merges feat/agent-project-membership (task 166/152). An agent can finally join
many projects: membership routes, per-membership role and optional brain
override, chat resolving context from the membership, and CLI attach-agent /
detach-agent / get memberships. The legacy Agent.projectId fallback is kept for
this release as the schema comment promises.

Conflict resolved in main.ts: that branch added its RBAC case to
mapUrlToPermission inline, while this branch had extracted the function to
middleware/url-permission.ts so it could be tested. Kept the extraction and
ported the case into it — joining a team is `edit:agents:<name>`, not
`create:agents`, which is the authority to mint a whole agent.

Also fixes something the extraction makes possible. security.test.ts contained a
hand-copied reproduction of mapUrlToPermission, because main.ts self-invokes
main() and nothing in it was importable. A security test asserting against a
copy stops testing the system the moment the real one changes, and this copy had
already drifted. It now imports the real function; all 18 assertions still pass,
against the code that actually runs.

Local: build clean, workspace 2550 passed, lint unchanged at 794 errors.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4wNHWf7xSwnZCWpJcyv9p

.taskmaster/tasks/task_059.md

@@ -0,0 +1,64 @@
+# Task ID: 59
+
+**Title:** Update CLI create prompt command for priority and link
+
+**Status:** done
+
+**Dependencies:** 40 ✓
+
+**Priority:** medium
+
+**Description:** Extend the mcpctl create prompt command to accept --priority (1-10) and --link (project/server:uri) flags.
+
+**Details:**
+
+1. Update `/src/cli/src/commands/create.ts` for prompt:
+   ```typescript
+   .command('prompt <name>')
+   .description('Create a new prompt')
+   .option('-p, --project <name>', 'Project to create prompt in')
+   .option('--priority <number>', 'Priority level (1-10, default: 5)', '5')
+   .option('--link <target>', 'Link to MCP resource (project/server:uri)')
+   .option('-f, --file <path>', 'Read content from file')
+   .action(async (name, options) => {
+     const priority = parseInt(options.priority, 10);
+     if (priority < 1 || priority > 10) {
+       console.error('Priority must be between 1 and 10');
+       process.exit(1);
+     }
+     
+     let content = '';
+     if (options.link) {
+       // Linked prompts don't need content (fetched from source)
+       content = `[Link: ${options.link}]`;
+     } else if (options.file) {
+       content = await fs.readFile(options.file, 'utf-8');
+     } else {
+       content = await promptForContent();
+     }
+     
+     const body = {
+       name,
+       content,
+       projectId: options.project,
+       priority,
+       linkTarget: options.link,
+     };
+     
+     await api.post('/api/v1/prompts', body);
+   });
+   ```
+
+2. Validate link format: `project/server:resource-uri`
+
+3. Add shell completions for new flags
+
+**Test Strategy:**
+
+- Unit test: --priority flag sets prompt priority
+- Unit test: --priority validation (1-10 range)
+- Unit test: --link flag sets linkTarget
+- Unit test: --link validation (format check)
+- Unit test: Linked prompt skips content prompt
+- Unit test: Default priority is 5
+- Integration test: End-to-end create with flags