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_049.md

@@ -0,0 +1,58 @@
+# Task ID: 49
+
+**Title:** Implement read_prompts tool for ongoing retrieval
+
+**Status:** done
+
+**Dependencies:** 48 ✓
+
+**Priority:** high
+
+**Description:** Create the read_prompts MCP tool that allows clients to request additional context by keywords after the session is ungated.
+
+**Details:**
+
+1. Add read_prompts tool definition:
+   ```typescript
+   private getReadPromptsTool(): Tool {
+     return {
+       name: 'read_prompts',
+       description: 'Request additional project context by keywords. Use this whenever you need guidelines, policies, or conventions related to your current work.',
+       inputSchema: {
+         type: 'object',
+         properties: {
+           tags: {
+             type: 'array',
+             items: { type: 'string' },
+             description: 'Keywords describing what context you need'
+           }
+         },
+         required: ['tags']
+       }
+     };
+   }
+   ```
+
+2. Implement read_prompts handler:
+   - Always use keyword matching (not LLM) for precision
+   - Exclude already-retrieved prompts from response
+   - Add newly retrieved prompts to session state
+   - Include reminder about more prompts available
+
+3. Response format:
+   ```
+   [Matched prompt content - deduplicated]
+   
+   Remember: you can request more prompts at any time with read_prompts({ tags: [...] }).
+   The project may have additional guidelines relevant to your current approach.
+   ```
+
+**Test Strategy:**
+
+- Unit test: read_prompts returns matched prompts by keyword
+- Unit test: Already retrieved prompts excluded from response
+- Unit test: Newly retrieved prompts added to session state
+- Unit test: Response includes reminder text
+- Unit test: read_prompts while gated returns error
+- Unit test: Empty tags returns empty response
+- Unit test: Uses keyword matching not LLM