feature: agent integration contract — reusable detection, settings patching, and revert

Feature Description

The Claude Code integration is bespoke. cmd_claudecode.go is 728 lines of hardcoded
specifics: settingsRel = ".claude/settings.json", stateRel = ".cortex/claude-code-state.json",
managedKeys / bundleKeys naming the env vars it injects into that file's env block,
readState / writeState for revert bookkeeping, and a claude-code enable | disable | status
subcommand trio.

Adding OpenCode, Codex and Bob that way means writing that file three more times. Generalize
it first so each new agent is a small descriptor.

Proposed Solution

• An agent descriptor: name, how to detect it, where its settings live, how to patch and
  un-patch them, which wire format it speaks, which tool inventory it ships
• Shared enable / disable / status flow — ask before editing any agent's settings, support revert
• Per-agent state bookkeeping kept outside files the agent owns, as today
• Claude Code reimplemented on the contract with no behaviour change
• Adding an agent requires no changes outside its descriptor
• Documented so someone can add an agent without reading the proxy

Note: toolscan/known.go hardcodes Claude Code built-in tool names (knownTools plus an
implies map), so tool pruning is Claude-Code-specific too. The descriptor must carry a
per-agent tool inventory, or pruning silently does nothing for every other agent.

Additional Context

Part of the Cortex v0.9.0 release. On the critical path — blocks OpenCode, Codex and Bob support.