docs: move the agent tool docs to 4-implementation/agent-tools

docs/4-implementation/turn-loop/mcp.md

@@ -20,7 +20,7 @@ entry on the schema's stdio default — it spawns
 the tools land in claude as
 `mcp__hyperhive__<tool>`. Each entry also has an `availableToSubagents`
 toggle (default `false`) — see
-[`docs/2-handbook/tools/subagent.md`](../../2-handbook/tools/subagent.md#mcp-servers-available-to-a-subagent)
+[`docs/4-implementation/agent-tools/subagent.md`](../agent-tools/subagent.md#mcp-servers-available-to-a-subagent)
 for what reaches a subagent's own `--mcp-config` and what doesn't.
 An `"http"` entry that needs request headers (a bearer-authenticated remote
 server) sets `headersFile` to an absolute path: a file holding a JSON object
@@ -48,7 +48,7 @@ runs on the change.
   (default: empty = unrestricted) limits which names `send` accepts —
   useful for sandboxing. The broker refuses `to: "operator"`. The error
   points an agent that has the matrix MCP tools at matrix
-  ([matrix](../../2-handbook/tools/matrix.md)), and tells one without them that the
+  ([matrix](../agent-tools/matrix.md)), and tells one without them that the
   operator reads its `set_status` line, its turn output on the dashboard,
   and its logs.
 - `recv` — drain inbox. Always an immediate peek, never blocks. `max`
@@ -139,11 +139,11 @@ hive_name?, swarm_name?, matrix_accounts? }`. `matrix_accounts` is a
 ## Privileged tools (by permission)
 
 - **Bash execution** (`execution`) — background shell tasks. See
-  [`docs/2-handbook/tools/bash.md`](../../2-handbook/tools/bash.md).
+  [`docs/4-implementation/agent-tools/bash.md`](../agent-tools/bash.md).
 - **Subagent spawning** — nested sessions on the agent's own runtime
   (claude or ACP, via `hive-runtime`) as background tasks, shipped
   default-on like bash execution; no permission gates it. See
-  [`docs/2-handbook/tools/subagent.md`](../../2-handbook/tools/subagent.md).
+  [`docs/4-implementation/agent-tools/subagent.md`](../agent-tools/subagent.md).
 - **Config changes** — no permission: they go through a forge PR on
   `agent-configs/<name>` — see
   [`docs/2-handbook/agent-lifecycle/config-changes.md`](../../2-handbook/agent-lifecycle/config-changes.md).
@@ -155,14 +155,14 @@ hive_name?, swarm_name?, matrix_accounts? }`. `matrix_accounts` is a
   [`docs/5-project/process/conventions.md#permissions`](../../5-project/process/conventions.md).
 - **Matrix MCP + extra servers** — `mcp__matrix__*` tools and
   per-agent extra MCP config. See
-  [`docs/2-handbook/tools/matrix.md`](../../2-handbook/tools/matrix.md).
+  [`docs/4-implementation/agent-tools/matrix.md`](../agent-tools/matrix.md).
 
 ## Waking the agent from inside the container
 
 The built-in producers (matrix, bash, forge) upsert a todo on the
 harness's in-agent socket (`HIVE_AGENT_SOCKET`, `UpsertTodo` — see
-[`docs/2-handbook/tools/bash.md` § Completion as a todo
-(loose-ends v2)](../../2-handbook/tools/bash.md#completion-as-a-todo-loose-ends-v2)
+[`docs/4-implementation/agent-tools/bash.md` § Completion as a todo
+(loose-ends v2)](../agent-tools/bash.md#completion-as-a-todo-loose-ends-v2)
 for the full upsert/signal/clear mechanism): a new or changed summary
 makes the harness signal its own turn loop, with no hive-c0re
 round-trip. An external MCP server (or any other in-container process)
@@ -205,7 +205,7 @@ The built-in list and the `--tools` value it resolves to live in
 `hive-sh4re` (the `Permission` enum itself is in `hive-types`), not in the
 harness, because the
 subagent daemon spawns its own `claude` and must resolve the same set —
-see [`docs/2-handbook/tools/subagent.md`](../../2-handbook/tools/subagent.md).
+see [`docs/4-implementation/agent-tools/subagent.md`](../agent-tools/subagent.md).
 
 - Allowed built-ins: `Edit`, `Glob`, `Grep`, `Read`, `Skill`, `Write`.
   `Skill` is what makes an installed plugin's `SKILL.md` invokable —