templates: the agent system prompt is a Jinja template, rendered through hive-template

system.md carries {{ label }}-style variables and an {% if not archetype %} block in place of the config:repo / config:archetype marker pairs, so prompt.rs drops its line filter, marker parsers and string replaces. The rendered prompt is byte for byte the old one for a custom agent, an archetype agent and an empty archetype name, with and without hive, swarm, docs and operators. hive-template now drops a block tag's own line.

docs/2-handbook/agents/agent-roster.md

@@ -105,16 +105,9 @@ state dirs work as for every other agent.
   `/agents/<name>/state` (so it can manage any agent's state dir; config
   isn't mounted, since a real config change is a PR from a clone), plus an RO mount for
   `/meta` (the hive's topology and limits files). Any agent holding it gets the same mounts.
-- **Prompt** — identical for every container but one block (below):
-  `prompts/system.md`
-  carries `<!-- role:agent -->` / `<!-- role:manager -->` marker
-  blocks, and `prompt::render` filters for `"agent"` unconditionally,
-  manager included ("always `agent` role — there is only one role",
-  `hive-agent/src/prompt.rs`'s own module doc). The `role:manager`
-  blocks are dead in production, exercised only by a unit test
-  (`filter_blocks(SAMPLE, "role", "manager")`). The one block that differs
-  is `<!-- config:repo -->` vs `<!-- config:archetype -->`: an agent built
-  from an [archetype](../swarm/archetypes.md) is told it has no config repo.
+- **Prompt** — identical for every container but one paragraph: an agent
+  built from an [archetype](../swarm/archetypes.md) is told it has no config
+  repo, every other agent is told how to propose changes to its own.
 - **Tool allow-list** — the MCP tools claude sees come from the agent's
   permissions alone, the same mechanism for every agent
   ([`docs/4-implementation/turn-loop/mcp.md`](../../4-implementation/turn-loop/mcp.md)). Ruth's permissions