Skip to content

The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.

docs(agent-harness): drop delegate tools from coordination link

Steven Enamakel5abeee0c1456
diff --git a/docs/gitbooks/en/developing/architecture/agent-harness.md b/docs/gitbooks/en/developing/architecture/agent-harness.md
index 13280b0506..023f2b0bcb 100644
--- a/docs/gitbooks/en/developing/architecture/agent-harness.md
+++ b/docs/gitbooks/en/developing/architecture/agent-harness.md
@@ -706,4 +706,4 @@ Goals and todos are crate-backed outright, with no shadow: thread goals live in
- [Architecture overview](README.md): where the harness sits in the bigger picture.
- [Memory](../../features/memory.md) and [Memory architecture](memory.md): the `memory` tool, the per-turn memory lifecycle and conversation logging.
- [Automatic model routing](../../features/model-routing/README.md): how `model: "hint:reasoning"` resolves to a concrete provider+model.
-- [Native tools: agent coordination](../../features/native-tools/agent-coordination.md): the user-facing surface for `spawn_subagent`, `delegate_*`, `todo`.
+- [Native tools: agent coordination](../../features/native-tools/agent-coordination.md): the user-facing surface for `spawn_subagent` and `todo`.