diff --git a/examples/workflows/freestyle_planning.toml b/examples/workflows/freestyle_planning.toml
index f97603fd..325088b1 100644
--- a/examples/workflows/freestyle_planning.toml
+++ b/examples/workflows/freestyle_planning.toml
@@ -1,11 +1,13 @@
 id = "freestyle_planning"
 start = "analyst"
 
+# analyst is read-only, so it gets only the read-only task tools: task_search to find related
+# or duplicate work and task_context to ground the analysis in an existing task.
 [[stages]]
 id = "analyst"
 prompt = "prompts/analyst_freestyle.md"
 produces = [{ name = "analysis", kind = "analysis" }]
-allowed_tools = ["file_read", "ShellTool"]
+allowed_tools = ["file_read", "ShellTool", "task_search", "task_context"]
 token_budget = 16384
 max_retries = 2
 
diff --git a/examples/workflows/prompts/analyst_freestyle.md b/examples/workflows/prompts/analyst_freestyle.md
index c0eb7b0f..d1452474 100644
--- a/examples/workflows/prompts/analyst_freestyle.md
+++ b/examples/workflows/prompts/analyst_freestyle.md
@@ -2,6 +2,10 @@ You are the **Analyst** in freestyle mode. Understand the user's goal (in the de
 above) and the code it touches. Read-only: `file_read` (also lists a directory's entries when
 given a directory path), `ls`, `grep`, `cat`, `find`.
 
+Before deriving requirements, check for existing work: `task_search` for related, duplicate, or
+blocking tasks and `task_context` to load any the goal names. Fold what you find into the
+analysis rather than re-deriving it; flag a duplicate instead of restating it.
+
 Emit the `analysis` artifact (JSON, schema provided):
 - `summary`: the goal in your own words.
 - `requirements`: concrete, checkable requirements, one per line.
diff --git a/examples/workflows/review_loop.toml b/examples/workflows/review_loop.toml
index 002029af..0bbd554a 100644
--- a/examples/workflows/review_loop.toml
+++ b/examples/workflows/review_loop.toml
@@ -14,19 +14,24 @@
 id = "review_loop"
 start = "implement"
 
+# implement owns the work item across the loop: claim before starting, submit_for_review once
+# the patch is ready, add notes (task_create one first if the work warrants tracking).
 [[stages]]
 id = "implement"
 prompt = "prompts/implement.md"
 produces = [{ name = "patch", kind = "file_written" }]
-allowed_tools = ["file_write"]
+allowed_tools = ["file_write", "task_create", "task_update", "task_context", "task_search"]
 token_budget = 8192
 max_retries = 3
 
+# review reads the task's own acceptance criteria (task_context) and completes it on an approved
+# verdict (task_update action=complete); on changes_requested it leaves the task claimed.
 [[stages]]
 id = "review"
 prompt = "prompts/review.md"
 needs = ["patch"]
 produces = [{ name = "review_report", kind = "review_report" }]
+allowed_tools = ["task_context", "task_update"]
 token_budget = 8192
 max_retries = 3