diff --git a/agents/README.md b/agents/README.md
index 2df8ea7..3f91c67 100644
--- a/agents/README.md
+++ b/agents/README.md
@@ -12,7 +12,7 @@ Coding-focused agent. Extends default with agent instructions covering code modi
 
 ## System prompt
 
-There is no built-in system prompt. The system prompt is assembled entirely from `agentSpawn` hook output. Both agents use `$OLLIE/x/prime <name>` to inject prompt template files from `p/` in order. `coding` additionally injects `08_tool-elevate` (relevant only with `execute_elevated_bash`) and omits it from `default`.
+There is no built-in system prompt. The system prompt is assembled entirely from `agentSpawn` hook output. Both agents use `$OLLIE/x/prime <name>` to inject prompt template files from `p/`. `coding` additionally injects `tools-elevate` (relevant only with `execute_elevated_bash`) and omits it from `default`.
 
 `bd prime` is appended last in both agents — it injects the active [beads](https://github.com/lneely/beads) context if a database is found, and silently does nothing otherwise.
 
diff --git a/agents/coding.json b/agents/coding.json
index 1f230c3..9cb6928 100644
--- a/agents/coding.json
+++ b/agents/coding.json
@@ -15,14 +15,14 @@
 	],
 	"hooks": {
 		"agentSpawn": [
-			"$OLLIE/x/prime 00_base",
-			"$OLLIE/x/prime 01_ollie",
-			"$OLLIE/x/prime 02_skills",
-			"$OLLIE/x/prime 03_tool-files",
-			"$OLLIE/x/prime 04_tool-reasoning",
-			"$OLLIE/x/prime 05_tool-memory",
-			"$OLLIE/x/prime 07_tool-subagents",
-			"$OLLIE/x/prime 08_tool-elevate",
+			"$OLLIE/x/prime sys-base",
+			"$OLLIE/x/prime sys-ollie",
+			"$OLLIE/x/prime sys-skills",
+			"$OLLIE/x/prime tools-file",
+			"$OLLIE/x/prime tools-reasoning",
+			"$OLLIE/x/prime tools-memory",
+			"$OLLIE/x/prime tools-subagent",
+			"$OLLIE/x/prime tools-elevate",
 			"bd prime 2>/dev/null || true"
 		],
 		"preTurn": ["true"],
diff --git a/agents/default.json b/agents/default.json
index 492e292..3a1fac1 100644
--- a/agents/default.json
+++ b/agents/default.json
@@ -4,13 +4,13 @@
 	],
 	"hooks": {
 		"agentSpawn": [
-			"$OLLIE/x/prime 00_base",
-			"$OLLIE/x/prime 01_ollie",
-			"$OLLIE/x/prime 02_skills",
-			"$OLLIE/x/prime 03_tool-files",
-			"$OLLIE/x/prime 04_tool-reasoning",
-			"$OLLIE/x/prime 05_tool-memory",
-			"$OLLIE/x/prime 07_tool-subagents",
+			"$OLLIE/x/prime sys-base",
+			"$OLLIE/x/prime sys-ollie",
+			"$OLLIE/x/prime sys-skills",
+			"$OLLIE/x/prime tools-file",
+			"$OLLIE/x/prime tools-reasoning",
+			"$OLLIE/x/prime tools-memory",
+			"$OLLIE/x/prime tools-subagent",
 			"bd prime 2>/dev/null || true"
 		],
 		"preTurn": ["true"],
diff --git a/doc/OBSERVATIONS.md b/doc/OBSERVATIONS.md
index 30a56bb..604a00c 100644
--- a/doc/OBSERVATIONS.md
+++ b/doc/OBSERVATIONS.md
@@ -4,7 +4,7 @@
 
 **Simple front-ends** — A TUI reads `chat`, writes `prompt`, polls `state`. There is no protocol to implement.
 
-**Crash resiliency** — Memory (`m/`) and plans (`pl/`) are written to persistent storage outside the session. If a session crashes or is killed mid-task, neither is lost — a fresh session picks up where the previous one left off.
+**Crash resiliency** — Memory (`m/`) is written to persistent storage outside the session. If a session crashes or is killed mid-task, it is not lost — a fresh session picks up where the previous one left off.
 
 **[Code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool)** — Anthropic describes code execution as "a foundational primitive for building high-performance agents." ollie takes that literally: `execute_code` is the only built-in tool. It is a pipeline executor — single stage, multi-stage, and parallel fan-out are all the same primitive. New capabilities are added by dropping a script into `t/` and a skill in `sk/`.
 
diff --git a/doc/env.sample b/doc/env.sample
index e2deba8..8043c47 100644
--- a/doc/env.sample
+++ b/doc/env.sample
@@ -19,9 +19,6 @@
 # Skills directory, colon-separated (default: ~/.config/ollie/skills)
 #OLLIE_SKILLS_PATH=~/.config/ollie/skills
 
-# Plans directory (default: ~/.config/ollie/plans)
-#OLLIE_PLAN_PATH=~/.config/ollie/plans
-
 # Memory directory (default: ~/.config/ollie/memory)
 #OLLIE_MEMORY_PATH=~/.config/ollie/memory
 
diff --git a/prompts/00_base.md b/prompts/sys-base.md
similarity index 100%
rename from prompts/00_base.md
rename to prompts/sys-base.md
diff --git a/prompts/01_ollie.md b/prompts/sys-ollie.md
similarity index 100%
rename from prompts/01_ollie.md
rename to prompts/sys-ollie.md
diff --git a/prompts/02_skills.md b/prompts/sys-skills.md
similarity index 100%
rename from prompts/02_skills.md
rename to prompts/sys-skills.md
diff --git a/prompts/08_tool-elevate.md b/prompts/tools-elevate.md
similarity index 100%
rename from prompts/08_tool-elevate.md
rename to prompts/tools-elevate.md
diff --git a/prompts/03_tool-files.md b/prompts/tools-file.md
similarity index 100%
rename from prompts/03_tool-files.md
rename to prompts/tools-file.md
diff --git a/prompts/05_tool-memory.md b/prompts/tools-memory.md
similarity index 100%
rename from prompts/05_tool-memory.md
rename to prompts/tools-memory.md
diff --git a/prompts/04_tool-reasoning.md b/prompts/tools-reasoning.md
similarity index 100%
rename from prompts/04_tool-reasoning.md
rename to prompts/tools-reasoning.md
diff --git a/prompts/07_tool-subagents.md b/prompts/tools-subagent.md
similarity index 100%
rename from prompts/07_tool-subagents.md
rename to prompts/tools-subagent.md