diff --git a/DEV-LEDGER.md b/DEV-LEDGER.md
index 3289be3..a4a7b53 100644
--- a/DEV-LEDGER.md
+++ b/DEV-LEDGER.md
@@ -152,6 +152,7 @@ One branch `codex/extractor-eval-loop` for Day 1-5, a second `codex/retrieval-ha
 
 ## Session Log
 
+- **2026-04-12 Codex (branch `codex/openclaw-capture-plugin`, polish pass)** tightened the OpenClaw capture plugin to use `before_agent_reply.cleanedBody` instead of the raw prompt-build input, which should prevent Discord wrapper metadata from being stored as the interaction prompt. Added `agent_end` cleanup and updated plugin docs. A fresh post-restart user turn is still needed to verify prompt cleanliness on Dalidou.
 - **2026-04-12 Codex (branch `codex/openclaw-capture-plugin`)** added a minimal external OpenClaw plugin at `openclaw-plugins/atocore-capture/` that mirrors Claude Code capture semantics: user-triggered assistant turns are POSTed to AtoCore `/interactions` with `client="openclaw"` and `reinforce=true`, fail-open, no extraction in-path. For live verification, temporarily added the local plugin load path to OpenClaw config and restarted the gateway so the plugin can load. Branch truth is ready; end-to-end verification still needs one fresh post-restart OpenClaw user turn to confirm new `client=openclaw` interactions appear on Dalidou.
 - **2026-04-12 Claude** Batch 3 (R9 fix): `144dbbd..e5e9a99`. Trust hierarchy for project attribution — interaction scope always wins when set, model project only used for unscoped interactions + registered check. 7 case tests (A-G) cover every combination. Harness 17/18 (no regression). Tests 286->290. Before: wrong registered project could silently override interaction scope. After: interaction.project is the strongest signal; model project is only a fallback for unscoped captures. Not yet guaranteed: nothing prevents the *same* project's model output from being semantically wrong within that project. R9 marked fixed.
 
diff --git a/openclaw-plugins/atocore-capture/README.md b/openclaw-plugins/atocore-capture/README.md
index f24c187..a7212bf 100644
--- a/openclaw-plugins/atocore-capture/README.md
+++ b/openclaw-plugins/atocore-capture/README.md
@@ -3,6 +3,7 @@
 Minimal OpenClaw plugin that mirrors Claude Code's `capture_stop.py` behavior:
 
 - watches user-triggered assistant turns
+- uses OpenClaw's cleaned user message (`before_agent_reply.cleanedBody`) so AtoCore stores the real prompt instead of the full inbound wrapper
 - POSTs `prompt` + `response` to `POST /interactions`
 - sets `client="openclaw"`
 - sets `reinforce=true`
@@ -25,5 +26,6 @@ If `baseUrl` is omitted, the plugin uses `ATOCORE_BASE_URL` or defaults to `http
 ## Notes
 
 - Project detection is intentionally left empty for now. Unscoped capture is acceptable because AtoCore's extraction pipeline handles unscoped interactions.
+- Prompt cleaning is done inside the plugin by reading OpenClaw's finalized cleaned message body instead of the raw prompt-build input.
 - Extraction is **not** part of the capture path. This plugin only records interactions and lets AtoCore reinforcement run automatically.
 - The plugin captures only user-triggered turns, not heartbeats or system-only runs.
diff --git a/openclaw-plugins/atocore-capture/index.js b/openclaw-plugins/atocore-capture/index.js
index dd27258..bbda756 100644
--- a/openclaw-plugins/atocore-capture/index.js
+++ b/openclaw-plugins/atocore-capture/index.js
@@ -46,11 +46,11 @@ export default definePluginEntry({
     const logger = api.logger;
     const pendingBySession = new Map();
 
-    api.on("before_agent_start", async (event, ctx) => {
+    api.on("before_agent_reply", async (event, ctx) => {
       if (ctx?.trigger && ctx.trigger !== "user") return;
       const config = api.getConfig?.() || {};
       const minPromptLength = Number(config.minPromptLength || DEFAULT_MIN_PROMPT_LENGTH);
-      const prompt = trimText(event?.prompt || "");
+      const prompt = trimText(event?.cleanedBody || "");
       if (!shouldCapturePrompt(prompt, minPromptLength)) {
         pendingBySession.delete(ctx.sessionId);
         return;
@@ -69,7 +69,10 @@ export default definePluginEntry({
       if (!pending) return;
 
       const assistantTexts = Array.isArray(event?.assistantTexts) ? event.assistantTexts : [];
-      const response = truncateResponse(trimText(assistantTexts.join("\n\n")), Number((api.getConfig?.() || {}).maxResponseLength || DEFAULT_MAX_RESPONSE_LENGTH));
+      const response = truncateResponse(
+        trimText(assistantTexts.join("\n\n")),
+        Number((api.getConfig?.() || {}).maxResponseLength || DEFAULT_MAX_RESPONSE_LENGTH)
+      );
       if (!response) return;
 
       const config = api.getConfig?.() || {};
@@ -87,6 +90,10 @@ export default definePluginEntry({
       pendingBySession.delete(ctx.sessionId);
     });
 
+    api.on("agent_end", async (event) => {
+      if (event?.sessionId) pendingBySession.delete(event.sessionId);
+    });
+
     api.on("session_end", async (event) => {
       if (event?.sessionId) pendingBySession.delete(event.sessionId);
     });