diff --git a/.claude/hooks/on-input-received.sh b/.claude/hooks/on-input-received.sh
deleted file mode 100755
index add13664..00000000
--- a/.claude/hooks/on-input-received.sh
+++ /dev/null
@@ -1,12 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-BREADCRUMB=".claude/tmp/active-run-dir"
-[ -f "$BREADCRUMB" ] || exit 0
-
-RUN_DIR=$(cat "$BREADCRUMB")
-LOG_FILE="$RUN_DIR/run-log.jsonl"
-[ -f "$LOG_FILE" ] || exit 0
-
-TIMESTAMP=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
-echo "{\"t\":\"$TIMESTAMP\",\"event\":\"input_received\"}" >>"$LOG_FILE"
diff --git a/.claude/hooks/on-waiting-for-input.sh b/.claude/hooks/on-waiting-for-input.sh
deleted file mode 100755
index 9c97a7e5..00000000
--- a/.claude/hooks/on-waiting-for-input.sh
+++ /dev/null
@@ -1,20 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-BREADCRUMB=".claude/tmp/active-run-dir"
-[ -f "$BREADCRUMB" ] || exit 0
-
-RUN_DIR=$(cat "$BREADCRUMB")
-LOG_FILE="$RUN_DIR/run-log.jsonl"
-[ -f "$LOG_FILE" ] || exit 0
-
-INPUT=$(cat)
-REASON=$(echo "$INPUT" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('notification_type',''))" 2>/dev/null || echo "")
-
-case "$REASON" in
-permission_prompt | elicitation_dialog | idle_prompt) ;;
-*) exit 0 ;;
-esac
-
-TIMESTAMP=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
-echo "{\"t\":\"$TIMESTAMP\",\"event\":\"waiting_for_input\",\"reason\":\"$REASON\"}" >>"$LOG_FILE"
diff --git a/.claude/settings.json b/.claude/settings.json
index c3bfbabf..ee09428b 100644
--- a/.claude/settings.json
+++ b/.claude/settings.json
@@ -7,28 +7,5 @@
       "command": "node",
       "args": ["packages/mcp/dist/esm/cli.js"]
     }
-  },
-  "hooks": {
-    "Notification": [
-      {
-        "matcher": "idle_prompt|permission_prompt|elicitation_dialog",
-        "hooks": [
-          {
-            "type": "command",
-            "command": ".claude/hooks/on-waiting-for-input.sh"
-          }
-        ]
-      }
-    ],
-    "UserPromptSubmit": [
-      {
-        "hooks": [
-          {
-            "type": "command",
-            "command": ".claude/hooks/on-input-received.sh"
-          }
-        ]
-      }
-    ]
   }
 }
diff --git a/packages/agents/content/skills/orchestrate/SKILL.md b/packages/agents/content/skills/orchestrate/SKILL.md
index ff09308c..992de7b9 100644
--- a/packages/agents/content/skills/orchestrate/SKILL.md
+++ b/packages/agents/content/skills/orchestrate/SKILL.md
@@ -229,13 +229,13 @@ Prefix the status line with a colored emoji for visual distinction:
 
    The `init_run` tool creates the run directory, writes a v3 `run-index.json` header, creates an empty `run-log.jsonl`, and emits a `run_started` event automatically. Do not write `run-index.json` manually.
 
-   **Write breadcrumb** (MCP success path only): After a successful `init_run`, write the active run directory to a breadcrumb file so that Claude Code hooks can discover it:
+   **Write breadcrumb** (MCP success path only): After a successful `init_run`, write the active run directory to a breadcrumb file so that `resolve-frontmatter.sh` can resolve the active run's `run_id` when stamping artifact frontmatter:
 
    ```
    mkdir -p .claude/tmp && echo "{run-dir}" > .claude/tmp/active-run-dir
    ```
 
-   Only write the breadcrumb after a successful `init_run` (MCP available). Do not write it on the MCP-unavailable fallback path. When MCP is unavailable, no `run-log.jsonl` is created, so the hooks have nothing to append to.
+   Only write the breadcrumb after a successful `init_run` (MCP available). Do not write it on the MCP-unavailable fallback path, where no run directory is created and there is no `run_id` to resolve.
 
    **Failure — MCP unavailable** (tool not found / server not connected): Resolve `mcp_policy` (see "Resolving MCP policy" above) and apply the policy:
    - `required`: Abort with a clear message explaining that MCP is unavailable and the policy requires it.