diff --git a/armsrc/hitagS.c b/armsrc/hitagS.c
index 4c4e3d493..7a42fcd81 100644
--- a/armsrc/hitagS.c
+++ b/armsrc/hitagS.c
@@ -419,7 +419,7 @@ static void hts_init_clock(void) {
 static int check_select(const uint8_t *rx, uint32_t uid) {
 
     // global var?
-    concatbits((uint8_t *)&reader_selected_uid, 0, rx, 5, 32);
+    concatbits((uint8_t *)&reader_selected_uid, 0, rx, 5, 32, false);
     reader_selected_uid = BSWAP_32(reader_selected_uid);
 
     if (reader_selected_uid == uid) {
@@ -1090,7 +1090,7 @@ static int hts_select_tag(const lf_hitag_data_t *packet, uint8_t *tx, size_t siz
 
     protocol_mode = packet->mode;
     uint8_t cmd = protocol_mode;
-    txlen = concatbits(tx, txlen, &cmd, 0, 5);
+    txlen = concatbits(tx, txlen, &cmd, 0, 5, false);
     hts_send_receive(tx, txlen, rx, sizeofrx, &rxlen, t_wait, ledcontrol, true);
 
     if (rxlen != 32) {
@@ -1105,10 +1105,10 @@ static int hts_select_tag(const lf_hitag_data_t *packet, uint8_t *tx, size_t siz
     // select uid
     txlen = 0;
     cmd = HITAGS_SELECT;
-    txlen = concatbits(tx, txlen, &cmd, 0, 5);
-    txlen = concatbits(tx, txlen, rx, 0, 32);
+    txlen = concatbits(tx, txlen, &cmd, 0, 5, false);
+    txlen = concatbits(tx, txlen, rx, 0, 32, false);
     uint8_t crc = CRC8Hitag1Bits(tx, txlen);
-    txlen = concatbits(tx, txlen, &crc, 0, 8);
+    txlen = concatbits(tx, txlen, &crc, 0, 8, false);
 
     hts_send_receive(tx, txlen, rx, sizeofrx, &rxlen, HITAG_T_WAIT_SC, ledcontrol, false);
 
@@ -1140,8 +1140,8 @@ static int hts_select_tag(const lf_hitag_data_t *packet, uint8_t *tx, size_t siz
             }
 
             txlen = 0;
-            txlen = concatbits(tx, txlen, rnd, 0, 32);
-            txlen = concatbits(tx, txlen, auth_ks, 0, 32);
+            txlen = concatbits(tx, txlen, rnd, 0, 32, false);
+            txlen = concatbits(tx, txlen, auth_ks, 0, 32, false);
 
             DBG DbpString("Authenticating using key:");
             DBG Dbhexdump(6, packet->key, false);
@@ -1173,13 +1173,13 @@ static int hts_select_tag(const lf_hitag_data_t *packet, uint8_t *tx, size_t siz
             // send write page request
             txlen = 0;
             cmd = HITAGS_WRITE_PAGE;
-            txlen = concatbits(tx, txlen, &cmd, 0, 4);
+            txlen = concatbits(tx, txlen, &cmd, 0, 4, false);
 
             uint8_t addr = 64;
-            txlen = concatbits(tx, txlen, &addr, 0, 8);
+            txlen = concatbits(tx, txlen, &addr, 0, 8, false);
 
             crc = CRC8Hitag1Bits(tx, txlen);
-            txlen = concatbits(tx, txlen, &crc, 0, 8);
+            txlen = concatbits(tx, txlen, &crc, 0, 8, false);
 
             hts_send_receive(tx, txlen, rx, sizeofrx, &rxlen, HITAG_T_WAIT_SC, ledcontrol, false);
 
@@ -1189,9 +1189,9 @@ static int hts_select_tag(const lf_hitag_data_t *packet, uint8_t *tx, size_t siz
             }
 
             txlen = 0;
-            txlen = concatbits(tx, txlen, packet->pwd, 0, 32);
+            txlen = concatbits(tx, txlen, packet->pwd, 0, 32, false);
             crc = CRC8Hitag1Bits(tx, txlen);
-            txlen = concatbits(tx, txlen, &crc, 0, 8);
+            txlen = concatbits(tx, txlen, &crc, 0, 8, false);
 
             hts_send_receive(tx, txlen, rx, sizeofrx, &rxlen, HITAG_T_WAIT_SC, ledcontrol, false);
 
@@ -1287,11 +1287,11 @@ void hts_read(const lf_hitag_data_t *payload, bool ledcontrol) {
         //send read request
         size_t txlen = 0;
         uint8_t cmd = HITAGS_READ_PAGE;
-        txlen = concatbits(tx, txlen, &cmd, 0, 4);
+        txlen = concatbits(tx, txlen, &cmd, 0, 4, false);
         uint8_t addr = page_addr;
-        txlen = concatbits(tx, txlen, &addr, 0, 8);
+        txlen = concatbits(tx, txlen, &addr, 0, 8, false);
         uint8_t crc = CRC8Hitag1Bits(tx, txlen);
-        txlen = concatbits(tx, txlen, &crc, 0, 8);
+        txlen = concatbits(tx, txlen, &crc, 0, 8, false);
 
         hts_send_receive(tx, txlen, rx, ARRAYLEN(rx), &rxlen, HITAG_T_WAIT_SC, ledcontrol, false);
 
@@ -1396,13 +1396,13 @@ void hts_write_page(const lf_hitag_data_t *payload, bool ledcontrol) {
     txlen = 0;
 
     uint8_t cmd = HITAGS_WRITE_PAGE;
-    txlen = concatbits(tx, txlen, &cmd, 0, 4);
+    txlen = concatbits(tx, txlen, &cmd, 0, 4, false);
 
     uint8_t addr = payload->page;
-    txlen = concatbits(tx, txlen, &addr, 0, 8);
+    txlen = concatbits(tx, txlen, &addr, 0, 8, false);
 
     uint8_t crc = CRC8Hitag1Bits(tx, txlen);
-    txlen = concatbits(tx, txlen, &crc, 0, 8);
+    txlen = concatbits(tx, txlen, &crc, 0, 8, false);
 
     hts_send_receive(tx, txlen, rx, ARRAYLEN(rx), &rxlen, HITAG_T_WAIT_SC, ledcontrol, false);
 
@@ -1430,9 +1430,9 @@ void hts_write_page(const lf_hitag_data_t *payload, bool ledcontrol) {
     // }
 
     txlen = 0;
-    txlen = concatbits(tx, txlen, payload->data, 0, 32);
+    txlen = concatbits(tx, txlen, payload->data, 0, 32, false);
     crc = CRC8Hitag1Bits(tx, txlen);
-    txlen = concatbits(tx, txlen, &crc, 0, 8);
+    txlen = concatbits(tx, txlen, &crc, 0, 8, false);
 
     enable_page_tearoff = g_tearoff_enabled;
 
@@ -1493,7 +1493,7 @@ int hts_read_uid(uint32_t *uid, bool ledcontrol, bool send_answer) {
     size_t txlen = 0;
     uint8_t tx[HITAG_FRAME_LEN] = { 0x00 };
 
-    txlen = concatbits(tx, txlen, &cmd, 0, 5);
+    txlen = concatbits(tx, txlen, &cmd, 0, 5, false);
 
     hts_send_receive(tx, txlen, rx, ARRAYLEN(rx), &rxlen, HITAG_T_WAIT_FIRST, ledcontrol, true);
 
diff --git a/client/src/cmdlfem410x.c b/client/src/cmdlfem410x.c
index 145392eb7..7f296336c 100644
--- a/client/src/cmdlfem410x.c
+++ b/client/src/cmdlfem410x.c
@@ -688,11 +688,11 @@ static int CmdEM410xClone(const char *Cmd) {
         uint8_t r_parity = 0;
         uint8_t nibble = id >> i & 0xF;
 
-        databits = concatbits(data, databits, &nibble, 4, 4);
+        databits = concatbits(data, databits, &nibble, 4, 4, false);
         for (size_t j = 0; j < 4; j++) {
             r_parity ^= nibble >> j & 1;
         }
-        databits = concatbits(data, databits, &r_parity, 7, 1);
+        databits = concatbits(data, databits, &r_parity, 7, 1, false);
         c_parity ^= nibble;
     }
     data[7] |= c_parity << 1;
diff --git a/common/commonutil.c b/common/commonutil.c
index d4eed608e..35a583988 100644
--- a/common/commonutil.c
+++ b/common/commonutil.c
@@ -555,9 +555,13 @@ void reverse_arraybytes_copy(uint8_t *arr, uint8_t *dest, size_t len) {
 }
 
 // TODO: Boost performance by copying in chunks of 1, 2, or 4 bytes when feasible.
-size_t concatbits(uint8_t *dest, int dest_offset, const uint8_t *src, int src_offset, size_t nbits) {
+/**
+ * @brief Concatenate bits from src to dest, bitstream is stored MSB first
+ * which means that the dest_offset=0 is the MSB of the dest[0]
+ *
+ */
+size_t concatbits(uint8_t *dest, int dest_offset, const uint8_t *src, int src_offset, size_t nbits, bool src_lsb) {
     int i, end, step;
-
     // overlap
     if ((src - dest) * 8 + src_offset - dest_offset > 0) {
         i = 0;
@@ -571,8 +575,8 @@ size_t concatbits(uint8_t *dest, int dest_offset, const uint8_t *src, int src_of
 
     for (; i != end; i += step) {
         // equiv of dest_bits[dest_offset + i] = src_bits[src_offset + i]
-        CLEAR_BIT(dest, dest_offset + i);
-        if (TEST_BIT(src, src_offset + i)) SET_BIT(dest, dest_offset + i);
+        CLEAR_BIT_MSB(dest, dest_offset + i);
+        if (src_lsb ? TEST_BIT_LSB(src, src_offset + i) : TEST_BIT_MSB(src, src_offset + i)) SET_BIT_MSB(dest, dest_offset + i);
     }
 
     return dest_offset + nbits;
diff --git a/common/commonutil.h b/common/commonutil.h
index 2ab4fbd79..2360f2a57 100644
--- a/common/commonutil.h
+++ b/common/commonutil.h
@@ -150,7 +150,7 @@ bool hexstr_to_byte_array(const char *hexstr, uint8_t *d, size_t *n);
 void reverse_arraybytes(uint8_t *arr, size_t len);
 void reverse_arraybytes_copy(uint8_t *arr, uint8_t *dest, size_t len);
 
-size_t concatbits(uint8_t *dest, int dest_offset, const uint8_t *src, int src_offset, size_t nbits);
+size_t concatbits(uint8_t *dest, int dest_offset, const uint8_t *src, int src_offset, size_t nbits, bool src_lsb);
 int char2int(char c);
 int hexstr2ByteArr(const char *hexstr, unsigned char *array, size_t asize);
 #endif
diff --git a/include/common.h b/include/common.h
index b405b2ac7..086354750 100644
--- a/include/common.h
+++ b/include/common.h
@@ -202,10 +202,15 @@ extern bool g_tearoff_enabled;
 #endif
 
 // bit stream operations
-#define TEST_BIT(data, i) (*((data) + ((i) / 8)) >> (7 - ((i) % 8))) & 1
-#define SET_BIT(data, i)   *((data) + ((i) / 8)) |= (1 << (7 - ((i) % 8)))
-#define CLEAR_BIT(data, i) *((data) + ((i) / 8)) &= ~(1 << (7 - ((i) % 8)))
-#define FLIP_BIT(data, i)  *((data) + ((i) / 8)) ^= (1 << (7 - ((i) % 8)))
+#define TEST_BIT_MSB(data, i)  ((*((data) + ((i) / 8)) >> (7 - ((i) % 8))) & 1)
+#define SET_BIT_MSB(data, i)   (*((data) + ((i) / 8)) |= (1 << (7 - ((i) % 8))))
+#define CLEAR_BIT_MSB(data, i) (*((data) + ((i) / 8)) &= ~(1 << (7 - ((i) % 8))))
+#define FLIP_BIT_MSB(data, i)  (*((data) + ((i) / 8)) ^= (1 << (7 - ((i) % 8))))
+
+#define TEST_BIT_LSB(data, i)  ((*((data) + ((i) / 8)) >> ((i) % 8)) & 1)
+#define SET_BIT_LSB(data, i)   (*((data) + ((i) / 8)) |= (1 << ((i) % 8)))
+#define CLEAR_BIT_LSB(data, i) (*((data) + ((i) / 8)) &= ~(1 << ((i) % 8)))
+#define FLIP_BIT_LSB(data, i)  (*((data) + ((i) / 8)) ^= (1 << ((i) % 8)))
 
 // time for decompressing and loading the image to the FPGA
 #define FPGA_LOAD_WAIT_TIME (1500)