diff --git a/NAMESPACE b/NAMESPACE
index 56ad05a..4f3271d 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -1,10 +1,12 @@
 # Generated by roxygen2: do not edit by hand
 
+S3method(plot,cchart.DSnp)
 export(T2.1)
 export(T2.2)
 export(add.data)
 export(alpha.risk)
 export(c4)
+export(cchart.DSnp)
 export(cchart.R)
 export(cchart.S)
 export(cchart.T2.1)
@@ -30,6 +32,7 @@ export(table.qtukey)
 importFrom(MASS,mvrnorm)
 importFrom(graphics,abline)
 importFrom(graphics,axis)
+importFrom(graphics,legend)
 importFrom(graphics,lines)
 importFrom(graphics,mtext)
 importFrom(graphics,par)
diff --git a/R/cchart.DSnp.R b/R/cchart.DSnp.R
new file mode 100644
index 0000000..6d8efef
--- /dev/null
+++ b/R/cchart.DSnp.R
@@ -0,0 +1,360 @@
+#' Double-Sampling np Control Chart
+#'
+#' Build and optionally plot a double-sampling np (DS-np) control chart for
+#' monitoring the nonconforming proportion in high-quality processes.
+#'
+#' The DS-np chart uses two sampling stages. At the first stage, a sample of
+#' size \code{n1} is inspected. If the count \code{x1} is at or below the
+#' warning limit, the process is accepted. If \code{x1} exceeds the first
+#' upper control limit, the process signals out-of-control immediately.
+#' Otherwise, a second sample of size \code{n2} is inspected and the combined
+#' count \code{x1 + x2} is compared to the second upper control limit.
+#'
+#' Limits can be supplied manually via \code{wl}, \code{ucl1}, and
+#' \code{ucl2}, obtained from a pre-computed \code{dsnp_limits()} object via
+#' the \code{limits} argument, or computed automatically inside the function
+#' when neither is provided.
+#'
+#' The fractional limits are converted to integer thresholds using the
+#' convention from the numerical core functions:
+#' \itemize{
+#'   \item \code{wl_accept = floor(wl)}: accept at first stage if
+#'         \code{x1 <= wl_accept}.
+#'   \item \code{ucl1_reject = floor(ucl1) + 1}: signal at first stage if
+#'         \code{x1 >= ucl1_reject}.
+#'   \item \code{ucl2_accept = floor(ucl2)}: accept at second stage if
+#'         \code{x1 + x2 <= ucl2_accept}.
+#' }
+#'
+#' @param x1 Integer vector of nonconforming counts from the first sample.
+#' @param n1 First-stage sample size (positive integer).
+#' @param n2 Second-stage sample size (positive integer).
+#' @param p0 In-control nonconforming proportion.
+#' @param x2 Optional integer vector of nonconforming counts from the second
+#'   sample. Must have the same length as \code{x1} when provided. Use
+#'   \code{NA} for observations where no second sample was taken. Required
+#'   for observations where \code{x1} falls in the intermediate (warning)
+#'   zone.
+#' @param wl Fractional warning limit. Must be less than \code{ucl1}.
+#' @param ucl1 Fractional upper control limit for the first stage. Must be
+#'   greater than \code{wl}.
+#' @param ucl2 Fractional upper control limit for the combined samples.
+#' @param limits Optional object returned by \code{dsnp_limits()}. When
+#'   provided, \code{wl}, \code{ucl1}, and \code{ucl2} are taken from
+#'   \code{limits$best}.
+#' @param alpha Maximum desired false alarm probability at \code{p0}. Used
+#'   only when limits need to be computed via \code{dsnp_limits()}.
+#' @param p1 Optional out-of-control proportion. When provided, performance
+#'   metrics at \code{p1} are included in the returned object.
+#' @param plot Logical. If \code{TRUE} (default), draws the control chart.
+#'   If \code{FALSE}, only returns the result object.
+#' @param ... Additional arguments passed to \code{plot()} (currently
+#'   unused).
+#'
+#' @return An object of class \code{"cchart.DSnp"}, which is a list with the
+#' following elements:
+#' \describe{
+#'   \item{call}{The matched call.}
+#'   \item{data}{A data.frame with columns \code{index}, \code{x1},
+#'     \code{x2}, \code{total}, \code{stage}, and \code{signal}.}
+#'   \item{limits}{A list with the fractional and integer thresholds:
+#'     \code{wl}, \code{ucl1}, \code{ucl2}, \code{wl_accept},
+#'     \code{ucl1_reject}, \code{ucl2_accept}.}
+#'   \item{parameters}{A list with \code{n1}, \code{n2}, \code{p0},
+#'     \code{alpha}, and \code{p1}.}
+#'   \item{performance}{A list with in-control performance metrics
+#'     (\code{arl0}, \code{ass0}, \code{p_signal0}), and optionally
+#'     out-of-control metrics (\code{arl1}, \code{ass1},
+#'     \code{p_signal1}) when \code{p1} is provided.}
+#' }
+#'
+#' @export
+#' @importFrom graphics legend abline plot points
+#' @author Daniela R. Recchia, Emanuel P. Barbosa
+#' @seealso \code{\link{dsnp_limits}}, \code{\link{dsnp_prob_accept}},
+#'   \code{\link{dsnp_arl}}, \code{\link{dsnp_ass}}
+#' @references Joekes, S., Smrekar, M. and Barbosa, E. (2015). Extending a
+#' double sampling control chart for non-conforming proportion in high quality
+#' processes to the case of small samples. \emph{Statistical Methodology}.
+#' @examples
+#'
+#' # Small example with manual limits
+#' x1 <- c(0, 1, 2, 3, 1, 0, 2, 4, 1, 0)
+#' x2 <- c(NA, NA, 2, NA, NA, NA, 3, NA, NA, NA)
+#' res <- cchart.DSnp(x1, n1 = 10, n2 = 20, p0 = 0.05,
+#'                    x2 = x2, wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+#'                    plot = FALSE)
+#' res$limits
+#' res$performance
+#'
+cchart.DSnp <- function(x1, n1, n2, p0,
+                        x2 = NULL,
+                        wl = NULL,
+                        ucl1 = NULL,
+                        ucl2 = NULL,
+                        limits = NULL,
+                        alpha = 0.0027,
+                        p1 = NULL,
+                        plot = TRUE,
+                        ...)
+{
+    cl <- match.call()
+
+    # --- Validate x1 ---
+    if(!is.numeric(x1) || length(x1) < 1)
+        stop("x1 must be a non-empty numeric vector")
+    if(any(x1 < 0))
+        stop("x1 must not contain negative values")
+    if(any(x1 > n1))
+        stop("x1 values must not exceed n1")
+    if(any(x1 != floor(x1)))
+        stop("x1 must contain integer values")
+
+    m <- length(x1)
+
+    # --- Resolve limits ---
+    have_limits_obj <- !is.null(limits)
+    have_manual     <- !is.null(wl) || !is.null(ucl1) || !is.null(ucl2)
+    have_none       <- !have_limits_obj && !have_manual
+
+    if(have_limits_obj && have_manual)
+        stop("Cannot specify both 'limits' and manual 'wl'/'ucl1'/'ucl2'")
+
+    if(have_manual && (is.null(wl) || is.null(ucl1) || is.null(ucl2)))
+        stop("All of 'wl', 'ucl1', and 'ucl2' must be provided together")
+
+    if(have_limits_obj)
+    {
+        if(!is.null(limits$best))
+        {
+            wl   <- limits$best$wl
+            ucl1 <- limits$best$ucl1
+            ucl2 <- limits$best$ucl2
+        }
+        else
+        {
+            stop("'limits' object does not contain a 'best' element")
+        }
+    }
+
+    if(have_none)
+    {
+        lim <- dsnp_limits(p0, n1, n2, alpha = alpha, p1 = p1,
+                           max_results = 1)
+        wl   <- lim$best$wl
+        ucl1 <- lim$best$ucl1
+        ucl2 <- lim$best$ucl2
+    }
+
+    # --- Validate limits ---
+    if(!is.numeric(wl) || !is.numeric(ucl1) || !is.numeric(ucl2))
+        stop("wl, ucl1, and ucl2 must be numeric")
+    if(length(wl) != 1 || length(ucl1) != 1 || length(ucl2) != 1)
+        stop("wl, ucl1, and ucl2 must be scalar")
+    if(wl >= ucl1)
+        stop("wl must be less than ucl1")
+    if(ucl2 <= wl)
+        stop("ucl2 must be greater than wl")
+
+    # --- Integer thresholds ---
+    wl_accept   <- floor(wl)
+    ucl1_reject <- floor(ucl1) + 1
+    ucl2_accept <- floor(ucl2)
+
+    # --- Validate x2 ---
+    if(!is.null(x2))
+    {
+        if(length(x2) != m)
+            stop("x2 must have the same length as x1")
+        if(any(!is.na(x2) & x2 < 0))
+            stop("x2 must not contain negative values")
+        if(any(!is.na(x2) & x2 > n2))
+            stop("x2 values must not exceed n2")
+        if(any(!is.na(x2) & x2 != floor(x2)))
+            stop("x2 must contain integer values")
+    }
+
+    # --- Classify each observation ---
+    index <- seq_len(m)
+    stage <- character(m)
+    signal <- logical(m)
+    total <- rep(NA_real_, m)
+    x2_used <- if(!is.null(x2)) x2 else rep(NA_real_, m)
+
+    for(i in seq_len(m))
+    {
+        d1 <- x1[i]
+
+        if(d1 <= wl_accept)
+        {
+            stage[i]  <- "accept_first"
+            signal[i] <- FALSE
+        }
+        else if(d1 >= ucl1_reject)
+        {
+            stage[i]  <- "signal_first"
+            signal[i] <- TRUE
+        }
+        else
+        {
+            # Intermediate zone: second sample required
+            if(is.null(x2) || is.na(x2_used[i]))
+                stop(paste0("Second sample (x2) is required for observation ",
+                            i, " where x1 = ", d1,
+                            " falls in the intermediate zone"))
+            d2 <- x2_used[i]
+            total[i] <- d1 + d2
+            if(total[i] > ucl2_accept)
+            {
+                stage[i]  <- "signal_second"
+                signal[i] <- TRUE
+            }
+            else
+            {
+                stage[i]  <- "accept_second"
+                signal[i] <- FALSE
+            }
+        }
+    }
+
+    # --- Build data frame ---
+    data_df <- data.frame(
+        index  = index,
+        x1     = x1,
+        x2     = x2_used,
+        total  = total,
+        stage  = stage,
+        signal = signal,
+        stringsAsFactors = FALSE
+    )
+
+    # --- Performance metrics ---
+    arl0_res  <- dsnp_arl(p0, n1, n2, wl, ucl1, ucl2)
+    ass0_res  <- dsnp_ass(p0, n1, n2, wl, ucl1)
+    pa0_res   <- dsnp_prob_accept(p0, n1, n2, wl, ucl1, ucl2)
+
+    performance <- list(
+        arl0       = arl0_res$arl,
+        ass0       = ass0_res$ass,
+        p_signal0  = pa0_res$p_signal
+    )
+
+    if(!is.null(p1))
+    {
+        arl1_res <- dsnp_arl(p1, n1, n2, wl, ucl1, ucl2)
+        ass1_res <- dsnp_ass(p1, n1, n2, wl, ucl1)
+        pa1_res  <- dsnp_prob_accept(p1, n1, n2, wl, ucl1, ucl2)
+
+        performance$arl1      <- arl1_res$arl
+        performance$ass1      <- ass1_res$ass
+        performance$p_signal1 <- pa1_res$p_signal
+    }
+
+    # --- Assemble result ---
+    result <- list(
+        call        = cl,
+        data        = data_df,
+        limits      = list(
+            wl           = wl,
+            ucl1         = ucl1,
+            ucl2         = ucl2,
+            wl_accept    = wl_accept,
+            ucl1_reject  = ucl1_reject,
+            ucl2_accept  = ucl2_accept
+        ),
+        parameters  = list(
+            n1    = n1,
+            n2    = n2,
+            p0    = p0,
+            alpha = alpha,
+            p1    = p1
+        ),
+        performance = performance
+    )
+    class(result) <- "cchart.DSnp"
+
+    # --- Plot ---
+    if(plot)
+        plot.cchart.DSnp(result, ...)
+
+    result
+}
+
+#' Plot a DS-np Control Chart
+#'
+#' S3 method for plotting objects of class \code{"cchart.DSnp"}.
+#'
+#' The plot shows the first-stage counts \code{x1} against the sample index.
+#' Points requiring a second sample are shown as open circles. Points that
+#' signal (at either stage) are shown in red. Horizontal lines mark the
+#' fractional limits.
+#'
+#' Note that \code{ucl2} is on the scale of the combined count
+#' \code{x1 + x2}. The plot is a simple operational visualization; the
+#' full decision logic is in the returned object.
+#'
+#' @param x An object of class \code{"cchart.DSnp"}.
+#' @param ... Additional graphical parameters (currently unused).
+#' @return Invisible \code{x}.
+#' @export
+#' @method plot cchart.DSnp
+plot.cchart.DSnp <- function(x, ...)
+{
+    d    <- x$data
+    lim  <- x$limits
+    n1   <- x$parameters$n1
+
+    # Determine y-axis range
+    y_max <- max(d$x1, na.rm = TRUE)
+    y_max <- max(y_max, lim$ucl1 + 1, lim$ucl2, na.rm = TRUE)
+    y_max <- ceiling(y_max * 1.1)
+    if(y_max < 5) y_max <- 5
+
+    # Base plot: x1 vs index
+    plot(d$index, d$x1, type = "n",
+         xlab = "Sample index", ylab = "Count (x1)",
+         xlim = c(1, nrow(d)),
+         ylim = c(0, y_max),
+         main = "DS-np Control Chart",
+         las = 1)
+
+    # Points that stayed at first stage (no second sample needed)
+    first_only <- d$stage %in% c("accept_first", "signal_first")
+    points(d$index[first_only], d$x1[first_only],
+           pch = 16, cex = 1.2)
+
+    # Points that needed a second sample
+    second <- d$stage %in% c("accept_second", "signal_second")
+    if(any(second))
+        points(d$index[second], d$x1[second],
+               pch = 1, cex = 1.2)
+
+    # Highlight signals in red
+    if(any(d$signal))
+        points(d$index[d$signal], d$x1[d$signal],
+               pch = 4, cex = 1.4, col = "red", lwd = 2)
+
+    # Limit lines
+    abline(h = lim$wl,   lty = 2, col = "blue")
+    abline(h = lim$ucl1, lty = 2, col = "red")
+    abline(h = lim$ucl2, lty = 3, col = "darkgreen")
+
+    # Legend
+    legend("topleft",
+           legend = c(
+               "First stage only",
+               "Second sample needed",
+               "Signal",
+               paste0("wl = ", lim$wl),
+               paste0("ucl1 = ", lim$ucl1),
+               paste0("ucl2 = ", lim$ucl2)
+           ),
+           pch   = c(16, 1, 4, NA, NA, NA),
+           lty   = c(NA, NA, NA, 2, 2, 3),
+           col   = c("black", "black", "red", "blue", "red", "darkgreen"),
+           cex   = 0.8,
+           bg    = "white",
+           bty   = "n")
+
+    invisible(x)
+}
diff --git a/R/d2.R b/R/d2.R
index e84e2c1..fef5e28 100755
--- a/R/d2.R
+++ b/R/d2.R
@@ -9,7 +9,7 @@
 #' @export
 #' @author Daniela R. Recchia, Emanuel P. Barbosa
 #' @seealso \link{d3},\link{c4}
-#' @importFrom stats ptukey
+#' @importFrom stats ptukey integrate
 #' @examples
 #' 
 #' d2(8)
diff --git a/README.md b/README.md
index 864b1ee..8a69a4d 100644
--- a/README.md
+++ b/README.md
@@ -28,7 +28,7 @@ The package is motivated by a recurring practical problem in classical Shewhart-
 | Range / process dispersion | `cchart.R()` | Shewhart R chart; exact Tukey-based R chart | The exact chart uses the relative range distribution through the Tukey distribution. |
 | Standard deviation | `cchart.S()` | Normalized S chart; exact chi-square-based S chart | Exact limits are based on the chi-square distribution of the sample variance. |
 | Nonconforming proportion | `cchart.p()` | Shewhart p chart; Cornish-Fisher p chart; standardized p chart | The Cornish-Fisher option is designed for low nonconforming proportions where normal approximation is poor. |
-| Double-sampling nonconforming count | `dsnp_prob_accept()`, `dsnp_arl()`, `dsnp_ass()` | Numerical core for DS-np charts | Limit search and plotting are under development. |
+| Double-sampling np chart | `dsnp_prob_accept()`, `dsnp_arl()`, `dsnp_ass()`, `dsnp_limits()`, `cchart.DSnp()` | DS-np numerical core, limit search, and control chart | Two-stage sampling for high-quality processes with small samples. |
 | Nonconformities per unit | `cchart.u()` | Shewhart u chart; standardized u chart | Attribute chart for counts per inspection unit. |
 | Multivariate mean vector | `T2.1()`, `T2.2()`, `cchart.T2.1()`, `cchart.T2.2()` | Hotelling T² charts for Phase I and Phase II | Supports individual and subgroup observations. |
 | Relative range constants | `d2()`, `d3()` | Numerical integration using Tukey distribution functions | Used by exact R-chart calculations and false alarm diagnostics. |
@@ -107,7 +107,7 @@ The package currently implements several core ideas from the research program, b
 
 | Candidate extension | Statistical target | Possible function names | Status |
 |---|---|---|---|
-| Double-sampling np chart | Nonconforming proportion in high-quality processes with small samples | `dsnp_limits()`, `cchart.DSnp()` | Numerical core implemented; limit search and plotting planned |
+| Double-sampling np chart | Nonconforming proportion in high-quality processes with small samples | `dsnp_limits()`, `cchart.DSnp()` | Implemented |
 | Generalized variance chart | Multivariate process variability using `|S|` | `gv_limits()`, `cchart.GV()` | Planned |
 | Cornish-Fisher corrected generalized variance chart | Corrected limits for `|S|` under non-normal sampling distribution | `gv_cf_limits()` | Planned |
 | Auxiliary trace chart | Complementary monitoring using `tr(V)` | `trv_limits()`, `cchart.trV()` | Planned |
diff --git a/man/IQCC-package.Rd b/man/IQCC-package.Rd
new file mode 100644
index 0000000..27d69b6
--- /dev/null
+++ b/man/IQCC-package.Rd
@@ -0,0 +1,31 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/constants.R
+\docType{package}
+\name{IQCC-package}
+\alias{IQCC}
+\alias{IQCC-package}
+\title{Package constants for control chart computations.}
+\description{
+Builds statistical control charts with exact limits for univariate and multivariate cases.
+}
+\seealso{
+Useful links:
+\itemize{
+  \item \url{https://github.com/flaviobarros/IQCC}
+  \item \url{https://flaviobarros.github.io/IQCC}
+  \item Report bugs at \url{https://github.com/flaviobarros/IQCC/issues}
+}
+
+}
+\author{
+\strong{Maintainer}: Flavio Barros \email{flaviomargarito@gmail.com}
+
+Other contributors:
+\itemize{
+  \item Emanuel Barbosa [contributor]
+  \item Elias Goncalves [contributor]
+  \item Daniela Recchia [contributor]
+}
+
+}
+\keyword{internal}
diff --git a/man/add.data.Rd b/man/add.data.Rd
index cf8deb0..06a626f 100644
--- a/man/add.data.Rd
+++ b/man/add.data.Rd
@@ -7,7 +7,7 @@
 add.data(datum2, estat, T2II, n, j, m = NULL)
 }
 \arguments{
-\item{datum2}{The data set for the phase II. Shoul be a vector.}
+\item{datum2}{The data set for the phase II. Should be a matrix.}
 
 \item{estat}{The values of the auxiliary statistics. Should be a list with a
 vector with the mean of the mean vectors, a matrix with the average of the
@@ -23,8 +23,8 @@ variance-covariance matrices and a matrix with the means.}
 set is show on the plot.}
 }
 \value{
-Add the new observation to the current Hoteliing control chart for
-phase II.
+Add the new observation to the current Hotelling control chart for
+phase II. Returns the new T2 statistic invisibly.
 }
 \description{
 This function is used to update the phase II control chart with new
diff --git a/man/alpha.risk.Rd b/man/alpha.risk.Rd
index ae50d04..f378b5c 100644
--- a/man/alpha.risk.Rd
+++ b/man/alpha.risk.Rd
@@ -7,10 +7,10 @@
 alpha.risk(n)
 }
 \arguments{
-\item{n}{The sample size.}
+\item{n}{The sample size. Can be a vector for multiple sample sizes.}
 }
 \value{
-Return the value of the alpha risk for a given sample size n.
+Return a vector of alpha risk values for the given sample sizes.
 }
 \description{
 Used to calculate the real probability of false alarm in the 3-sigma R
diff --git a/man/binomdata.Rd b/man/binomdata.Rd
index ce8268c..b52838c 100644
--- a/man/binomdata.Rd
+++ b/man/binomdata.Rd
@@ -4,12 +4,14 @@
 \name{binomdata}
 \alias{binomdata}
 \title{Binomial Data.}
-\format{A data frame with 25 observations on the following 4 variables.
+\format{
+A data frame with 25 observations on the following 4 variables.
 \describe{ 
 \item{i}{Index.} 
 \item{ni}{The sample Size.}
 \item{Di}{Number of non-conforming units per sample.}
-\item{pi}{Proportion of non-conforming units per sample.} }}
+\item{pi}{Proportion of non-conforming units per sample.} }
+}
 \source{
 Montgomery, D.C.,2001."Introduction to Statistical Quality Control".
 }
diff --git a/man/cchart.DSnp.Rd b/man/cchart.DSnp.Rd
new file mode 100644
index 0000000..54e25d8
--- /dev/null
+++ b/man/cchart.DSnp.Rd
@@ -0,0 +1,130 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/cchart.DSnp.R
+\name{cchart.DSnp}
+\alias{cchart.DSnp}
+\title{Double-Sampling np Control Chart}
+\usage{
+cchart.DSnp(
+  x1,
+  n1,
+  n2,
+  p0,
+  x2 = NULL,
+  wl = NULL,
+  ucl1 = NULL,
+  ucl2 = NULL,
+  limits = NULL,
+  alpha = 0.0027,
+  p1 = NULL,
+  plot = TRUE,
+  ...
+)
+}
+\arguments{
+\item{x1}{Integer vector of nonconforming counts from the first sample.}
+
+\item{n1}{First-stage sample size (positive integer).}
+
+\item{n2}{Second-stage sample size (positive integer).}
+
+\item{p0}{In-control nonconforming proportion.}
+
+\item{x2}{Optional integer vector of nonconforming counts from the second
+sample. Must have the same length as \code{x1} when provided. Use
+\code{NA} for observations where no second sample was taken. Required
+for observations where \code{x1} falls in the intermediate (warning)
+zone.}
+
+\item{wl}{Fractional warning limit. Must be less than \code{ucl1}.}
+
+\item{ucl1}{Fractional upper control limit for the first stage. Must be
+greater than \code{wl}.}
+
+\item{ucl2}{Fractional upper control limit for the combined samples.}
+
+\item{limits}{Optional object returned by \code{dsnp_limits()}. When
+provided, \code{wl}, \code{ucl1}, and \code{ucl2} are taken from
+\code{limits$best}.}
+
+\item{alpha}{Maximum desired false alarm probability at \code{p0}. Used
+only when limits need to be computed via \code{dsnp_limits()}.}
+
+\item{p1}{Optional out-of-control proportion. When provided, performance
+metrics at \code{p1} are included in the returned object.}
+
+\item{plot}{Logical. If \code{TRUE} (default), draws the control chart.
+If \code{FALSE}, only returns the result object.}
+
+\item{...}{Additional arguments passed to \code{plot()} (currently
+unused).}
+}
+\value{
+An object of class \code{"cchart.DSnp"}, which is a list with the
+following elements:
+\describe{
+  \item{call}{The matched call.}
+  \item{data}{A data.frame with columns \code{index}, \code{x1},
+    \code{x2}, \code{total}, \code{stage}, and \code{signal}.}
+  \item{limits}{A list with the fractional and integer thresholds:
+    \code{wl}, \code{ucl1}, \code{ucl2}, \code{wl_accept},
+    \code{ucl1_reject}, \code{ucl2_accept}.}
+  \item{parameters}{A list with \code{n1}, \code{n2}, \code{p0},
+    \code{alpha}, and \code{p1}.}
+  \item{performance}{A list with in-control performance metrics
+    (\code{arl0}, \code{ass0}, \code{p_signal0}), and optionally
+    out-of-control metrics (\code{arl1}, \code{ass1},
+    \code{p_signal1}) when \code{p1} is provided.}
+}
+}
+\description{
+Build and optionally plot a double-sampling np (DS-np) control chart for
+monitoring the nonconforming proportion in high-quality processes.
+}
+\details{
+The DS-np chart uses two sampling stages. At the first stage, a sample of
+size \code{n1} is inspected. If the count \code{x1} is at or below the
+warning limit, the process is accepted. If \code{x1} exceeds the first
+upper control limit, the process signals out-of-control immediately.
+Otherwise, a second sample of size \code{n2} is inspected and the combined
+count \code{x1 + x2} is compared to the second upper control limit.
+
+Limits can be supplied manually via \code{wl}, \code{ucl1}, and
+\code{ucl2}, obtained from a pre-computed \code{dsnp_limits()} object via
+the \code{limits} argument, or computed automatically inside the function
+when neither is provided.
+
+The fractional limits are converted to integer thresholds using the
+convention from the numerical core functions:
+\itemize{
+  \item \code{wl_accept = floor(wl)}: accept at first stage if
+        \code{x1 <= wl_accept}.
+  \item \code{ucl1_reject = floor(ucl1) + 1}: signal at first stage if
+        \code{x1 >= ucl1_reject}.
+  \item \code{ucl2_accept = floor(ucl2)}: accept at second stage if
+        \code{x1 + x2 <= ucl2_accept}.
+}
+}
+\examples{
+
+# Small example with manual limits
+x1 <- c(0, 1, 2, 3, 1, 0, 2, 4, 1, 0)
+x2 <- c(NA, NA, 2, NA, NA, NA, 3, NA, NA, NA)
+res <- cchart.DSnp(x1, n1 = 10, n2 = 20, p0 = 0.05,
+                   x2 = x2, wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                   plot = FALSE)
+res$limits
+res$performance
+
+}
+\references{
+Joekes, S., Smrekar, M. and Barbosa, E. (2015). Extending a
+double sampling control chart for non-conforming proportion in high quality
+processes to the case of small samples. \emph{Statistical Methodology}.
+}
+\seealso{
+\code{\link{dsnp_limits}}, \code{\link{dsnp_prob_accept}},
+  \code{\link{dsnp_arl}}, \code{\link{dsnp_ass}}
+}
+\author{
+Daniela R. Recchia, Emanuel P. Barbosa
+}
diff --git a/man/cchart.R.Rd b/man/cchart.R.Rd
index 6cb6bbf..365a685 100644
--- a/man/cchart.R.Rd
+++ b/man/cchart.R.Rd
@@ -15,7 +15,8 @@ cchart.R(x, n, type = "norm", y = NULL)
 (traditional Shewhart R chart) and "tukey" (exact R chart). If not
 specified, a Shewhart R chart will be plotted.}
 
-\item{y}{The data used in phase I to estimate the standard deviation.}
+\item{y}{The data used in phase I to estimate the standard deviation.
+Required when type = "tukey".}
 }
 \value{
 Return a R control chart.
diff --git a/man/cchart.S.Rd b/man/cchart.S.Rd
index 8bae96d..7e0076f 100644
--- a/man/cchart.S.Rd
+++ b/man/cchart.S.Rd
@@ -13,7 +13,7 @@ cchart.S(x, type = "n", m = NULL)
 plotted where "n" plots a S chart with normalized probability limits and "e"
 plots a S chart with exact limits.}
 
-\item{m}{The sample sizes. Only necessary in the control chart with exact
+\item{m}{The sample size. Only necessary in the control chart with exact
 (probability) limits.}
 }
 \value{
diff --git a/man/cchart.T2.1.Rd b/man/cchart.T2.1.Rd
index d7c8777..18faca2 100644
--- a/man/cchart.T2.1.Rd
+++ b/man/cchart.T2.1.Rd
@@ -7,12 +7,12 @@
 cchart.T2.1(T2, m, n, p)
 }
 \arguments{
-\item{T2}{The values of the T2 statistic. Shoul be a matrix.}
+\item{T2}{The values of the T2 statistic. Should be a numeric vector.}
 
 \item{m}{The number of samples generated previously in data.1.}
 
 \item{n}{The size of each sample used previously in data.1. If they are
-individual obsersations, then use n = 1.}
+individual observations, then use n = 1.}
 
 \item{p}{The dimension used previously in function data.1.}
 }
diff --git a/man/cchart.T2.2.Rd b/man/cchart.T2.2.Rd
index 43fb6c1..57fc150 100644
--- a/man/cchart.T2.2.Rd
+++ b/man/cchart.T2.2.Rd
@@ -46,7 +46,7 @@ datum <- data.1(20, 10, mu, Sigma)
 estat <- stats(datum, 20, 10, 2)
 datum2 <- data.2(estat, 10, p = 2)
 T2II <- T2.2(datum2, estat, 10)
-# For the first sample j = 1. T2II is a vector with the value of the firts T2 statistic.
+# For the first sample j = 1. T2II is a vector with the value of the first T2 statistic.
 cchart.T2.2(T2II, 20, 10, 1, 25, 2)
 # Same of the above, but now showing the phase I data set.
 cchart.T2.2(T2II, 20, 10, 1, 25, 2, datum = datum)
@@ -56,7 +56,7 @@ datum <- data.1(50, 1, mu, Sigma)
 estat <- stats(datum, 50, 1, 2)
 datum2 <- data.2(estat, 1, p = 2)
 T2II <- T2.2(datum2, estat, 1)
-# For the first sample j = 1. T2II is a vector with the value of the firts T2 statistic.
+# For the first sample j = 1. T2II is a vector with the value of the first T2 statistic.
 cchart.T2.2(T2II, 50, 1, 1, 25, 2)
 # Same of the above, but now showing the phase I data set.
 cchart.T2.2(T2II, 50, 1, 1, 25, 2, datum = datum)
diff --git a/man/cchart.Xbar.Rd b/man/cchart.Xbar.Rd
index f346c89..eae192a 100644
--- a/man/cchart.Xbar.Rd
+++ b/man/cchart.Xbar.Rd
@@ -4,16 +4,28 @@
 \alias{cchart.Xbar}
 \title{X-bar Control Chart for phase I and II.}
 \usage{
-cchart.Xbar(x1 = NULL, n1 = NULL, x2 = NULL, n2 = NULL, x2bars = NULL, sigma = NULL)
+cchart.Xbar(
+  x1 = NULL,
+  n1 = NULL,
+  x2 = NULL,
+  n2 = NULL,
+  x2bars = NULL,
+  sigma = NULL
+)
 }
 \arguments{
 \item{x1}{The phase I data to be plotted.}
+
 \item{n1}{A value or a vector of values specifying the sample sizes
 associated with each group for the phase I data.}
+
 \item{x2}{The phase II data to be plotted.}
+
 \item{n2}{A value or a vector of values specifying the sample sizes
 associated with each group for the phase II data.}
+
 \item{x2bars}{The mean of means from phase I.}
+
 \item{sigma}{The standard deviation from phase I.}
 }
 \value{
diff --git a/man/cchart.Xbar1.Rd b/man/cchart.Xbar1.Rd
index dcc6bb3..b59c8bd 100644
--- a/man/cchart.Xbar1.Rd
+++ b/man/cchart.Xbar1.Rd
@@ -13,7 +13,8 @@ cchart.Xbar1(x, sizes)
 associated with each group.}
 }
 \value{
-Return a x-bar control chart for phase I.
+Returns a list with the mean of means (x2bar) and the standard
+deviation (sigma), invisibly. Also plots the control chart as a side effect.
 }
 \description{
 Builds the x-bar control chart for phase I.
@@ -25,7 +26,7 @@ normal by the central limit theorem.
 \examples{
 
 data(pistonrings)
-cchart.Xbar1(pistonrings[1:25, ])
+cchart.Xbar1(pistonrings[1:25, ], 5)
 
 }
 \seealso{
diff --git a/man/cchart.Xbar2.Rd b/man/cchart.Xbar2.Rd
index a22ae6d..0964517 100644
--- a/man/cchart.Xbar2.Rd
+++ b/man/cchart.Xbar2.Rd
@@ -11,7 +11,7 @@ cchart.Xbar2(x, x2bar, sigma, sizes)
 
 \item{x2bar}{The mean of means.}
 
-\item{sigma}{The standar deviation of the data.}
+\item{sigma}{The standard deviation of the data.}
 
 \item{sizes}{A value or a vector of values specifying the sample sizes
 associated with each group.}
@@ -29,8 +29,8 @@ function XbarI.
 \examples{
 
 data(pistonrings)
-stat <- cchart.Xbar1(pistonrings[1:25, ])
-cchart.Xbar2(pistonrings[26:40, ], stat[[1]][1], stat[[1]][2])
+stat <- cchart.Xbar1(pistonrings[1:25, ], 5)
+cchart.Xbar2(pistonrings[26:40, ], stat[[1]][1], stat[[1]][2], 5)
 
 }
 \seealso{
diff --git a/man/cchart.Xbar_R.Rd b/man/cchart.Xbar_R.Rd
index c556921..09c0cf9 100644
--- a/man/cchart.Xbar_R.Rd
+++ b/man/cchart.Xbar_R.Rd
@@ -22,7 +22,7 @@ This function builds the X-bar and R control charts in the same window.
 
 data(pistonrings)
 attach(pistonrings)
-cchart.Xbar_R(pistonrings[1:25, ])
+cchart.Xbar_R(pistonrings[1:25, ], 5)
 
 }
 \author{
diff --git a/man/cchart.p.Rd b/man/cchart.p.Rd
index a8481e6..62e2ca7 100644
--- a/man/cchart.p.Rd
+++ b/man/cchart.p.Rd
@@ -4,8 +4,16 @@
 \alias{cchart.p}
 \title{p-chart}
 \usage{
-cchart.p(x1 = NULL, n1 = NULL, type = "norm", p1 = NULL, x2 = NULL,
-  n2 = NULL, phat = NULL, p2 = NULL)
+cchart.p(
+  x1 = NULL,
+  n1 = NULL,
+  type = "norm",
+  p1 = NULL,
+  x2 = NULL,
+  n2 = NULL,
+  phat = NULL,
+  p2 = NULL
+)
 }
 \arguments{
 \item{x1}{The phase I data that will be plotted (if it is a phase I chart).}
@@ -38,7 +46,7 @@ This function builds p-charts.
 \details{
 For a phase I p-chart, n1 must be specified and either x1 or p1.  For a
 phase II p-chart, n2 must be specified, plus x2 or p2 and either phat, x1
-and n1, or p1 and n1.  The Shewhart is based on normal-aprroximation and
+and n1, or p1 and n1.  The Shewhart is based on normal-approximation and
 should be used only for large values of np or n*p (n*p > 6).
 }
 \examples{
diff --git a/man/cchart.u.Rd b/man/cchart.u.Rd
index d593bc2..84d44fd 100644
--- a/man/cchart.u.Rd
+++ b/man/cchart.u.Rd
@@ -4,8 +4,16 @@
 \alias{cchart.u}
 \title{u-chart}
 \usage{
-cchart.u(x1 = NULL, n1 = NULL, type = "norm", u1 = NULL, x2 = NULL,
-  n2 = NULL, lambda = NULL, u2 = NULL)
+cchart.u(
+  x1 = NULL,
+  n1 = NULL,
+  type = "norm",
+  u1 = NULL,
+  x2 = NULL,
+  n2 = NULL,
+  lambda = NULL,
+  u2 = NULL
+)
 }
 \arguments{
 \item{x1}{The phase I data that will be plotted (if it is a phase I chart).}
diff --git a/man/data.1.Rd b/man/data.1.Rd
index 9033fa2..9f89c15 100644
--- a/man/data.1.Rd
+++ b/man/data.1.Rd
@@ -14,14 +14,14 @@ use n = 1.}
 
 \item{mu}{The vector with the means of the data to be generated.}
 
-\item{Sigma}{The vector with the variance-covariance matrix of the data to
+\item{Sigma}{The variance-covariance matrix of the data to
 be generated.}
 }
 \value{
 Return an array with the simulated data.
 }
 \description{
-This function simulate a normal data set to be used in the phase I Hoteliing
+This function simulates a normal data set to be used in the phase I Hotelling
 control charts.
 }
 \examples{
diff --git a/man/data.2.Rd b/man/data.2.Rd
index 27b10fd..4b733ef 100644
--- a/man/data.2.Rd
+++ b/man/data.2.Rd
@@ -7,8 +7,9 @@
 data.2(estat, n, delta = 0, p)
 }
 \arguments{
-\item{estat}{The values of the auxiliary statistics. Should be a list with a
-matrix with the means, mean of the means and mean of the standard deviation.}
+\item{estat}{The values of the auxiliary statistics. Should be a list with
+the mean of means, the average variance-covariance matrix, and a matrix
+with the means of each sample.}
 
 \item{n}{The size of each sample. If they are individual observations, use n
 = 1.}
diff --git a/man/dsnp_limits.Rd b/man/dsnp_limits.Rd
index be4cbab..af124ce 100644
--- a/man/dsnp_limits.Rd
+++ b/man/dsnp_limits.Rd
@@ -64,6 +64,10 @@ The function enumerates all valid combinations of integer thresholds
 limits compatible with \code{dsnp_prob_accept}, and evaluates each
 candidate's performance at the in-control proportion p0. When p1 is
 supplied, out-of-control metrics are also computed and used for ranking.
+
+When the warning zone is empty (ucl1_reject = wl_accept + 1), the
+chart degenerates to a single-sample scheme and probabilities are
+computed directly via \code{pbinom} without calling the core functions.
 }
 \examples{
 
diff --git a/man/moonroof.Rd b/man/moonroof.Rd
index a2507b3..88c3838 100644
--- a/man/moonroof.Rd
+++ b/man/moonroof.Rd
@@ -4,12 +4,14 @@
 \name{moonroof}
 \alias{moonroof}
 \title{Moonroof}
-\format{A data frame with 34 observations on the following 4 variables.
+\format{
+A data frame with 34 observations on the following 4 variables.
 \describe{ 
 \item{i}{Index.} 
 \item{yi}{The number of defects.} 
 \item{ni}{The sample size.} 
-\item{ui}{The proportion of defects.} }}
+\item{ui}{The proportion of defects.} }
+}
 \source{
 DeVor, R.E.; Chang, T.; Sutherland, J.W., 2007. "Statistical Quality
 Design and Control".
diff --git a/man/pistonrings.Rd b/man/pistonrings.Rd
index 6256240..4e05303 100644
--- a/man/pistonrings.Rd
+++ b/man/pistonrings.Rd
@@ -4,13 +4,15 @@
 \name{pistonrings}
 \alias{pistonrings}
 \title{Piston Rings Data Set.}
-\format{A data frame with 40 observations on the following 5 variables.
+\format{
+A data frame with 40 observations on the following 5 variables.
 \describe{ 
-\item{V1}{The fisrt measure.} 
+\item{V1}{The first measure.} 
 \item{V2}{The second measure.} 
 \item{V3}{The third measure.} 
-\item{V4}{The fouth measure.} 
-\item{V5}{The fifth measure.} }}
+\item{V4}{The fourth measure.} 
+\item{V5}{The fifth measure.} }
+}
 \source{
 Montgomery, D.C.,(2008)."Introduction to Statistical Quality
 Control".4th Ed. Wiley
diff --git a/man/plot.cchart.DSnp.Rd b/man/plot.cchart.DSnp.Rd
new file mode 100644
index 0000000..791a91e
--- /dev/null
+++ b/man/plot.cchart.DSnp.Rd
@@ -0,0 +1,29 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/cchart.DSnp.R
+\name{plot.cchart.DSnp}
+\alias{plot.cchart.DSnp}
+\title{Plot a DS-np Control Chart}
+\usage{
+\method{plot}{cchart.DSnp}(x, ...)
+}
+\arguments{
+\item{x}{An object of class \code{"cchart.DSnp"}.}
+
+\item{...}{Additional graphical parameters (currently unused).}
+}
+\value{
+Invisible \code{x}.
+}
+\description{
+S3 method for plotting objects of class \code{"cchart.DSnp"}.
+}
+\details{
+The plot shows the first-stage counts \code{x1} against the sample index.
+Points requiring a second sample are shown as open circles. Points that
+signal (at either stage) are shown in red. Horizontal lines mark the
+fractional limits.
+
+Note that \code{ucl2} is on the scale of the combined count
+\code{x1 + x2}. The plot is a simple operational visualization; the
+full decision logic is in the returned object.
+}
diff --git a/man/softdrink.Rd b/man/softdrink.Rd
index c5adb5c..aca1960 100644
--- a/man/softdrink.Rd
+++ b/man/softdrink.Rd
@@ -4,7 +4,8 @@
 \name{softdrink}
 \alias{softdrink}
 \title{Soft Drink Data Set.}
-\format{A data frame with 15 lines and 10 columns.  
+\format{
+A data frame with 15 lines and 10 columns.  
 \describe{
 \item{x1}{The first measure.} 
 \item{x2}{The second measure.}
@@ -13,10 +14,11 @@
 \item{x5}{The fifth measure.} 
 \item{x6}{The sixth measure.}
 \item{x7}{The seventh measure.} 
-\item{x8}{The eigth measure.} 
+\item{x8}{The eighth measure.} 
 \item{x9}{The ninth measure.} 
 \item{x10}{The tenth
-measure.} }}
+measure.} }
+}
 \source{
 Montgomery, D.C.,(2001)."Introduction to Statistical Quality
 Control".4th ed. Wiley.
diff --git a/man/table.qtukey.Rd b/man/table.qtukey.Rd
index f992649..db31c2e 100644
--- a/man/table.qtukey.Rd
+++ b/man/table.qtukey.Rd
@@ -13,10 +13,8 @@ to 1 minus the confidence level.}
 \item{n}{The maximum sample size.}
 }
 \value{
-It is used the fact that the sample relative range distribution is
-the same as the sample studentized range distribution (tukey distribution)
-with infinity d.f. in the denominator . It is considered 4 quantiles:
-alpha/2 , alpha , 1-alpha and 1-alpha/2, for different sample size values .
+Returns a matrix with 4 columns containing the quantiles, printed to
+the console and returned invisibly.
 }
 \description{
 Builds a table with quantiles of the sample relative range distribution.
diff --git a/tests/testthat/test-cchart-DSnp.R b/tests/testthat/test-cchart-DSnp.R
new file mode 100644
index 0000000..c74e386
--- /dev/null
+++ b/tests/testthat/test-cchart-DSnp.R
@@ -0,0 +1,315 @@
+# --- cchart.DSnp tests ---
+
+# --- 1. Structure tests ---
+
+test_that("cchart.DSnp returns structured list with plot=FALSE", {
+  x1 <- c(0, 1, 2, 3, 1)
+  x2 <- c(NA, NA, 1, NA, NA)
+  res <- cchart.DSnp(x1, n1 = 10, n2 = 20, p0 = 0.05,
+                     x2 = x2, wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                     plot = FALSE)
+  expect_type(res, "list")
+  expect_s3_class(res, "cchart.DSnp")
+  expect_named(res, c("call", "data", "limits", "parameters", "performance"))
+})
+
+test_that("cchart.DSnp data has correct columns", {
+  x1 <- c(0, 1, 2)
+  x2 <- c(NA, NA, 1)
+  res <- cchart.DSnp(x1, n1 = 10, n2 = 20, p0 = 0.05,
+                     x2 = x2, wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                     plot = FALSE)
+  expect_s3_class(res$data, "data.frame")
+  expect_named(res$data, c("index", "x1", "x2", "total", "stage", "signal"))
+  expect_equal(nrow(res$data), 3)
+})
+
+test_that("cchart.DSnp limits contains all threshold elements", {
+  res <- cchart.DSnp(c(0), n1 = 10, n2 = 20, p0 = 0.05,
+                     wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                     plot = FALSE)
+  expect_named(res$limits, c("wl", "ucl1", "ucl2",
+                              "wl_accept", "ucl1_reject", "ucl2_accept"))
+})
+
+test_that("cchart.DSnp parameters stores inputs", {
+  res <- cchart.DSnp(c(0), n1 = 10, n2 = 20, p0 = 0.05,
+                     wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                     alpha = 0.01, plot = FALSE)
+  expect_equal(res$parameters$n1, 10)
+  expect_equal(res$parameters$n2, 20)
+  expect_equal(res$parameters$p0, 0.05)
+  expect_equal(res$parameters$alpha, 0.01)
+  expect_null(res$parameters$p1)
+})
+
+test_that("cchart.DSnp performance contains arl0, ass0, p_signal0", {
+  res <- cchart.DSnp(c(0), n1 = 10, n2 = 20, p0 = 0.05,
+                     wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                     plot = FALSE)
+  expect_true("arl0" %in% names(res$performance))
+  expect_true("ass0" %in% names(res$performance))
+  expect_true("p_signal0" %in% names(res$performance))
+})
+
+# --- 2. Manual limits integer thresholds ---
+
+test_that("cchart.DSnp integer thresholds are correct", {
+  res <- cchart.DSnp(c(0), n1 = 10, n2 = 20, p0 = 0.05,
+                     wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                     plot = FALSE)
+  expect_equal(res$limits$wl_accept, 1)
+  expect_equal(res$limits$ucl1_reject, 3)
+  expect_equal(res$limits$ucl2_accept, 4)
+})
+
+# --- 3. Classification logic ---
+
+test_that("cchart.DSnp accepts at first stage when x1 <= wl_accept", {
+  # wl_accept = 1, so x1 = 0 and x1 = 1 should accept
+  res <- cchart.DSnp(c(0, 1, 1), n1 = 10, n2 = 20, p0 = 0.05,
+                     wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                     plot = FALSE)
+  expect_equal(res$data$stage[1], "accept_first")
+  expect_false(res$data$signal[1])
+  expect_equal(res$data$stage[2], "accept_first")
+  expect_false(res$data$signal[2])
+})
+
+test_that("cchart.DSnp signals at first stage when x1 >= ucl1_reject", {
+  # ucl1_reject = 3, so x1 = 3 should signal
+  res <- cchart.DSnp(c(3, 4), n1 = 10, n2 = 20, p0 = 0.05,
+                     wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                     plot = FALSE)
+  expect_equal(res$data$stage[1], "signal_first")
+  expect_true(res$data$signal[1])
+  expect_equal(res$data$stage[2], "signal_first")
+  expect_true(res$data$signal[2])
+})
+
+test_that("cchart.DSnp requires second sample when x1 in intermediate zone", {
+  # x1 = 2 is between wl_accept=1 and ucl1_reject=3
+  res <- cchart.DSnp(c(2), n1 = 10, n2 = 20, p0 = 0.05,
+                     x2 = c(1),
+                     wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                     plot = FALSE)
+  expect_equal(res$data$stage[1], "accept_second")
+  expect_false(res$data$signal[1])
+  expect_equal(res$data$total[1], 3)
+})
+
+test_that("cchart.DSnp total <= ucl2_accept accepts at second stage", {
+  # x1=2, x2=2, total=4, ucl2_accept=4 -> accept
+  res <- cchart.DSnp(c(2), n1 = 10, n2 = 20, p0 = 0.05,
+                     x2 = c(2),
+                     wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                     plot = FALSE)
+  expect_equal(res$data$stage[1], "accept_second")
+  expect_false(res$data$signal[1])
+  expect_equal(res$data$total[1], 4)
+})
+
+test_that("cchart.DSnp total > ucl2_accept signals at second stage", {
+  # x1=2, x2=3, total=5, ucl2_accept=4 -> signal
+  res <- cchart.DSnp(c(2), n1 = 10, n2 = 20, p0 = 0.05,
+                     x2 = c(3),
+                     wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                     plot = FALSE)
+  expect_equal(res$data$stage[1], "signal_second")
+  expect_true(res$data$signal[1])
+  expect_equal(res$data$total[1], 5)
+})
+
+# --- 4. Validation error tests ---
+
+test_that("cchart.DSnp errors on negative x1", {
+  expect_error(
+    cchart.DSnp(c(-1), n1 = 10, n2 = 20, p0 = 0.05,
+                wl = 1.5, ucl1 = 2.5, ucl2 = 4.5, plot = FALSE),
+    "x1 must not contain negative values"
+  )
+})
+
+test_that("cchart.DSnp errors when x1 > n1", {
+  expect_error(
+    cchart.DSnp(c(11), n1 = 10, n2 = 20, p0 = 0.05,
+                wl = 1.5, ucl1 = 2.5, ucl2 = 4.5, plot = FALSE),
+    "x1 values must not exceed n1"
+  )
+})
+
+test_that("cchart.DSnp errors on negative x2", {
+  expect_error(
+    cchart.DSnp(c(2), n1 = 10, n2 = 20, p0 = 0.05,
+                x2 = c(-1),
+                wl = 1.5, ucl1 = 2.5, ucl2 = 4.5, plot = FALSE),
+    "x2 must not contain negative values"
+  )
+})
+
+test_that("cchart.DSnp errors when x2 > n2", {
+  expect_error(
+    cchart.DSnp(c(2), n1 = 10, n2 = 20, p0 = 0.05,
+                x2 = c(21),
+                wl = 1.5, ucl1 = 2.5, ucl2 = 4.5, plot = FALSE),
+    "x2 values must not exceed n2"
+  )
+})
+
+test_that("cchart.DSnp errors when x2 needed but missing", {
+  expect_error(
+    cchart.DSnp(c(2), n1 = 10, n2 = 20, p0 = 0.05,
+                wl = 1.5, ucl1 = 2.5, ucl2 = 4.5, plot = FALSE),
+    "Second sample.*required"
+  )
+})
+
+test_that("cchart.DSnp errors when x2 needed but NA", {
+  expect_error(
+    cchart.DSnp(c(2), n1 = 10, n2 = 20, p0 = 0.05,
+                x2 = c(NA),
+                wl = 1.5, ucl1 = 2.5, ucl2 = 4.5, plot = FALSE),
+    "Second sample.*required"
+  )
+})
+
+test_that("cchart.DSnp errors when only partial manual limits provided", {
+  expect_error(
+    cchart.DSnp(c(0), n1 = 10, n2 = 20, p0 = 0.05,
+                wl = 1.5, ucl1 = 2.5, plot = FALSE),
+    "All of.*wl.*ucl1.*ucl2.*must be provided together"
+  )
+  expect_error(
+    cchart.DSnp(c(0), n1 = 10, n2 = 20, p0 = 0.05,
+                wl = 1.5, plot = FALSE),
+    "All of.*wl.*ucl1.*ucl2.*must be provided together"
+  )
+})
+
+test_that("cchart.DSnp errors when limits and manual limits both given", {
+  lim <- dsnp_limits(p0 = 0.05, n1 = 5, n2 = 10, alpha = 0.10,
+                     max_results = 1)
+  expect_error(
+    cchart.DSnp(c(0), n1 = 10, n2 = 20, p0 = 0.05,
+                wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                limits = lim, plot = FALSE),
+    "Cannot specify both.*limits.*and manual"
+  )
+})
+
+test_that("cchart.DSnp errors on non-integer x1", {
+  expect_error(
+    cchart.DSnp(c(1.5), n1 = 10, n2 = 20, p0 = 0.05,
+                wl = 1.5, ucl1 = 2.5, ucl2 = 4.5, plot = FALSE),
+    "x1 must contain integer values"
+  )
+})
+
+# --- 5. Use with dsnp_limits() ---
+
+test_that("cchart.DSnp auto-computes limits via dsnp_limits when none given", {
+  res <- cchart.DSnp(c(0, 1, 2, 0, 1), n1 = 10, n2 = 20, p0 = 0.05,
+                     x2 = c(NA, NA, 1, NA, NA),
+                     plot = FALSE)
+  expect_true(!is.null(res$limits$wl))
+  expect_true(!is.null(res$limits$ucl1))
+  expect_true(!is.null(res$limits$ucl2))
+  expect_true(is.numeric(res$limits$wl))
+})
+
+test_that("cchart.DSnp works with limits object from dsnp_limits", {
+  lim <- dsnp_limits(p0 = 0.05, n1 = 5, n2 = 10, alpha = 0.10,
+                     max_results = 1)
+  res <- cchart.DSnp(c(0, 1, 0), n1 = 5, n2 = 10, p0 = 0.05,
+                     x2 = c(NA, 0, NA),
+                     limits = lim, plot = FALSE)
+  expect_equal(res$limits$wl, lim$best$wl)
+  expect_equal(res$limits$ucl1, lim$best$ucl1)
+  expect_equal(res$limits$ucl2, lim$best$ucl2)
+})
+
+# --- 6. Performance consistency ---
+
+test_that("cchart.DSnp performance matches dsnp_* functions", {
+  wl <- 1.5; ucl1 <- 2.5; ucl2 <- 4.5
+  n1 <- 10; n2 <- 20; p0 <- 0.05
+
+  res <- cchart.DSnp(c(0, 1, 2, 3), n1 = n1, n2 = n2, p0 = p0,
+                     x2 = c(NA, NA, 1, NA),
+                     wl = wl, ucl1 = ucl1, ucl2 = ucl2,
+                     plot = FALSE)
+
+  arl0 <- dsnp_arl(p0, n1, n2, wl, ucl1, ucl2)
+  ass0 <- dsnp_ass(p0, n1, n2, wl, ucl1)
+  pa0  <- dsnp_prob_accept(p0, n1, n2, wl, ucl1, ucl2)
+
+  expect_equal(res$performance$arl0, arl0$arl)
+  expect_equal(res$performance$ass0, ass0$ass)
+  expect_equal(res$performance$p_signal0, pa0$p_signal)
+})
+
+test_that("cchart.DSnp performance includes p1 metrics when p1 provided", {
+  res <- cchart.DSnp(c(0), n1 = 10, n2 = 20, p0 = 0.05,
+                     wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                     p1 = 0.10, plot = FALSE)
+  expect_true("arl1" %in% names(res$performance))
+  expect_true("ass1" %in% names(res$performance))
+  expect_true("p_signal1" %in% names(res$performance))
+
+  arl1 <- dsnp_arl(0.10, 10, 20, 1.5, 2.5, 4.5)
+  expect_equal(res$performance$arl1, arl1$arl)
+})
+
+# --- 7. Plot tests ---
+
+test_that("cchart.DSnp plot=FALSE does not open graphics", {
+  expect_no_error(
+    cchart.DSnp(c(0, 1), n1 = 10, n2 = 20, p0 = 0.05,
+                 wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                 plot = FALSE)
+  )
+})
+
+test_that("cchart.DSnp plot=TRUE produces a plot without error", {
+  pdf(NULL)  # null device
+  on.exit(dev.off())
+  res <- cchart.DSnp(c(0, 1, 2, 3, 0), n1 = 10, n2 = 20, p0 = 0.05,
+                     x2 = c(NA, NA, 1, NA, NA),
+                     wl = 1.5, ucl1 = 2.5, ucl2 = 4.5)
+  expect_s3_class(res, "cchart.DSnp")
+})
+
+# --- 8. Mixed observation types ---
+
+test_that("cchart.DSnp handles mixed stages correctly", {
+  x1 <- c(0, 1, 2, 3, 1, 0, 2, 4, 1, 0)
+  x2 <- c(NA, NA, 2, NA, NA, NA, 3, NA, NA, NA)
+  res <- cchart.DSnp(x1, n1 = 10, n2 = 20, p0 = 0.05,
+                     x2 = x2, wl = 1.5, ucl1 = 2.5, ucl2 = 4.5,
+                     plot = FALSE)
+
+  # x1=0 -> accept_first
+  expect_equal(res$data$stage[1], "accept_first")
+  expect_false(res$data$signal[1])
+
+  # x1=1 -> accept_first
+  expect_equal(res$data$stage[2], "accept_first")
+
+  # x1=2, x2=2 -> total=4, accept_second
+  expect_equal(res$data$stage[3], "accept_second")
+  expect_equal(res$data$total[3], 4)
+  expect_false(res$data$signal[3])
+
+  # x1=3 -> signal_first
+  expect_equal(res$data$stage[4], "signal_first")
+  expect_true(res$data$signal[4])
+
+  # x1=2, x2=3 -> total=5, signal_second
+  expect_equal(res$data$stage[7], "signal_second")
+  expect_equal(res$data$total[7], 5)
+  expect_true(res$data$signal[7])
+
+  # x1=4 -> signal_first
+  expect_equal(res$data$stage[8], "signal_first")
+  expect_true(res$data$signal[8])
+})
diff --git a/vignettes/iqcc-positioning.Rmd b/vignettes/iqcc-positioning.Rmd
index aa6cf8b..94ab703 100644
--- a/vignettes/iqcc-positioning.Rmd
+++ b/vignettes/iqcc-positioning.Rmd
@@ -46,7 +46,7 @@ well calibrated for the distribution and sample size at hand.
 |---|---|---|
 | Range-based dispersion monitoring | Normal approximations can inflate the actual false alarm risk, especially for small subgroups. | Use exact range-chart limits based on the relative range distribution. |
 | Standard deviation monitoring | The distribution of the sample standard deviation is asymmetric for small samples. | Use exact limits derived from the chi-square distribution of the sample variance. |
-| Nonconforming proportion in high-quality processes | The binomial distribution is discrete, bounded, and strongly skewed when the nonconforming proportion is very small. | Use Cornish-Fisher corrected limits or DS-np methods under development. |
+| Nonconforming proportion in high-quality processes | The binomial distribution is discrete, bounded, and strongly skewed when the nonconforming proportion is very small. | Use Cornish-Fisher corrected limits or the double-sampling np chart. |
 | Multivariate process mean monitoring | Hotelling T² requires phase-specific calibration. | Use the implemented Phase I and Phase II Hotelling T² functions. |
 | Multivariate process variability | A single normal approximation for generalized variance may be poorly calibrated. | Candidate future extensions include generalized variance and auxiliary trace charts. |
 
@@ -63,8 +63,8 @@ The current package includes several families of functions:
   monitoring.
 - `alpha.risk()` for studying the actual false alarm risk of classical range
   charts.
-- `dsnp_prob_accept()`, `dsnp_arl()`, and `dsnp_ass()` for the numerical core of
-  double-sampling np charts.
+- `dsnp_prob_accept()`, `dsnp_arl()`, `dsnp_ass()`, `dsnp_limits()`, and
+  `cchart.DSnp()` for double-sampling np charts.
 
 ## Example: using a corrected p chart
 
@@ -86,20 +86,28 @@ cchart.p(
 )
 ```
 
-## Example: inspecting the DS-np numerical core
+## Example: DS-np chart with automatic limit search
 
-The DS-np plotting interface is still under development, but the numerical core
-can already be used to inspect the acceptance probability, average run length,
-and average sample size for a proposed plan.
+The double-sampling np chart uses two sampling stages to monitor the
+nonconforming proportion in high-quality processes. `dsnp_limits()` searches
+for feasible fractional control limits, and `cchart.DSnp()` builds and plots
+the chart.
 
-```{r dsnp-core-example, eval = FALSE}
+```{r dsnp-example, eval = FALSE}
 library(IQCC)
 
-plan <- list(n1 = 34, n2 = 162, wl = 1.5, ucl1 = 2.5, ucl2 = 4.5)
+# Find limits for a given in-control proportion
+lim <- dsnp_limits(p0 = 0.005, n1 = 34, n2 = 162, alpha = 0.0027,
+                   p1 = 0.0075)
+lim$best[, c("wl", "ucl1", "ucl2", "arl0", "arl1", "ass0")]
 
-dsnp_prob_accept(0.005, plan$n1, plan$n2, plan$wl, plan$ucl1, plan$ucl2)
-dsnp_arl(0.005, plan$n1, plan$n2, plan$wl, plan$ucl1, plan$ucl2)
-dsnp_ass(0.005, plan$n1, plan$n2, plan$wl, plan$ucl1)
+# Build the chart from observed data
+x1 <- c(0, 0, 1, 0, 0, 1, 0, 0, 0, 2, 0, 0, 1, 0, 0)
+x2 <- c(NA, NA, NA, NA, NA, NA, NA, NA, NA, 1, NA, NA, NA, NA, NA)
+
+chart <- cchart.DSnp(x1, n1 = 34, n2 = 162, p0 = 0.005,
+                     x2 = x2, limits = lim)
+chart$performance
 ```
 
 ## Development principles
@@ -122,7 +130,6 @@ where classical approximations are simple but inaccurate.
 
 The main planned extensions are:
 
-- automatic limit search and plotting for double-sampling np charts;
 - generalized variance charts for multivariate process variability;
 - Cornish-Fisher corrected generalized variance limits;
 - auxiliary trace charts for complementary multivariate variability monitoring;