feat: --quick economy preset for short, low-cost tests (CLI + REPL + web)

Billing concern: a full run with 2-3 voters, deep chaining and exhaustive recon
burns a lot of tokens. --quick is one switch for a fast, cheap pass:
one voter, one chain round, light recon (intensity 1), ≤6 agents, eco budget.
Dropping voting from 3 models to 1 is the biggest saver.

- CLI: --quick on run/whitebox/greybox (apply_quick, applied last so it wins)
- REPL: /quick (aliases /economy /eco), listed in help + completion
- web: ⚡ Quick-mode checkbox in the wizard -> /quick in the REPL script
- README: documented in the flags table
- 420 tests passing

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

neurosploit-rs/app/src/main.rs

@@ -109,6 +109,11 @@ enum Cmd {
         /// Recon intensity 1-4 (1 quick .. 4 exhaustive; installs tools).
         #[arg(long, default_value_t = 3)]
         recon: usize,
+        /// Economy preset for a short, low-cost test: one voter, one chain
+        /// round, light recon, ≤6 agents, eco budget. Applied last, so it wins
+        /// over the per-knob flags above.
+        #[arg(long)]
+        quick: bool,
         #[arg(long)]
         offline: bool,
         /// Use local agentic CLI subscription (Claude/Codex/Gemini/Grok/OpenCode/Hermes login).
@@ -310,6 +315,9 @@ enum Cmd {
         /// Recon intensity 1-4 (1 quick .. 4 exhaustive; installs tools).
         #[arg(long, default_value_t = 3)]
         recon: usize,
+        /// Economy preset for a short, low-cost review (see `run --quick`).
+        #[arg(long)]
+        quick: bool,
         #[arg(long)]
         offline: bool,
         #[arg(long)]
@@ -348,6 +356,9 @@ enum Cmd {
         /// Recon intensity 1-4 (1 quick .. 4 exhaustive; installs tools).
         #[arg(long, default_value_t = 3)]
         recon: usize,
+        /// Economy preset for a short, low-cost test (see `run --quick`).
+        #[arg(long)]
+        quick: bool,
         #[arg(long)]
         offline: bool,
         #[arg(long)]
@@ -827,7 +838,7 @@ async fn main() -> anyhow::Result<()> {
         Cmd::Internal { graph, scaffold, from, expand, mermaid, save } => {
             handle_internal(graph.as_deref(), scaffold.as_deref(), &from, expand, mermaid, save.as_deref())?
         }
-        Cmd::Run { url, models, max_agents, vote_n, chain_depth, recon, offline, subscription, mcp, creds, focus, objective, out_of_scope, in_scope, scope_file, environment, policy, budget, token_limit, deep_test_limit, coverage_first, depth_first, sample_per_route, revalidate_poc, compliance, jira, only, verbose } => {
+        Cmd::Run { url, models, max_agents, vote_n, chain_depth, recon, quick, offline, subscription, mcp, creds, focus, objective, out_of_scope, in_scope, scope_file, environment, policy, budget, token_limit, deep_test_limit, coverage_first, depth_first, sample_per_route, revalidate_poc, compliance, jira, only, verbose } => {
             let url = if url.starts_with("http") { url } else { format!("https://{url}") };
             let mut cfg = RunConfig::new(&url);
             cfg.max_agents = max_agents;
@@ -853,6 +864,7 @@ async fn main() -> anyhow::Result<()> {
             }
             apply_authorization(&mut cfg, &in_scope, cli.capability_token.clone(), &environment, &policy)?;
             apply_budget(&mut cfg, budget.as_deref(), token_limit, deep_test_limit, coverage_first, depth_first, sample_per_route)?;
+            if quick { apply_quick(&mut cfg); }
             apply_network(&mut cfg, &cli)?;
             cfg.intercept = cli.intercept.clone();
             cfg.sandbox = cli.sandbox.clone();
@@ -868,7 +880,7 @@ async fn main() -> anyhow::Result<()> {
             let ig = harness::integrations::Integrations::load(&repl::proj_dir());
             post_integrations(&ig, &url, &out, jira, false, None).await;
         }
-        Cmd::Whitebox { path, models, max_agents, vote_n, chain_depth, recon, offline, subscription, jira, only, verbose } => {
+        Cmd::Whitebox { path, models, max_agents, vote_n, chain_depth, recon, quick, offline, subscription, jira, only, verbose } => {
             let path = resolve_source(&base, &path)?; // local path OR github URL/owner/repo
             let mut cfg = RunConfig::new(&path);
             cfg.max_agents = max_agents;
@@ -879,6 +891,7 @@ async fn main() -> anyhow::Result<()> {
             cfg.subscription = subscription;
             cfg.verbose = verbose;
             cfg.pinned = parse_only(&only);
+            if quick { apply_quick(&mut cfg); }
             if !models.is_empty() {
                 cfg.models = models;
             }
@@ -887,7 +900,7 @@ async fn main() -> anyhow::Result<()> {
             let ig = harness::integrations::Integrations::load(&repl::proj_dir());
             post_integrations(&ig, &path, &out, jira, false, None).await;
         }
-        Cmd::Greybox { repo, url, models, creds, focus, max_agents, vote_n, chain_depth, recon, offline, subscription, mcp, only, verbose } => {
+        Cmd::Greybox { repo, url, models, creds, focus, max_agents, vote_n, chain_depth, recon, quick, offline, subscription, mcp, only, verbose } => {
             let repo = resolve_source(&base, &repo)?; // local path OR github URL/owner/repo
             let url = if url.starts_with("http") { url } else { format!("https://{url}") };
             let mut cfg = RunConfig::new(&url);
@@ -901,6 +914,7 @@ async fn main() -> anyhow::Result<()> {
             cfg.verbose = verbose;
             cfg.instructions = focus;
             cfg.pinned = parse_only(&only);
+            if quick { apply_quick(&mut cfg); }
             if !models.is_empty() {
                 cfg.models = models;
             }
@@ -1965,6 +1979,23 @@ fn apply_budget(
     Ok(())
 }
 
+/// `--quick`: a single economy preset for a short, low-cost test. Applied LAST,
+/// so it deliberately wins over the per-knob flags — one switch the operator
+/// reaches for when they just want a fast, cheap pass instead of a full
+/// engagement: one voter, one chaining round, light recon, a hard cap on
+/// breadth, under the `eco` budget (deep reasoning only on the strongest
+/// signals). The single biggest token saver here is dropping voting from 2-3
+/// models to one.
+fn apply_quick(cfg: &mut RunConfig) {
+    use harness::budget::{Budget, Mode};
+    cfg.vote_n = 1;
+    cfg.chain_depth = 1;
+    cfg.recon_intensity = 1;
+    cfg.max_agents = 6;
+    cfg.budget = Budget::with_mode(Mode::Eco);
+    println!("  \x1b[2mquick: economy preset — 1 voter, 1 chain round, light recon, ≤6 agents, eco budget\x1b[0m");
+}
+
 /// Egress route, out-of-band channel and inbound SMS.
 ///
 /// The transport spec is parsed here rather than at run time so a typo fails

neurosploit-rs/app/src/repl.rs

@@ -152,7 +152,7 @@ pub(crate) const ACCEPTED: &[&str] = &[
     "/history", "/idle", "/inscope", "/instructions", "/integration", "/integrations", "/key", "/log",
     "/logs", "/mcp", "/memory", "/model", "/models", "/objective", "/objectives", "/observe",
     "/observe-only", "/offline",
-    "/onboard", "/only", "/oos", "/outofscope", "/policy", "/providers", "/proxy", "/q", "/quit", "/recon",
+    "/onboard", "/only", "/oos", "/outofscope", "/policy", "/providers", "/proxy", "/quick", "/economy", "/eco", "/q", "/quit", "/recon",
     "/pause", "/repo", "/report", "/results", "/resume", "/retest", "/revalidate", "/run", "/runs",
     "/scope", "/scope-out", "/show", "/status", "/stop", "/sub", "/subscription", "/target",
     "/temp-email", "/tempmail", "/theme", "/timeout", "/ua", "/url", "/useragent", "/validate",
@@ -163,7 +163,7 @@ pub(crate) const ACCEPTED: &[&str] = &[
 const COMMANDS: &[&str] = &[
     "/help", "/onboard", "/show", "/config", "/providers", "/model", "/key", "/sub", "/target",
     "/repo", "/auth", "/creds", "/focus", "/objective", "/scope-out", "/attach", "/context", "/mcp", "/offline",
-    "/votes", "/chain", "/recon", "/tempmail", "/timeout", "/proxy", "/burp", "/ua", "/agents", "/only", "/theme", "/clear", "/run", "/stop", "/pause", "/continue", "/runs", "/results", "/report",
+    "/quick", "/economy", "/eco", "/votes", "/chain", "/recon", "/tempmail", "/timeout", "/proxy", "/burp", "/ua", "/agents", "/only", "/theme", "/clear", "/run", "/stop", "/pause", "/continue", "/runs", "/results", "/report",
     "/status", "/logs", "/diff", "/retest", "/validate", "/finding", "/expand", "/integrations",
     "/memory", "/forget", "/graph", "/inscope", "/observe", "/guardrail", "/policy",
     "/capability", "/audit", "/quit",
@@ -846,6 +846,18 @@ pub async fn repl(base: &Path, auth: SessionAuth) -> anyhow::Result<()> {
                 if arg.is_empty() { println!("  recon intensity: {} ({}) — set with /recon <1-4>  [1 quick · 2 standard · 3 deep · 4 exhaustive]", s.recon_intensity, lvl(s.recon_intensity)); }
                 else { s.recon_intensity = arg.parse::<usize>().unwrap_or(s.recon_intensity).clamp(1, 4); println!("  recon intensity: {} ({}) — more rounds, more enumeration, auto-installs tools", s.recon_intensity, lvl(s.recon_intensity)); }
             }
+            "/quick" | "/economy" | "/eco" => {
+                // Economy preset for a short, low-cost test — the single switch
+                // for "fast and cheap" instead of tuning each knob. The big
+                // saver is one voter instead of two or three.
+                s.vote_n = 1;
+                s.chain_depth = 1;
+                s.recon_intensity = 1;
+                s.max_agents = 6;
+                println!("  \x1b[1;32m⚡ quick mode\x1b[0m — economy preset for a short, low-cost run:");
+                println!("    1 voter · 1 chain round · light recon · ≤6 agents");
+                println!("    \x1b[2m(raise any back up with /votes /chain /recon /agents — or /run to go)\x1b[0m");
+            }
             "/tempmail" | "/temp-email" => {
                 match arg.trim() {
                     "on" | "true" | "1" => { s.temp_email = true; println!("  temp-email: \x1b[32mon\x1b[0m — register flows may use the free mail.tm inbox to read a confirmation code"); }
@@ -2224,6 +2236,7 @@ fn help() {
     h("/votes <n>",         "number of validator votes per finding");
     h("/chain <n>",         "attack-chain depth (post-exploitation pivots; 0 = off)");
     h("/recon <1-4>",       "recon intensity: 1 quick · 2 standard · 3 deep · 4 exhaustive (installs tools)");
+    h("/quick",             "economy preset: short, low-cost run (1 voter · 1 chain round · light recon · ≤6 agents)");
     h("/tempmail on|off",   "opt-in disposable inbox (mail.tm) to read a register confirmation code");
     h("/timeout <min>",     "idle guardrail: stop if no new finding in <min> (0 = off)");
     h("/proxy <url>|off",   "route agent HTTP through Burp/ZAP  (/burp = default :8080)");