agentsys 5.3.7 → 5.4.1

package/.agnix.toml

@@ -25,23 +25,33 @@ mcp = true
 imports = true
 cross_platform = false # Intentional - we document all 3 platform paths
 agents_md = true
-copilot = false # Not targeting Copilot
-cursor = false # Not targeting Cursor
+kiro_agents = false # Kiro agent copies reference agentsys subagents not resolvable from .kiro/
 prompt_engineering = true
 generic_instructions = true
 frontmatter_validation = true
 xml_balance = true
 import_references = true
 disabled_rules = [
-    "XP-003",      # Intentional - we document all 3 platform paths (.claude/, .opencode/, .codex/)
+    "AGM-003",     # docs/reference/AGENTS.md is a comprehensive reference doc
+    "AGM-005",     # Cursor platform examples are reference content in AGENTS.md
+    "AGM-006",     # Intentional - root AGENTS.md (instructions) + docs/reference/AGENTS.md (reference)
+    "AS-012",      # enhance-hooks is a comprehensive hook reference (needs >500 lines)
     "AS-014",      # False positives on regex escape sequences (\n, \s, \d)
     "CC-AG-009",   # False positive - Skill, AskUserQuestion, LSP are valid Claude Code tools
+    "CC-HK-008",   # Hook script path resolution differs on Windows (forward slash prefix)
+    "CC-MEM-005",  # "Be concise" is ecosystem-wide boilerplate
+    "CC-MEM-006",  # Negative instructions (NEVER/Do not) are ecosystem standard critical rules
     "CC-MEM-009",  # Intentional - CLAUDE.md uses structured sections, size is necessary
-    "AGM-006",     # Intentional - root AGENTS.md (instructions) + docs/reference/AGENTS.md (reference)
-    "AGM-003",     # docs/reference/AGENTS.md is a comprehensive reference doc
-    "PE-001",      # Reference docs have structured layout; middle placement is intentional
-    "AS-012",      # enhance-hooks is a comprehensive hook reference (needs >500 lines)
     "CC-SK-009",   # enhance-skills contains example injections for teaching purposes
+    "CC-SK-012",   # Intentional - argument-hint present for UI display
+    "CC-SK-017",   # Intentional - version is a client-specific frontmatter field
+    "CDX-AG-002",  # False positive - "tokens" in ecosystem boilerplate is not a secret
+    "CDX-AG-005",  # Codex agent instruction format - AGENTS.md uses agentsys conventions
+    "KR-SK-001",   # Kiro skill copies use Claude Code frontmatter fields (version, argument-hint)
+    "PE-001",      # Reference docs have structured layout; middle placement is intentional
+    "PE-005",      # Same as CC-MEM-005 for prompt engineering rules
+    "XML-001",     # False positive - <login-url> is a placeholder in examples
+    "XP-003",      # Intentional - we document all 3 platform paths (.claude/, .opencode/, .codex/)
 ]
 
 [tool_versions]

package/.claude-plugin/marketplace.json

@@ -1,7 +1,7 @@
 {
   "name": "agentsys",
-  "description": "14 specialized plugins for AI workflow automation - task orchestration, PR workflow, slop detection, code review, drift detection, enhancement analysis, documentation sync, repo mapping, perf investigations, topic research, agent config linting, cross-tool AI consultation, and structured AI debate",
-  "version": "5.3.7",
+  "description": "15 specialized plugins for AI workflow automation - task orchestration, PR workflow, slop detection, code review, drift detection, enhancement analysis, documentation sync, repo mapping, perf investigations, topic research, agent config linting, cross-tool AI consultation, structured AI debate, and workflow pattern learning",
+  "version": "5.4.1",
   "owner": {
     "name": "Avi Fenesh",
     "url": "https://github.com/avifenesh"
@@ -175,6 +175,17 @@
       "version": "1.0.0",
       "category": "automation",
       "homepage": "https://github.com/agent-sh/web-ctl"
+    },
+    {
+      "name": "skillers",
+      "source": {
+        "source": "url",
+        "url": "https://github.com/agent-sh/skillers.git"
+      },
+      "description": "Learn from workflow patterns across sessions and suggest skills, hooks, and agents to automate repetitive work",
+      "version": "1.0.0",
+      "category": "productivity",
+      "homepage": "https://github.com/agent-sh/skillers"
     }
   ]
 }

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agentsys",
-  "version": "5.3.7",
+  "version": "5.4.1",
   "description": "Professional-grade slash commands for Claude Code with cross-platform support",
   "keywords": [
     "workflow",

package/.gitmodules

@@ -0,0 +1,3 @@
+[submodule "agent-knowledge"]
+	path = agent-knowledge
+	url = https://github.com/agent-sh/agent-knowledge.git

package/AGENTS.md

@@ -150,12 +150,12 @@ agentsys                # Run installer
 <agents>
 ## Agents
 
-43 agents across 14 plugins. Key agents by model:
+35 agents across 15 plugins. Key agents by model:
 
 | Model | Agents | Use Case |
 |-------|--------|----------|
-| **opus** | exploration, planning, implementation, perf-orchestrator | Complex reasoning, analysis |
-| **sonnet** | task-discoverer, delivery-validator, ci-fixer, deslop-agent, reporters | Validation, pattern matching |
+| **opus** | exploration, planning, implementation, perf-orchestrator, debate-orchestrator, skillers-recommender | Complex reasoning, analysis |
+| **sonnet** | task-discoverer, delivery-validator, ci-fixer, deslop-agent, reporters, learn, release-agent, skillers-compactor | Validation, pattern matching |
 | **haiku** | worktree-manager, ci-monitor, simple-fixer | Mechanical execution |
 
 See [README.md](./README.md#command-details) and [docs/reference/AGENTS.md](./docs/reference/AGENTS.md) for full agent list.
@@ -164,7 +164,7 @@ See [README.md](./README.md#command-details) and [docs/reference/AGENTS.md](./do
 <skills>
 ## Skills
 
-25 skills across plugins. Agents invoke skills for reusable implementation.
+32 skills across plugins. Agents invoke skills for reusable implementation.
 
 | Category | Key Skills |
 |----------|------------|

package/CHANGELOG.md

@@ -7,6 +7,43 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [5.4.1] - 2026-03-10
+
+### Added
+
+- **Project base branch** (`--base=BRANCH`) - `/next-task` now supports configuring a project-level base branch for batch workflows. All downstream operations (worktrees, diffs, PRs) use the configured branch instead of main.
+- **Free-text preference caching** - When users select "Other" for any policy decision and type a custom response, it gets cached and offered as an option next time. Auto-removed after 3 skips.
+- **Gate 0 hook** - SubagentStop hook blocks Phase 2 unless policy decisions are persisted to preference cache.
+- **Multi-tool transcript support** - `/skillers compact` now reads from Claude Code, Codex CLI, and OpenCode (was Claude Code only).
+
+### Fixed
+
+- **ship target branch validation** - `/ship` now reads `baseBranch` from flow state and validates non-default targets with user confirmation.
+- **Quality sweep** - Removed 95 lines of prose slop and duplication across ship and skillers.
+- **Pre-push hooks** - Fixed for repos without `npm test` script (falls back to JS syntax check).
+- **Cached source null check** - `getPolicyQuestions` no longer crashes when preference file has freeText but no source.
+
+## [5.4.0] - 2026-03-10
+
+### Added
+
+- **`/release` command** - Discovery-first release workflow that detects how a repo releases before executing. Supports 12+ ecosystems (npm, cargo, python, go, maven, gradle, ruby, nuget, dart, hex, packagist, swift) and 7 release tool configurations (semantic-release, release-it, goreleaser, changesets, cargo-release, lerna, standard-version).
+- **`/skillers` command** - Transcript-based workflow pattern learning. Analyzes Claude Code conversation history, clusters recurring patterns into weighted themes, and suggests skills/hooks/agents to automate repetitive work.
+- **release-agent** (sonnet) - Discovers release method via tool configs, CI workflows, scripts, and manifests before performing the release.
+- **skillers-compactor** (sonnet) - Extracts observations from conversation transcripts and clusters them into knowledge themes.
+- **skillers-recommender** (opus) - Analyzes accumulated knowledge and classifies patterns as hook/skill/agent recommendations.
+- **Agnix CI validation** - All plugins now run agnix lint in CI pipelines.
+- **agent-knowledge submodule** - Research guides available as a git submodule.
+- **Website additions** - How It Works content for consult, debate, web-ctl tabs.
+
+### Fixed
+
+- **Accurate ecosystem counts** - Stats now show 15 plugins, 35 agents, 32 skills, 3,751 tests, 14 commands. Previously showed inflated/stale counts.
+- **Pinned action SHAs** - Updated to latest stable versions for security.
+- **CodeQL regex** - Fixed inefficient regular expression flagged by code scanning.
+- **Go test fixture** - Added go.mod so CodeQL can analyze Go fixtures.
+- **Website CSS** - Reduced commands section bottom padding, removed inline how-it-works paragraphs.
+
 ## [5.3.7] - 2026-03-02
 
 ### Fixed

package/README.md

@@ -21,7 +21,7 @@
 </p>
 
 <p align="center">
-  <b>14 plugins · 43 agents · 30 skills (across all repos) · 30k lines of lib code · 3,750 tests · 5 platforms</b><br>
+  <b>15 plugins · 35 agents · 32 skills (across all repos) · 30k lines of lib code · 3,751 tests · 5 platforms</b><br>
   <em>Plugins distributed as standalone repos under <a href="https://github.com/agent-sh">agent-sh</a> org — agentsys is the marketplace &amp; installer</em>
 </p>
 
@@ -47,7 +47,7 @@ AI models can write code. That's not the hard part anymore. The hard part is eve
 
 ## What This Is
 
-An agent orchestration system — 14 plugins, 43 agents, and 30 skills that compose into structured pipelines for software development. Each plugin lives in its own standalone repo under the [agent-sh](https://github.com/agent-sh) org. agentsys is the marketplace and installer that ties them together.
+An agent orchestration system — 15 plugins, 35 agents, and 32 skills that compose into structured pipelines for software development. Each plugin lives in its own standalone repo under the [agent-sh](https://github.com/agent-sh) org. agentsys is the marketplace and installer that ties them together.
 
 Each agent has a single responsibility, a specific model assignment, and defined inputs/outputs. Pipelines enforce phase gates so agents can't skip steps. State persists across sessions so work survives interruptions.
 
@@ -104,8 +104,8 @@ Skills are the reusable implementation units. Agents invoke skills; commands orc
 | Section | What's there |
 |---------|--------------|
 | [The Approach](#the-approach) | Why it's built this way |
-| [Commands](#commands) | All 13 commands overview |
-| [Skills](#skills) | 30 skills across plugins |
+| [Commands](#commands) | All 14 commands overview |
+| [Skills](#skills) | 32 skills across plugins |
 | [Command Details](#command-details) | Deep dive into each command |
 | [How Commands Work Together](#how-commands-work-together) | Standalone vs integrated |
 | [Design Philosophy](#design-philosophy) | The thinking behind the architecture |
@@ -765,6 +765,47 @@ npx playwright install chromium
 
 **Skills:** web-auth (human-in-the-loop auth), web-browse (headless actions)
 
+### /release
+
+> Versioned release with automatic ecosystem and tooling detection
+
+```bash
+/release                # Patch release (auto-discovers how this repo releases)
+/release minor          # Minor version bump
+/release major --dry-run # Preview what would happen
+```
+
+The release agent discovers how your repo releases before executing:
+
+1. **Checks for release tools** - semantic-release, release-it, goreleaser, changesets, cargo-release
+2. **Checks for scripts** - Makefile `release:` target, npm `release` script, `scripts/release.*`
+3. **Falls back to generic** - Version bump, changelog, tag, push, GitHub release, publish
+
+Supports 12+ ecosystems: npm, cargo, python, go, maven, gradle, ruby, nuget, dart, hex, packagist, swift.
+
+**Agent:** release-agent (sonnet model)
+
+**Skill:** release (generic fallback workflow)
+
+### /skillers
+
+> Learn from your workflow patterns and suggest automations
+
+```bash
+/skillers show              # Display current config and knowledge stats
+/skillers compact           # Analyze recent transcripts, extract patterns
+/skillers compact --days=14 # Analyze older transcripts
+/skillers recommend         # Get automation suggestions from accumulated knowledge
+```
+
+Reads your Claude Code conversation transcripts, identifies recurring patterns (pain points, repeated workflows, wishes), clusters them into weighted themes, and suggests skills, hooks, or agents to automate them.
+
+No per-turn overhead - it reads transcripts that Claude Code already saves.
+
+**Agents:** skillers-compactor (sonnet), skillers-recommender (opus)
+
+**Skills:** compact, recommend
+
 ---
 
 ## How Commands Work Together
@@ -970,7 +1011,7 @@ The system is built on research, not guesswork.
 - Instruction following reliability
 
 **Testing:**
-- 3,750 tests passing
+- 3,751 tests passing
 - Drift-detect validated on 1,000+ repositories
 - E2E workflow testing across all commands
 - Cross-platform validation (Claude Code, OpenCode, Codex CLI, Cursor, Kiro)

package/lib/adapter-transforms.js

@@ -490,7 +490,9 @@ function transformCommandForKiro(content, options) {
   // template literals inside the code as false fence endings.
   content = content.replace(/^```(?:javascript|js)?\n([\s\S]*?)^```$/gm, (fullBlock, codeContent) => {
     if (!codeContent.includes('Promise.all') || !codeContent.includes('Task(')) return fullBlock;
-    const taskMatches = [...codeContent.matchAll(/Task\s*\(\s*\{[\s\S]*?subagent_type:\s*['"](?:[^"':]+:)?([^'"]+)['"][\s\S]*?prompt:\s*`((?:[^`]|\$\{[^}]*\})*)`/gs)];
+    // Use lazy [\s\S]*? for the template literal body: it stops at the first backtick and
+    // naturally matches any character including standalone $ (e.g. $100, $BUDGET).
+    const taskMatches = [...codeContent.matchAll(/Task\s*\(\s*\{[\s\S]*?subagent_type:\s*['"](?:[^"':]+:)?([^'"]+)['"][\s\S]*?prompt:\s*`([\s\S]*?)`/gs)];
     if (taskMatches.length < 2) return fullBlock;
 
     const delegations = taskMatches.map(m => {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentsys",
-  "version": "5.3.7",
+  "version": "5.4.1",
   "description": "A modular runtime and orchestration system for AI agents - works with Claude Code, OpenCode, and Codex CLI",
   "main": "lib/platform/detect-platform.js",
   "type": "commonjs",

package/site/assets/css/main.css

@@ -645,7 +645,7 @@
  * COMMANDS SECTION
  * -------------------------------------------------------------------------- */
 .commands {
-  padding: var(--space-24) var(--space-6);
+  padding: var(--space-24) var(--space-6) var(--space-16);
 }
 
 .commands__inner {
@@ -903,6 +903,44 @@
   color: var(--color-text-faint);
 }
 
+/* --------------------------------------------------------------------------
+ * SCROLL CUE
+ * -------------------------------------------------------------------------- */
+.scroll-cue {
+  text-align: center;
+  padding: var(--space-8) 0 var(--space-4);
+}
+
+.scroll-cue__link {
+  display: inline-flex;
+  flex-direction: column;
+  align-items: center;
+  gap: var(--space-2);
+  color: var(--color-text-tertiary);
+  text-decoration: none;
+  transition: color 0.2s ease;
+}
+
+.scroll-cue__link:hover {
+  color: var(--color-text-primary);
+}
+
+.scroll-cue__text {
+  font-size: var(--text-sm);
+  font-weight: 500;
+  letter-spacing: 0.05em;
+  text-transform: uppercase;
+}
+
+.scroll-cue__arrow {
+  animation: scroll-bounce 2s ease-in-out infinite;
+}
+
+@keyframes scroll-bounce {
+  0%, 100% { transform: translateY(0); }
+  50% { transform: translateY(6px); }
+}
+
 /* --------------------------------------------------------------------------
  * HOW IT WORKS
  * -------------------------------------------------------------------------- */

package/site/assets/js/main.js

@@ -658,6 +658,30 @@
           { title: 'Score sources', desc: 'Each source is scored by quality, relevance, and authority. Low-quality sources are filtered out.' },
           { title: 'Create guide', desc: 'Synthesizes a structured learning guide with RAG-optimized index saved for future agent lookups.' }
         ]
+      },
+      11: {
+        subtitle: 'Ask another AI. Get a second opinion.',
+        steps: [
+          { title: 'Detect tools', desc: 'Finds which AI CLI tools are installed on your system. Picks the right model and flags for your effort level.' },
+          { title: 'Run consultation', desc: 'Spawns the tool via ACP (JSON-RPC 2.0 over stdio) or CLI with safe-mode defaults and a 240s timeout.' },
+          { title: 'Return response', desc: 'Parses output, redacts secrets (Shannon entropy > 4.0), and returns the response. Supports session continuations.' }
+        ]
+      },
+      12: {
+        subtitle: 'Two AIs argue. You get the truth.',
+        steps: [
+          { title: 'Set up debate', desc: 'Parses natural language to identify proposer, challenger, topic, rounds, and effort level.' },
+          { title: 'Run rounds', desc: 'Proposer builds a case with evidence. Challenger responds with counterpoints. Each round refines the arguments.' },
+          { title: 'Deliver verdict', desc: 'The orchestrator synthesizes all rounds and picks a winner with reasoning and actionable takeaways.' }
+        ]
+      },
+      13: {
+        subtitle: 'Browser automation. Encrypted sessions.',
+        steps: [
+          { title: 'Start session', desc: 'Creates an encrypted browser profile using AES-256-GCM. No daemon - each action is a single Playwright process.' },
+          { title: 'Authenticate', desc: 'Opens headed Chrome for human login (2FA, CAPTCHAs). Polls for success, then encrypts cookies for reuse.' },
+          { title: 'Run headless', desc: 'Subsequent actions run headless using saved cookies. Snapshot-based element discovery with classified error codes.' }
+        ]
       }
     };
 

package/site/content.json

@@ -1,11 +1,11 @@
 {
   "meta": {
     "title": "agentsys",
-    "description": "A modular runtime and orchestration system for AI agents. 14 plugins, 43 agents, 30 skills — structured pipelines for Claude Code, OpenCode, Codex CLI, Cursor, and Kiro.",
+    "description": "A modular runtime and orchestration system for AI agents. 15 plugins, 35 agents, 32 skills - structured pipelines for Claude Code, OpenCode, Codex CLI, Cursor, and Kiro.",
     "url": "https://agent-sh.github.io/agentsys",
     "repo": "https://github.com/agent-sh/agentsys",
     "npm": "https://www.npmjs.com/package/agentsys",
-    "version": "5.3.7",
+    "version": "5.4.1",
     "author": "Avi Fenesh",
     "author_url": "https://github.com/avifenesh"
   },
@@ -43,7 +43,7 @@
       "suffix": ""
     },
     {
-      "value": "3,750",
+      "value": "3,751",
       "label": "Tests",
       "suffix": ""
     },
@@ -463,7 +463,7 @@
   ],
   "research": {
     "knowledge_base": "8,000 lines of curated documentation from Anthropic, OpenAI, Google, and Microsoft",
-    "testing": "3,750 tests passing",
+    "testing": "3,751 tests passing",
     "drift_detect_repos": "1,000+ repositories validated",
     "token_reduction": "77% fewer tokens for drift-detect vs multi-agent approaches"
   },

package/site/index.html

@@ -4,12 +4,12 @@
   <meta charset="UTF-8">
   <meta name="viewport" content="width=device-width, initial-scale=1">
   <title>AgentSys - Agent Runtime &amp; Orchestration System</title>
-  <meta name="description" content="A modular runtime and orchestration system for AI agents. 14 plugins, 43 agents, 30 skills — structured pipelines for Claude Code, OpenCode, Codex CLI, Cursor, and Kiro.">
+  <meta name="description" content="A modular runtime and orchestration system for AI agents. 15 plugins, 35 agents, 32 skills — structured pipelines for Claude Code, OpenCode, Codex CLI, Cursor, and Kiro.">
   <meta name="theme-color" content="#09090b">
 
   <!-- Open Graph -->
   <meta property="og:title" content="AgentSys">
-  <meta property="og:description" content="A modular runtime and orchestration system for AI agents. 14 plugins, 43 agents, 30 skills.">
+  <meta property="og:description" content="A modular runtime and orchestration system for AI agents. 15 plugins, 35 agents, 32 skills.">
   <meta property="og:image" content="https://agent-sh.github.io/agentsys/assets/logo.png">
   <meta property="og:url" content="https://agent-sh.github.io/agentsys/">
   <meta property="og:type" content="website">
@@ -17,7 +17,7 @@
   <!-- Twitter Card -->
   <meta name="twitter:card" content="summary_large_image">
   <meta name="twitter:title" content="AgentSys">
-  <meta name="twitter:description" content="AI workflow automation. 14 plugins, 43 agents, 30 skills.">
+  <meta name="twitter:description" content="AI workflow automation. 15 plugins, 35 agents, 32 skills.">
   <meta name="twitter:image" content="https://agent-sh.github.io/agentsys/assets/logo.png">
 
   <!-- Content Security Policy -->
@@ -109,14 +109,14 @@
       <div class="hero__inner">
         <div class="hero__content">
           <div class="hero__badge anim-fade-in" data-delay="100">
-            14 plugins &middot; 43 agents &middot; 30 skills
+            15 plugins &middot; 35 agents &middot; 32 skills
           </div>
           <h1 class="hero__title anim-fade-up" id="hero-title" data-delay="200">
             A modular <span class="text-gradient">runtime and orchestration system</span><br>
             for AI agents.
           </h1>
           <p class="hero__subtitle anim-fade-up" data-delay="350">
-            Structured pipelines, gated phases, specialized agents. Works with Claude Code, OpenCode, and Codex CLI. 3,917 tests. Production-grade.
+            Structured pipelines, gated phases, specialized agents. Works with Claude Code, OpenCode, Codex CLI, Cursor, and Kiro. 3,750 tests. Production-grade.
           </p>
           <div class="hero__ctas anim-fade-up" data-delay="500">
             <a href="#install" class="btn btn--primary">Get Started</a>
@@ -195,6 +195,9 @@
             <button class="tabs__tab" role="tab" aria-selected="false" aria-controls="tab-panel-8" id="tab-8" tabindex="-1" data-index="8">/repo-map</button>
             <button class="tabs__tab" role="tab" aria-selected="false" aria-controls="tab-panel-9" id="tab-9" tabindex="-1" data-index="9">/sync-docs</button>
             <button class="tabs__tab" role="tab" aria-selected="false" aria-controls="tab-panel-10" id="tab-10" tabindex="-1" data-index="10">/learn</button>
+            <button class="tabs__tab" role="tab" aria-selected="false" aria-controls="tab-panel-11" id="tab-11" tabindex="-1" data-index="11">/consult</button>
+            <button class="tabs__tab" role="tab" aria-selected="false" aria-controls="tab-panel-12" id="tab-12" tabindex="-1" data-index="12">/debate</button>
+            <button class="tabs__tab" role="tab" aria-selected="false" aria-controls="tab-panel-13" id="tab-13" tabindex="-1" data-index="13">/web-ctl</button>
           </div>
 
           <!-- Tab panels -->
@@ -406,10 +409,75 @@
 <span class="code-prompt">$</span> /learn kubernetes --depth=brief    <span class="code-comment"># Quick overview</span></code></pre>
             </div>
           </div>
+
+          <div class="tabs__panel" role="tabpanel" id="tab-panel-11" aria-labelledby="tab-11" hidden>
+            <h3 class="tabs__panel-name">/consult</h3>
+            <p class="tabs__panel-tagline">Get a second opinion from another AI tool</p>
+            <ul class="tabs__panel-features">
+              <li>Cross-tool AI consultation via ACP transport</li>
+              <li>6 providers: Claude, Gemini, Codex, Copilot, Kiro, OpenCode</li>
+              <li>Effort-mapped model selection per provider</li>
+              <li>Session continuations and context injection</li>
+            </ul>
+            <div class="code-block">
+              <button class="code-block__copy" aria-label="Copy code to clipboard" data-code="/consult &quot;Is this the right approach?&quot; --tool=gemini --effort=high
+/consult &quot;Review for performance&quot; --tool=codex">
+                <svg width="16" height="16" viewBox="0 0 16 16" fill="currentColor" aria-hidden="true"><path d="M0 6.75C0 5.784.784 5 1.75 5h1.5a.75.75 0 010 1.5h-1.5a.25.25 0 00-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 00.25-.25v-1.5a.75.75 0 011.5 0v1.5A1.75 1.75 0 019.25 16h-7.5A1.75 1.75 0 010 14.25v-7.5z"/><path d="M5 1.75C5 .784 5.784 0 6.75 0h7.5C15.216 0 16 .784 16 1.75v7.5A1.75 1.75 0 0114.25 11h-7.5A1.75 1.75 0 015 9.25v-7.5zm1.75-.25a.25.25 0 00-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 00.25-.25v-7.5a.25.25 0 00-.25-.25h-7.5z"/></svg>
+              </button>
+              <pre><code><span class="code-prompt">$</span> /consult "Is this the right approach?" --tool=gemini <span class="code-comment"># Second opinion</span>
+<span class="code-prompt">$</span> /consult "Review for performance" --tool=codex      <span class="code-comment"># Codex review</span></code></pre>
+            </div>
+          </div>
+
+          <div class="tabs__panel" role="tabpanel" id="tab-panel-12" aria-labelledby="tab-12" hidden>
+            <h3 class="tabs__panel-name">/debate</h3>
+            <p class="tabs__panel-tagline">Structured adversarial debate between AI tools</p>
+            <ul class="tabs__panel-features">
+              <li>Multi-round proposer/challenger format</li>
+              <li>Evidence-backed arguments with mandatory counterpoints</li>
+              <li>Any two AI tools as debaters (Claude, Gemini, Codex, Kiro, etc.)</li>
+              <li>Final verdict from the orchestrator</li>
+            </ul>
+            <div class="code-block">
+              <button class="code-block__copy" aria-label="Copy code to clipboard" data-code="/debate codex vs gemini about microservices vs monolith
+/debate claude vs kiro about our auth implementation">
+                <svg width="16" height="16" viewBox="0 0 16 16" fill="currentColor" aria-hidden="true"><path d="M0 6.75C0 5.784.784 5 1.75 5h1.5a.75.75 0 010 1.5h-1.5a.25.25 0 00-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 00.25-.25v-1.5a.75.75 0 011.5 0v1.5A1.75 1.75 0 019.25 16h-7.5A1.75 1.75 0 010 14.25v-7.5z"/><path d="M5 1.75C5 .784 5.784 0 6.75 0h7.5C15.216 0 16 .784 16 1.75v7.5A1.75 1.75 0 0114.25 11h-7.5A1.75 1.75 0 015 9.25v-7.5zm1.75-.25a.25.25 0 00-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 00.25-.25v-7.5a.25.25 0 00-.25-.25h-7.5z"/></svg>
+              </button>
+              <pre><code><span class="code-prompt">$</span> /debate codex vs gemini about microservices vs monolith  <span class="code-comment"># Structured debate</span>
+<span class="code-prompt">$</span> /debate claude vs kiro about our auth implementation     <span class="code-comment"># Codebase debate</span></code></pre>
+            </div>
+          </div>
+
+          <div class="tabs__panel" role="tabpanel" id="tab-panel-13" aria-labelledby="tab-13" hidden>
+            <h3 class="tabs__panel-name">/web-ctl</h3>
+            <p class="tabs__panel-tagline">Browser automation for AI agents</p>
+            <ul class="tabs__panel-features">
+              <li>Headless Playwright with encrypted session persistence</li>
+              <li>Human-in-the-loop auth handoff with CAPTCHA detection</li>
+              <li>Anti-bot measures and output sanitization</li>
+              <li>Snapshot-based accessibility tree for element discovery</li>
+            </ul>
+            <div class="code-block">
+              <button class="code-block__copy" aria-label="Copy code to clipboard" data-code="/web-ctl goto https://example.com
+/web-ctl auth github --url https://github.com/login">
+                <svg width="16" height="16" viewBox="0 0 16 16" fill="currentColor" aria-hidden="true"><path d="M0 6.75C0 5.784.784 5 1.75 5h1.5a.75.75 0 010 1.5h-1.5a.25.25 0 00-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 00.25-.25v-1.5a.75.75 0 011.5 0v1.5A1.75 1.75 0 019.25 16h-7.5A1.75 1.75 0 010 14.25v-7.5z"/><path d="M5 1.75C5 .784 5.784 0 6.75 0h7.5C15.216 0 16 .784 16 1.75v7.5A1.75 1.75 0 0114.25 11h-7.5A1.75 1.75 0 015 9.25v-7.5zm1.75-.25a.25.25 0 00-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 00.25-.25v-7.5a.25.25 0 00-.25-.25h-7.5z"/></svg>
+              </button>
+              <pre><code><span class="code-prompt">$</span> /web-ctl goto https://example.com                       <span class="code-comment"># Navigate</span>
+<span class="code-prompt">$</span> /web-ctl auth github --url https://github.com/login    <span class="code-comment"># Auth handoff</span></code></pre>
+            </div>
+          </div>
         </div>
       </div>
     </section>
 
+    <!-- ===== SCROLL CUE ===== -->
+    <div class="scroll-cue anim-fade-up" data-delay="300">
+      <a href="#how-it-works" class="scroll-cue__link" aria-label="Scroll to How It Works">
+        <span class="scroll-cue__text">How It Works</span>
+        <svg class="scroll-cue__arrow" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M12 5v14"/><path d="m19 12-7 7-7-7"/></svg>
+      </a>
+    </div>
+
     <!-- ===== HOW IT WORKS ===== -->
     <section class="how-it-works" id="how-it-works" aria-labelledby="hiw-title">
       <div class="how-it-works__inner">
@@ -497,8 +565,8 @@
         <!-- Agent tier tabs -->
         <div class="agents-skills__tabs anim-fade-up" data-delay="200">
           <div class="agent-tabs" role="tablist" aria-label="Agent tiers">
-            <button class="agent-tabs__tab agent-tabs__tab--active" role="tab" aria-selected="true" aria-controls="agent-tier-opus" id="agent-tab-opus" data-index="0">Opus <span class="agent-tabs__count">13</span></button>
-            <button class="agent-tabs__tab" role="tab" aria-selected="false" aria-controls="agent-tier-sonnet" id="agent-tab-sonnet" tabindex="-1" data-index="1">Sonnet <span class="agent-tabs__count">13</span></button>
+            <button class="agent-tabs__tab agent-tabs__tab--active" role="tab" aria-selected="true" aria-controls="agent-tier-opus" id="agent-tab-opus" data-index="0">Opus <span class="agent-tabs__count">14</span></button>
+            <button class="agent-tabs__tab" role="tab" aria-selected="false" aria-controls="agent-tier-sonnet" id="agent-tab-sonnet" tabindex="-1" data-index="1">Sonnet <span class="agent-tabs__count">15</span></button>
             <button class="agent-tabs__tab" role="tab" aria-selected="false" aria-controls="agent-tier-haiku" id="agent-tab-haiku" tabindex="-1" data-index="2">Haiku <span class="agent-tabs__count">4</span></button>
             <button class="agent-tabs__tab" role="tab" aria-selected="false" aria-controls="agent-tier-specialists" id="agent-tab-specialists" tabindex="-1" data-index="3">Specialists <span class="agent-tabs__count">10</span></button>
           </div>
@@ -519,6 +587,7 @@
               <div class="agent-card"><span class="agent-card__name">hooks-enhancer</span><span class="tier-badge tier-badge--opus">opus</span><p class="agent-card__desc">Git hooks and automation analysis</p></div>
               <div class="agent-card"><span class="agent-card__name">prompt-enhancer</span><span class="tier-badge tier-badge--opus">opus</span><p class="agent-card__desc">Prompt engineering best practices</p></div>
               <div class="agent-card"><span class="agent-card__name">skills-enhancer</span><span class="tier-badge tier-badge--opus">opus</span><p class="agent-card__desc">Skill definition quality analysis</p></div>
+              <div class="agent-card"><span class="agent-card__name">debate-orchestrator</span><span class="tier-badge tier-badge--opus">opus</span><p class="agent-card__desc">Structured adversarial debate coordination</p></div>
             </div>
           </div>
 
@@ -538,6 +607,8 @@
               <div class="agent-card"><span class="agent-card__name">perf-theory-tester</span><span class="tier-badge tier-badge--sonnet">sonnet</span><p class="agent-card__desc">Controlled experiment execution</p></div>
               <div class="agent-card"><span class="agent-card__name">sync-docs-agent</span><span class="tier-badge tier-badge--sonnet">sonnet</span><p class="agent-card__desc">Documentation sync and update</p></div>
               <div class="agent-card"><span class="agent-card__name">agnix-agent</span><span class="tier-badge tier-badge--sonnet">sonnet</span><p class="agent-card__desc">Agent config linting orchestration</p></div>
+              <div class="agent-card"><span class="agent-card__name">consult-agent</span><span class="tier-badge tier-badge--sonnet">sonnet</span><p class="agent-card__desc">Cross-tool AI consultation orchestration</p></div>
+              <div class="agent-card"><span class="agent-card__name">web-session</span><span class="tier-badge tier-badge--sonnet">sonnet</span><p class="agent-card__desc">Browser automation and session management</p></div>
             </div>
           </div>
 
@@ -614,6 +685,10 @@
               <span class="skill-card">sync-docs</span>
               <span class="skill-card">learn-topic</span>
               <span class="skill-card">agnix-lint</span>
+              <span class="skill-card">consult</span>
+              <span class="skill-card">debate</span>
+              <span class="skill-card">web-auth</span>
+              <span class="skill-card">web-browse</span>
             </div>
           </div>
         </div>

package/site/ux-spec.md

@@ -94,7 +94,7 @@ Scroll order with rationale for each section. All sections are full-width, alter
 - **Single column on mobile:** Text above, terminal below. Stack with 48px gap.
 
 ### Left Column Content
-1. **Badge** (top, above title): Small pill showing version or "14 plugins . 43 agents . 30 skills"
+1. **Badge** (top, above title): Small pill showing version or "15 plugins . 35 agents . 32 skills"
    - Background: `rgba(99, 102, 241, 0.12)`, border: `1px solid rgba(99, 102, 241, 0.25)`, border-radius: 9999px
    - Font: 13px, font-weight 500, primary accent color
    - Padding: 4px 14px
@@ -104,7 +104,7 @@ Scroll order with rationale for each section. All sections are full-width, alter
    - Color: white
    - "entire dev workflow" portion highlighted with a subtle gradient text (primary-to-secondary accent via `background-clip: text`)
 
-3. **Subtitle:** "14 plugins, 43 agents, 30 skills. From task selection to merged PR. Works with Claude Code, OpenCode, Codex CLI, Cursor, and Kiro."
+3. **Subtitle:** "15 plugins, 35 agents, 32 skills. From task selection to merged PR. Works with Claude Code, OpenCode, Codex CLI, Cursor, and Kiro."
    - Font: 18px on desktop, 16px on mobile, font-weight 400, line-height 1.6
    - Color: `rgba(255, 255, 255, 0.6)`
    - Max-width: 520px
@@ -650,13 +650,13 @@ This disables:
 ### Head Content
 ```html
 <title>AgentSys - Agent Runtime &amp; Orchestration System</title>
-<meta name="description" content="A modular runtime and orchestration system for AI agents. 14 plugins, 43 agents, 30 skills — structured pipelines for Claude Code, OpenCode, Codex CLI, Cursor, and Kiro.">
+<meta name="description" content="A modular runtime and orchestration system for AI agents. 15 plugins, 35 agents, 32 skills — structured pipelines for Claude Code, OpenCode, Codex CLI, Cursor, and Kiro.">
 <meta name="viewport" content="width=device-width, initial-scale=1">
 <meta name="theme-color" content="#0a0a0f">
 
 <!-- Open Graph -->
 <meta property="og:title" content="AgentSys">
-<meta property="og:description" content="AI workflow automation. 14 plugins, 43 agents, 30 skills. Task to merged PR.">
+<meta property="og:description" content="AI workflow automation. 15 plugins, 35 agents, 32 skills. Task to merged PR.">
 <meta property="og:image" content="https://agent-sh.github.io/agentsys/assets/og-image.png">
 <meta property="og:url" content="https://agent-sh.github.io/agentsys/">
 <meta property="og:type" content="website">
@@ -664,7 +664,7 @@ This disables:
 <!-- Twitter Card -->
 <meta name="twitter:card" content="summary_large_image">
 <meta name="twitter:title" content="AgentSys">
-<meta name="twitter:description" content="AI workflow automation. 14 plugins, 43 agents, 30 skills.">
+<meta name="twitter:description" content="AI workflow automation. 15 plugins, 35 agents, 32 skills.">
 <meta name="twitter:image" content="https://agent-sh.github.io/agentsys/assets/og-image.png">
 ```