docs(skill): add web dashboard and configurable agent limits

.claude/skills/conductor/SKILL.md

@@ -14,6 +14,8 @@ conductor run workflow.yaml --input question="Hello"     # Execute (full output
 conductor run workflow.yaml -q --input question="Hello"  # Quiet: lifecycle + routing only
 conductor run workflow.yaml -s --input question="Hello"  # Silent: JSON result only
 conductor run workflow.yaml --log-file auto               # Log full debug output to file
+conductor run workflow.yaml --web --input q="Hello"       # Real-time web dashboard
+conductor run workflow.yaml --web-bg --input q="Hello"    # Background mode (prints URL, exits)
 conductor validate workflow.yaml                         # Validate only
 conductor init my-workflow --template simple              # Create from template
 conductor templates                                      # List templates
@@ -96,7 +98,8 @@ output:
 | `limits` | Safety bounds (max_iterations up to 500, timeout_seconds) |
 | `cost` | Token usage and cost tracking configuration |
 | `runtime` | Provider, model, temperature, max_tokens, MCP servers |
-| checkpoint | Auto-saved on failure; resume with `conductor resume` |
+| `--web` | Real-time web dashboard with DAG graph, live streaming, in-browser human gates |
+| `checkpoint` | Auto-saved on failure; resume with `conductor resume` |
 
 ## Common Patterns
 

.claude/skills/conductor/references/authoring.md

@@ -17,6 +17,8 @@ workflow:
     temperature: 0.7             # 0.0-1.0 (optional)
     max_tokens: 4096             # Max output tokens per response (optional)
     timeout: 600                 # Per-request timeout in seconds (optional)
+    max_agent_iterations: 50     # Max tool-use roundtrips per agent (1-500, optional)
+    max_session_seconds: 120     # Wall-clock timeout per agent session (optional)
 
   input:                         # Define workflow inputs
     param_name:
@@ -71,6 +73,9 @@ agents:
     tools:                       # null = all, [] = none, [list] = subset
       - web_search
 
+    max_agent_iterations: 100    # Override workflow default for this agent (optional)
+    max_session_seconds: 60      # Wall-clock timeout for this agent (optional)
+
     routes:                      # Where to go next
       - to: next_agent
 ```

.claude/skills/conductor/references/execution.md

@@ -314,7 +314,22 @@ Preview execution plan without running agents. Shows the workflow graph, agent o
 conductor run workflow.yaml --web --input question="test"
 ```
 
-Visualize execution in real-time with a browser dashboard. Shows agent prompts, reasoning, tool calls, and outputs as they stream in.
+Real-time browser dashboard for visualizing and interacting with workflows as they run:
+
+- **Interactive DAG graph** — Zoomable, draggable workflow graph with animated edges showing execution flow and conditional routing
+- **Live agent streaming** — Watch agent reasoning, tool calls, and outputs stream in real-time as each step executes
+- **Three-pane layout** — Resizable panels for the graph, agent detail, and a tabbed output pane (Log, Activity, Output)
+- **In-browser human gates** — Respond to human-in-the-loop decisions directly in the dashboard
+- **Per-node detail** — Click any node to see its prompt, metadata (model, tokens, cost), activity stream, and output
+- **Background mode** — Run with `--web-bg` to start in background, print URL, and exit
+
+```bash
+# Background mode: prints dashboard URL and exits
+conductor run workflow.yaml --web-bg --input question="test"
+
+# Stop background workflow
+conductor stop
+```
 
 ### Validate First
 

.claude/skills/conductor/references/yaml-schema.md

@@ -32,6 +32,8 @@ workflow:
     temperature: float              # 0.0-1.0, controls randomness (optional)
     max_tokens: integer             # Max OUTPUT tokens per response, 1-200000 (optional)
     timeout: float                  # Per-request timeout in seconds (optional, default: 600)
+    max_agent_iterations: integer   # Max tool-use roundtrips per agent (1-500, optional)
+    max_session_seconds: float      # Wall-clock timeout per agent session in seconds (optional)
     mcp_servers:                    # MCP server configurations
       <server_name>:
         type: string                # "stdio" (default), "http", or "sse"
@@ -124,6 +126,10 @@ agents:
     tools:                          # null = all workflow tools, [] = none, [list] = subset
       - string
 
+    # Agent-level limits (override workflow runtime defaults)
+    max_agent_iterations: integer   # Max tool-use roundtrips for this agent (1-500, optional)
+    max_session_seconds: float      # Wall-clock timeout for this agent session (optional)
+
     # Script-only fields (type: script)
     command: string                 # Command to execute (Jinja2 templated)
     args: [string]                  # Command arguments (each Jinja2 templated)