dashboard

A command that shows the current status of a Plan Cascade task, a system for organizing and running multi-step work.

In plain words
What is it for?
Use it to view execution status, optionally with more detail or machine-readable JSON.
Why use it?
It makes the task’s progress and saved planning state easier to inspect.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/taoidle/plan-cascade/dashboard
Clone the repo
git clone --depth 1 https://github.com/Taoidle/plan-cascade
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 940 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.00940
Opus 5 $0.00012 $0.00470
Sonnet 5 $0.00005 $0.00188
Haiku 4.5 $0.00002 $0.00094

Measured 2d ago against content hash c7b27478711e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dashboard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/dashboard.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Cascade Dashboard

Display execution status for the current Plan Cascade task.

Step 1: Parse Arguments

VERBOSE="False"
JSON_OUTPUT="False"

for arg in $ARGUMENTS; do
    case "$arg" in
        --verbose|-v) VERBOSE="True" ;;
        --json) JSON_OUTPUT="True" ;;
    esac
done

Step 2: Detect State Files

CRITICAL: Use the Read tool to check for state files first.

Check for existence of:

  • mega-plan.json - indicates MEGA mode
  • prd.json - indicates HYBRID mode
  • progress.txt - execution tracking
  • .iteration-state.json - iteration state

Step 3: Run Dashboard Aggregator

uv run python << 'PYTHON_EOF'
import sys
import json
from pathlib import Path

# Setup import path for plan_cascade module
plugin_root = Path(r"${CLAUDE_PLUGIN_ROOT}") if "${CLAUDE_PLUGIN_ROOT}" else None
if plugin_root and (plugin_root / "src").exists():
    sys.path.insert(0, str(plugin_root / "src"))
else:
    # Try current directory parent (for development)
    if (Path.cwd().parent / "src").exists():
        sys.path.insert(0, str(Path.cwd().parent / "src"))

project_root = Path.cwd()
verbose = ${VERBOSE}
json_output = ${JSON_OUTPUT}

try:
    # Use the dashboard module's public API
    from plan_cascade.core.dashboard import get_dashboard, format_dashboard

    # Get aggregated dashboard state
    state = get_dashboard(
        project_root=project_root,
        legacy_mode=True,  # Use legacy mode for compatibility
    )

    if json_output:
        # JSON output using state.to_dict()
        print(json.dumps(state.to_dict(), indent=2, default=str))
    else:
        # Formatted output using the dashboard formatter
        print(format_dashboard(state, verbose=verbose))

except ImportError as e:
    # Fallback if dashboard module not available
    print(f"Dashboard module not available: {e}")
    print("")
    print("=" * 60)
    print("PLAN CASCADE DASHBOARD")
    print("=" * 60)
    print("")

    # Simple fallback detection
    has_mega = (project_root / "mega-plan.json").exists()
    has_prd = (project_root / "prd.json").exists()

    if has_mega:
        print("Strategy: MEGA (Multi-Feature)")
        print("Status: Run /plan-cascade:mega-status for details")
    elif has_prd:
        print("Strategy: HYBRID (Single Feature)")
        print("Status: Run /plan-cascade:hybrid-status for details")
    else:
        print("Status: NO ACTIVE EXECUTION")
        print("")
        print("Start a new task with:")
        print("  /plan-cascade:hybrid-auto <description>")
        print("  /plan-cascade:mega-plan <description>")

    print("=" * 60)

except Exception as e:
    print(f"Dashboard error: {e}")
    import traceback
    traceback.print_exc()
    print("")
    print("No active execution found. Start with:")
    print("  /plan-cascade:hybrid-auto <description>")
    print("  /plan-cascade:mega-plan <description>")
PYTHON_EOF

Read the full file on GitHub · 138 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 138 lines · 23 tokens per session scan A c7b27478711e

Subscribe to this mod's changes

dashboard is a command published in the GitHub repository Taoidle/plan-cascade (131 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 940 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.