update-dashboard

A command that collects agent, execution, and schedule metrics and writes them to a YAML dashboard file. YAML is a human-readable format for structured settings and data.

In plain words
What is it for?
Use it to update `/home/developer/dashboard.yaml` with agent counts, success rates, costs, schedules, and health status.
Why use it?
It avoids manually checking several sources and assembling a platform-status file. It also applies stated thresholds to label overall health.

Command for Claude Code

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/abilityai/trinity/update-dashboard
Clone the repo
git clone --depth 1 https://github.com/Abilityai/trinity

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,091 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.01091
Opus 5 $0.00000 $0.00545
Sonnet 5 $0.00000 $0.00218
Haiku 4.5 $0.00000 $0.00109

Measured 2d ago against content hash a0d535dec2bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-dashboard scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "http://backend:8000/api/agents/execution-stats" \
config/agent-templates/trinity-system/.claude/commands/ops/update-dashboard.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Dashboard

Gather current platform metrics and update the dashboard.yaml file.

Instructions

  1. Gather fleet data using mcp__trinity__list_agents:

    • Total agent count
    • Running vs stopped counts
    • Count by health status (healthy/warning/critical)
  2. Get execution stats via API:

curl -s "http://backend:8000/api/agents/execution-stats" \
  -H "Authorization: Bearer $TRINITY_MCP_API_KEY"
  • Total executions (24h)
  • Success rate
  • Total cost
  1. Get schedule stats via API:
curl -s "http://backend:8000/api/ops/schedules" \
  -H "Authorization: Bearer $TRINITY_MCP_API_KEY"
  • Total schedules
  • Enabled vs disabled
  • Next scheduled run
  1. Determine overall health:

    • healthy (green): All agents healthy, success rate >90%
    • degraded (yellow): Some warnings, or success rate 70-90%
    • critical (red): Any critical issues, or success rate <70%
  2. Write dashboard.yaml to /home/developer/dashboard.yaml:

title: "Trinity Platform Status"
description: "Real-time platform health and metrics"
refresh: 60

sections:
  - title: "Platform Health"
    layout: grid
    columns: 4
    widgets:
      - type: status
        label: "Platform Status"
        value: "{healthy|degraded|critical}"
        color: "{green|yellow|red}"
        colspan: 1

      - type: metric
        label: "Agents"
        value: {total_agents}
        description: "{running} running, {stopped} stopped"

      - type: metric
        label: "Healthy"
        value: {healthy_count}
        trend: {up if improved, down if worse, omit if same}

      - type: metric
        label: "Issues"
        value: {warning_count + critical_count}
        trend: {down if improved, up if worse}

  - title: "Executions (24h)"
    layout: grid
    columns: 4
    widgets:
      - type: metric
        label: "Tasks"
        value: {execution_count}
        description: "Last 24 hours"

      - type: progress
        label: "Success Rate"
        value: {success_rate}
        color: "{green if >90, yellow if >70, red otherwise}"

      - type: metric
        label: "Cost"
        value: "${total_cost}"
        description: "Last 24 hours"

      - type: text
        content: "Last: {last_execution_time}"
        size: sm
        color: gray

  - title: "Schedules"
    layout: grid
    columns: 3
    widgets:
      - type: metric
        label: "Total"
        value: {schedule_count}
        description: "{enabled} enabled"

      - type: status
        label: "Automation"
        value: "{Active|Paused}"
        color: "{green|gray}"

      - type: text
        content: "Next: {next_run_time}"
        size: sm

  - title: "Agent Status"
    layout: list
    widgets:
      - type: table
        columns:
          - { key: agent, label: Agent }
          - { key: status, label: Status }
          - { key: health, label: Health }
          - { key: context, label: Context }
        rows:
          # One row per agent, e.g.:
          # - { agent: "research-bot", status: "running", health: "healthy", context: "45%" }
        max_rows: 10

  - title: ""
    layout: list
    widgets:
      - type: text
        content: "Updated: {ISO timestamp}"
        size: xs
        color: gray
        align: right

Read the full file on GitHub · 164 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 · 164 lines · 0 tokens per session scan A a0d535dec2bc

Subscribe to this mod's changes

update-dashboard is a command published in the GitHub repository Abilityai/trinity (496 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,091 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.