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.
npx agentmods add commands/abilityai/trinity/update-dashboardgit clone --depth 1 https://github.com/Abilityai/trinityWhat 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.
| Model | Per session | Once 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 |
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" \ 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
-
Gather fleet data using
mcp__trinity__list_agents:- Total agent count
- Running vs stopped counts
- Count by health status (healthy/warning/critical)
-
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
- Get schedule stats via API:
curl -s "http://backend:8000/api/ops/schedules" \
-H "Authorization: Bearer $TRINITY_MCP_API_KEY"
- Total schedules
- Enabled vs disabled
- Next scheduled run
-
Determine overall health:
healthy(green): All agents healthy, success rate >90%degraded(yellow): Some warnings, or success rate 70-90%critical(red): Any critical issues, or success rate <70%
-
Write dashboard.yaml to
/home/developer/dashboard.yaml:
title: "Trinity Platform Status"
description: "Real-time platform health and metrics"
refresh: 60
sections:
- title: "Platform Health"
layout: grid
columns: 4
widgets:
- type: status
label: "Platform Status"
value: "{healthy|degraded|critical}"
color: "{green|yellow|red}"
colspan: 1
- type: metric
label: "Agents"
value: {total_agents}
description: "{running} running, {stopped} stopped"
- type: metric
label: "Healthy"
value: {healthy_count}
trend: {up if improved, down if worse, omit if same}
- type: metric
label: "Issues"
value: {warning_count + critical_count}
trend: {down if improved, up if worse}
- title: "Executions (24h)"
layout: grid
columns: 4
widgets:
- type: metric
label: "Tasks"
value: {execution_count}
description: "Last 24 hours"
- type: progress
label: "Success Rate"
value: {success_rate}
color: "{green if >90, yellow if >70, red otherwise}"
- type: metric
label: "Cost"
value: "${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
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.
- 2d ago First seen · 164 lines · 0 tokens per session scan A a0d535dec2bc
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.