god-dashboard-builder

god-dashboard-builder is an agent for coding agents from hannsxpeter/godpowers. It costs 48 tokens per session (439 once invoked), scanned A, original, MIT.

An agent that designs dashboards around decisions. A dashboard is a screen of charts and metrics used to monitor a system or business.

In plain words
What is it for?
Use it to plan dashboard audiences, chart questions, targets, deploy annotations, update frequency, and stale-data warnings. It writes a dashboard specification file.
Why use it?
It helps avoid dashboards filled with numbers that nobody uses by requiring each chart to answer a question and support an action.

Agent

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 agents/hannsxpeter/godpowers/god-dashboard-builder
Clone the repo
git clone --depth 1 https://github.com/hannsxpeter/godpowers

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for god-dashboard-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/hannsxpeter/godpowers/god-dashboard-builder.svg)](https://agentmods.dev/agents/hannsxpeter/godpowers/god-dashboard-builder)
Your own site
<a href="https://agentmods.dev/agents/hannsxpeter/godpowers/god-dashboard-builder"><img src="https://agentmods.dev/badge/agents/hannsxpeter/godpowers/god-dashboard-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 439 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 $0.00048 $0.00439
Opus 5 $0.00024 $0.00219
Sonnet 5 $0.00010 $0.00088
Haiku 4.5 $0.00005 $0.00044

Measured 4d ago against content hash ba8a4d233980, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

god-dashboard-builder 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 4d 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.

extensions/data-pack/agents/god-dashboard-builder.md · 67 lines

What it actually says

God Dashboard Builder

Build dashboards people actually use.

Process

1. Audience

  • Who looks at this dashboard?
  • How often?
  • What action will they take based on what they see?

If the answer is "no specific action", the dashboard is vanity. Don't build it.

2. Question per chart

Every chart answers ONE question:

  • "Are we hitting the SLO?" -> error rate over time
  • "Where are users dropping off?" -> funnel chart
  • "Is revenue growing?" -> MRR over time

If a chart doesn't answer a question, delete it.

3. Annotation

  • Every chart has a title that states the question
  • Every chart has a target line or threshold (where applicable)
  • Deploys annotated on the chart (so you can see deploy-related changes)

4. Refresh and freshness

  • Documented update frequency
  • Stale data indicator (if data is older than expected, show it)

Output

Write .godpowers/data/dashboards/<dashboard-name>/SPEC.mdx.

Have-Nots

DASH-01 Vanity metric

Chart shows a metric with no associated action. Fail.

DASH-02 No question per chart

Chart title is just a metric name, not a question. Fail.

DASH-03 No threshold

Chart shows a metric with a target but no visible threshold line. Fail.

DASH-04 No deploy annotations

Production dashboards without deploy markers. Hard to correlate changes with code. Fail.

DASH-05 No staleness indicator

Stale data displayed as fresh. Misleading. Fail.

DASH-06 Dashboard sprawl

More than 7 charts on one dashboard. Cognitive overload. Fail.

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. 4d ago First seen · 67 lines · 48 tokens per session scan A ba8a4d233980

Subscribe to this mod's changes

god-dashboard-builder is an agent published in the GitHub repository hannsxpeter/godpowers (5 stars, last pushed 15d ago), licensed MIT. It adds 48 tokens to every session and 439 once invoked, about $0.0002 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 2026-08-31.