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 agents/hannsxpeter/godpowers/god-dashboard-buildergit clone --depth 1 https://github.com/hannsxpeter/godpowersWrote 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.
[](https://agentmods.dev/agents/hannsxpeter/godpowers/god-dashboard-builder)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 4d ago First seen · 67 lines · 48 tokens per session scan A ba8a4d233980
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.
Other agents, from other repositories
ap-verifier
L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase. This is a single-context repo.
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
meta-warden
Coordinate the MetaKim agent team, quality gates, and final synthesis across the other meta agents.
scout
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
devops-engineer
Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.