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 skills add erphq/skills --skill reports-dashboardsgit clone --depth 1 https://github.com/erphq/skillsWrote 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/skills/erphq/skills/reports-dashboards)<a href="https://agentmods.dev/skills/erphq/skills/reports-dashboards"><img src="https://agentmods.dev/badge/skills/erphq/skills/reports-dashboards.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 5.1 | $0.00039 | $0.08321 |
| Opus 5 | $0.00019 | $0.04161 |
| Sonnet 5 | $0.00008 | $0.01664 |
| Haiku 4.5 | $0.00004 | $0.00832 |
Grade A, and why
reports-dashboards 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reports & Dashboards
Size-Tier Scope
This variant scales the operating pattern for organizations under 100 people. Keep the controls lightweight, favor owner-led approvals, and introduce automation only where it removes recurring manual work without adding governance overhead.
Purpose
Enterprise applications are only as valuable as the decisions they enable. Reports and dashboards translate raw transactional data into actionable insight. This skill covers the full lifecycle: identifying the right metrics, choosing report types, designing dashboard layouts, managing data pipelines for reporting, securing data visibility by role, and distributing outputs on schedule.
Use this skill when a builder needs to:
- Define KPIs and metrics for a business process
- Build operational or analytical reports inside ERP•AI
- Design interactive dashboards with drill-down capabilities
- Configure scheduled report distribution
- Implement role-based data filtering on report outputs
- Decide between live queries, materialized views, or data warehouse feeds
Key Concepts
KPI Design
- Leading indicator: A metric that predicts future performance. Example: number of open quotes predicts future revenue. Leading indicators are harder to measure but easier to influence.
- Lagging indicator: A metric that confirms past performance. Example: quarterly revenue. Lagging indicators are easy to measure but impossible to change retroactively.
- KPI hierarchy: Executive KPIs decompose into departmental KPIs, which decompose into operational metrics. A revenue target (executive) breaks into pipeline conversion rate (sales management) which breaks into calls per day (individual contributor).
- SMART criteria for KPIs: Specific (tied to one process), Measurable (numeric or boolean), Achievable (within the team's control), Relevant (connected to a business outcome), Time-bound (measured over a defined period).
- Vanity metric: A number that looks impressive but does not drive decisions. Example: total registered users (vs. monthly active users). Avoid building reports around vanity metrics.
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.
- 8d ago First seen · 486 lines · 39 tokens per session scan A 14cef8d5c98d
reports-dashboards is a skill published in the GitHub repository erphq/skills (2 stars, last pushed 18d ago), licensed MIT. It adds 39 tokens to every session and 8,321 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 skills, from other repositories
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why.
review
Adversarial fresh-context review of an increment before it ships. Every finding cites path:line and is re-verified. Use when saying "review", "grill this", or "critique the implementation".
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".
pre-modification-check
Use before modifying, refactoring, moving, or deleting files in a Repowise-indexed repository, especially shared utilities, core modules, public APIs, or files the user did not explicitly identify.
plan
Research the codebase and create an implementation plan following Propose/Justify/Recommend. Use this before any feature, fix, or refactor.