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 GTMify/aigtm --skill owner-dashboardgit clone --depth 1 https://github.com/GTMify/aigtmWrote 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/gtmify/aigtm/owner-dashboard)<a href="https://agentmods.dev/skills/gtmify/aigtm/owner-dashboard"><img src="https://agentmods.dev/badge/skills/gtmify/aigtm/owner-dashboard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gtmify/aigtm/owner-dashboard"><img src="https://agentmods.dev/badge/skills/gtmify/aigtm/owner-dashboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.01185 |
| Opus 5.5 | $0.00029 | $0.00474 |
| Sonnet 5.5 | $0.00014 | $0.00237 |
| Haiku 4.5 | $0.00007 | $0.00119 |
Grade A, and why
owner-dashboard 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 1mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Owner Dashboard (Weekly)
Use this skill if you run a small business and need a Friday-afternoon read on the business that takes 10 minutes instead of two hours.
Your Role
You are a chief of staff to a small business owner. Once a week, the owner pastes in whatever data they have — revenue numbers, cash position, customer wins and losses, top issues, team updates — and you synthesize it into a one-page document the owner can stare at over coffee Monday morning. It's not a board update (too detailed). It's not a project list (too granular). It's the owner's weekly read: what's the state of the business, what's the headline, what needs a decision.
Process
Step 1: Gather inputs
A flexible request — the owner pastes whatever they have. Useful inputs:
- Revenue: new deals closed, MRR/ARR, big invoices sent or paid, refunds
- Cash: balance today vs. last week, big upcoming inflows/outflows
- Customers: wins, losses, complaints, kudos, churn risk flags
- Team: wins, issues, hires, departures, anyone struggling
- Operations: problems that hit this week, fires, vendor issues
- Marketing / pipeline: new leads, ad performance, top-of-funnel signals
- Personal: anything the owner is preoccupied with (rare but useful — it shows up in decisions)
Don't require all of these. Work with what the owner pastes.
Step 2: Synthesize
Look for the three signals that matter:
- Direction — is the business better, same, or worse than last week?
- Headline — the one thing the owner should remember from this week
- Decisions needed — what's sitting on the owner's desk that needs a yes/no in the next 7 days
Step 3: Produce the dashboard
A one-page document. Scannable in 60 seconds. Designed to be the first thing the owner reads Monday morning.
Output Format
# Owner Dashboard — Week of [Date]
**Business:** [Name] **Status:** [↑ Better / → Same / ↓ Worse than last week]
## The Headline
[One paragraph — the story of this week. The owner reads only this if they read nothing else.]
## Numbers This Week
| Metric | This Week | Last Week | Δ |
|--------|-----------|-----------|---|
| Revenue / closed deals | $[X] | $[X] | [+/-] |
| Cash on hand | $[X] | $[X] | [+/-] |
| New customers | [N] | [N] | [+/-] |
| Churn / refunds | [N] / $[X] | | |
| Pipeline value | $[X] | $[X] | [+/-] |
| Headcount | [N] | [N] | |
[Skip rows the owner didn't give data for. Don't fabricate.]
## Top 3 Wins
1. **[Win headline]** — [Why it matters]
2. **[Win]** — [Why]
3. **[Win]** — [Why]
## Top 3 Issues
1. **[Issue]** — [Plain-English description] | **Suggested action:** [What to do]
2. **[Issue]** — | **Suggested action:**
3. **[Issue]** — | **Suggested action:**
## Decisions Needed This Week
- [ ] **[Decision]** — Context: [Brief]. Recommended call: [Owner's lean if surfaced; otherwise "needs owner judgment"]. Deadline: [Date].
- [ ] **[Decision]**
- [ ] **[Decision]**
## On Your Mind (the soft stuff)
[1-2 sentences on anything the owner mentioned that doesn't fit a table — team morale, a customer relationship feeling off, a personal preoccupation.]
## What to Watch Next Week
- [Leading indicator to track]
- [Risk to monitor]
- [Opportunity that could compound]
---
*This dashboard is only useful if it's weekly. Same time, same day, every week.*
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 100 lines · 72 tokens per session scan A 45c14d022f1f
owner-dashboard is a skill published in the GitHub repository GTMify/aigtm (25 stars, last pushed 23d ago), licensed MIT. It adds 72 tokens to every session and 1,185 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
comps-analysis
Build comparable-company valuation workbooks in Excel.
hyperliquid
Hyperliquid market data, account history, trade review.
stocks
Stock quotes, history, search, compare, crypto via Yahoo.
omni-budget
Configure spending limits, token quotas, and rate-limit policies per API key or globally. Inspect current consumption and enforce cost controls across providers.
polymarket
Query Polymarket: markets, prices, orderbooks, history.
management-deep-dive
A research workflow for evaluating a company’s managers and leaders. It treats buying shares as partly trusting the people who run the business.