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 costory-io/costory-finops-mcp-skills --skill dashboardsgit clone --depth 1 https://github.com/costory-io/costory-finops-mcp-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/costory-io/costory-finops-mcp-skills/dashboards)<a href="https://agentmods.dev/skills/costory-io/costory-finops-mcp-skills/dashboards"><img src="https://agentmods.dev/badge/skills/costory-io/costory-finops-mcp-skills/dashboards/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/costory-io/costory-finops-mcp-skills/dashboards"><img src="https://agentmods.dev/badge/skills/costory-io/costory-finops-mcp-skills/dashboards.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00092 | $0.06888 |
| Opus 5 | $0.00046 | $0.03444 |
| Sonnet 5 | $0.00018 | $0.01378 |
| Haiku 4.5 | $0.00009 | $0.00689 |
Grade A, and why
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 12d 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 — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dashboards
A DashboardV2 has a shared dashboardContext input (global theme) and widgets that inherit it by default. Each widget is either a chart (Advanced Explorer queries + chartType) or a text block (type: "text", textContent).
Context-first rule: define the full dashboardContext before listing widgets. Widgets should contain only overrides — never duplicate what already lives in dashboardContext. If two or more widgets share the same period, groupBy, metric, currency, or filter scope, extract that shared value to dashboardContext first.
Temporary compatibility: the deprecated top-level
contextalias is accepted during migration, but always generatedashboardContext. Never send both.
When to Trigger
- Creating a new Costory dashboard
- Generating an interesting overview when the user has not specified every widget (use How to generate interesting dashboards below)
- Adding, replacing, or removing widgets on an existing dashboard
- Editing
dashboardContext(global filter, period, groupBy, metric, currency) without recreating - Copying a widget to another dashboard
- User asks for a cost overview "by service / by region" style dashboard
Dashboard dashboardContext fields
| Field | Role | Widget inheritance |
|---|---|---|
metricId |
Default cost column (e.g. "cost") |
Cost widgets omit metricId to inherit |
currency |
USD, EUR, GBP, CNY | Cost widgets omit currency to inherit |
groupBy |
Default split dimension — use when most widgets share the same axis | Cost widgets omit groupBy to inherit (or set null explicitly for totals) |
datePreset or startDate/endDate |
Dashboard period — required when chart widgets are present (text-only dashboards may omit). Prefer datePreset whenever an available preset matches the requested range |
Widgets omit from/to/datePreset to inherit |
conditionsCel |
Dashboard-wide CEL filter (scope) | AND-merged into every cost widget by default |
scopeId |
Optional saved scope | Inherited like other context fields |
What ships with it
1 file 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.
- 12d ago First seen · 479 lines · 92 tokens per session scan A 1a5dd718545a
dashboards is a skill published in the GitHub repository costory-io/costory-finops-mcp-skills (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 92 tokens to every session and 6,888 once invoked, about $0.0005 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
querying-well-data
How to query a Well workspace correctly — discover the schema first, then query the right root. Use whenever the user asks about their invoices, companies, contacts, bank transactions, accounts, or accounting ledger in Well, or before writing any wellqueryrecords call.
ar-aging
Produce an accounts-receivable aging report and surface overdue invoices for a Well workspace. Use when the user asks who owes them money, an AR aging report, overdue invoices, days sales outstanding (DSO), or which customers to chase.
balance-sheet
Build a balance sheet (bilan) from a Well workspace. Use when the user asks for a balance sheet, bilan, assets/liabilities/equity, or financial position at a point in time.
cash-flow-forecast
Forecast cash flow and runway for a Well workspace from booked invoices and collected bank transactions. Use when the user asks for a cash-flow forecast, runway, how long until they run out of cash, projected balance, or expected inflows/outflows.
compte-de-resultat
Build a profit & loss statement (compte de résultat / income statement) from a Well workspace. Use when the user asks for a P&L, income statement, compte de résultat, revenue vs expenses, or net result over a period.
month-end-close
Run a month-end (or period) close checklist against a Well workspace — verify everything is reconciled and posted before the books are closed. Use when the user asks to close the month/period, run a close checklist, check if the books are ready to close, or what's left before closing.