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 juspay/xyne-spaces --skill dashboard-datagit clone --depth 1 https://github.com/juspay/xyne-spacesWrote 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/juspay/xyne-spaces/dashboard-data)<a href="https://agentmods.dev/skills/juspay/xyne-spaces/dashboard-data"><img src="https://agentmods.dev/badge/skills/juspay/xyne-spaces/dashboard-data.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.00425 |
| Opus 5 | $0.00022 | $0.00212 |
| Sonnet 5 | $0.00009 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
dashboard-data 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.
What it actually says
Dashboard data
Follow this order; data retrieval is a hard gate before visual composition.
- Identify the requested measures, dimensions, time window, timezone, and comparison period.
- Inspect available read-only data tools. Query the authoritative source and retain the exact query/window needed to explain the snapshot.
- If no suitable tool or supplied dataset is available, stop. Name the missing connection. Never invent placeholder values, convert guesses into metrics, or deliver a sample dashboard.
- Check basic integrity: units, aggregation level, missing intervals, duplicate series, timezone, and whether counters require rate/increase rather than raw values.
- Build a self-contained HTML snapshot with no runtime fetches, tokens, cookies, internal URLs, or embedded credentials.
- Show
Data as of <timestamp with timezone>, the reporting window, and a human-readable source label. Do not expose secret query parameters. - Use stable card order, chart domains, colors, labels, and DOM structure across refreshes. A scheduled refresh should change the data, not randomly redesign the dashboard.
- Present unavailable metrics as unavailable; do not coerce missing data to zero.
- QA desktop and mobile layouts, chart legibility, empty/error states, console output, and network requests before delivery.
If the user explicitly asks for a recurring refresh, schedule the same complete /dashboard brief only after the first verified snapshot succeeds. Preserve the original conversation target. Never schedule implicitly, and never let a scheduled dashboard schedule another run.
Prefer KPI cards only for decision-driving headline values. Use lines for trends, bars for comparisons, tables for exact lookup, and annotations for threshold crossings. Include a concise textual takeaway adjacent to each complex chart.
Treat the artifact as a verified snapshot. The delivered HTML must remain useful offline and must never contact the underlying data source when opened or shared.
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 · 25 lines · 44 tokens per session scan A 91ec83cfee3a
dashboard-data is a skill published in the GitHub repository juspay/xyne-spaces (143 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 425 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 2026-08-30.
Other skills, from other repositories
unicli-repair
Evidence-driven repair workflow for a broken Uni-CLI adapter. Trigger on a failed unicli envelope, a quarantined adapter, or an explicit adapter-repair request. Classifies non-source failures, edits only the reported adapter path, and uses the original command as a bounded oracle.
autonomous-run
Prepare, start, inspect, resume, or stop a finite local overnight coding run after a human has accepted a Wayfinder terminal spec; coordinates a declared Claude/Codex maker and independent checker without pushing, merging, or writing to external systems.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.
i18n-localization
Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.
electron-desktop
Desktop application development with Electron for Windows, macOS, and Linux. Use when building cross-platform desktop apps, implementing native OS features, or packaging web apps for desktop.