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 skills/nexu-io/open-design/github-dashboardnpx skills add nexu-io/open-design --skill github-dashboardgit clone --depth 1 https://github.com/nexu-io/open-designWhat 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 | $0.00055 | $0.01760 |
| Opus 5 | $0.00028 | $0.00880 |
| Sonnet 5 | $0.00011 | $0.00352 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
github-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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- github-dashboard — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Dashboard Skill
Create a single-screen GitHub repository analytics dashboard in the FlowAI / Soft Paper Workspace visual style: warm off-white canvas, white rounded panels, a fixed left sidebar, compact KPI cards, pastel pills, dense tables, and low-contrast hairlines.
Resource map
github-dashboard/
├── SKILL.md
├── example.html ← rendered reference dashboard
└── references/
├── template.html ← live-artifact-compatible HTML template
├── example-data.json ← normalized public GitHub data shape
├── artifact-example.json ← minimal live-artifact create input
└── provenance-example.json ← safe source/provenance example
When to use this skill
Use this when the user asks for a dashboard or report about a single GitHub repository, for example:
- repository growth dashboard
- open-source project health report
- GitHub stars / forks / contributors analytics
- issue and pull-request activity page
- maintainer / contributor dashboard
If the user asks for refreshability, source auditability, or scheduled updates, produce the live-artifact source set (template.html, data.json, artifact.json, provenance.json) and follow the live-artifact contract. If they only need a visual artifact, produce a self-contained index.html.
Workflow
-
Resolve repository scope
- Parse
owner/repofrom the brief. - This v1 skill is scoped to one repository. If multiple repositories are requested, ask the user to pick the primary repository or create one dashboard per repository.
- If the repo is missing, ask one concise question for the GitHub URL or
owner/repo.
- Parse
-
Collect public GitHub data
- Prefer GitHub CLI/API for public repository data when available.
- Current stars/forks/watchers/open issue count:
GET /repos/{owner}/{repo}(stargazers_count,forks_count,watchers_count,open_issues_count). - Contributors: paginate
GET /repos/{owner}/{repo}/contributors?per_page=100&page=N, sort bycontributionsdescending, and take the top N used by the dashboard. If only page 1 is available, label totals as first-page estimates. - Issues: use GitHub Search API (
repo:{owner}/{repo} is:issue) for total counts, or paginateGET /repos/{owner}/{repo}/issues?state=alland filter out items with apull_requestfield. - Pull requests: use GitHub Search API (
repo:{owner}/{repo} is:pr) for total counts, or paginateGET /repos/{owner}/{repo}/pulls?state=alland count pages via theLinkheader. - Recent activity: combine the newest issues and pull requests, normalize them into display-ready rows, and cap the preview list at 5–10 items.
- Growth/delta metrics: GitHub REST does not expose complete historical star/fork deltas. Use GraphQL, stargazer event snapshots, the Events API where available, or explicitly mark deltas as estimated/synthetic in
provenance.json. - Do not store auth tokens, raw HTTP envelopes, cookies, rate-limit headers, or private metadata.
What ships with it
6 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.
- 3d ago First seen · 131 lines · 55 tokens per session scan A f69eda62ae8a
github-dashboard is a skill published in the GitHub repository nexu-io/open-design (93,356 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 1,760 once invoked, about $0.0003 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
deck-swiss-international
16 列网格 + 单一饱和 accent + 22 个锁死版面 (Klein Blue / Lemon / Mint / Safety Orange).
competitive-teardown
定位图 + 功能矩阵 + 价格对比 + 机会窗口, 把竞品资料转成产品决策报告.
deck-guizang-editorial
电子杂志 × 电子墨水; 10 个版面 + 5 套调色板 (墨水/靛蓝瓷/森林墨/牛皮纸/沙丘).
deck-open-slide-canvas
锁死 1920×1080 画布, React 组件级自由组合, 不绑模板.
doc-kami-parchment
暖羊皮纸底 (#f5f4ed) + 墨蓝单色 accent (#1B365D) + 单一衬线字体, 编辑级排印.
exec-briefing-memo
Decision needed + recommendation + evidence + tradeoffs, 把复杂材料压成可拍板的一页.