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 accuknox/agentZ --skill dashboard-creatorgit clone --depth 1 https://github.com/accuknox/agentZWrote 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/accuknox/agentz/dashboard-creator)<a href="https://agentmods.dev/skills/accuknox/agentz/dashboard-creator"><img src="https://agentmods.dev/badge/skills/accuknox/agentz/dashboard-creator/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/accuknox/agentz/dashboard-creator"><img src="https://agentmods.dev/badge/skills/accuknox/agentz/dashboard-creator.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 | $0.00022 | $0.00938 |
| Opus 5.5 | $0.00009 | $0.00375 |
| Sonnet 5.5 | $0.00004 | $0.00188 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
dashboard-creator 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dashboard Creator
Build the dashboard from values you have already computed. The gateway validates, stores, limits, and queries data; it is not a transformation engine.
Sequence
- Call
list_dashboardsbefore choosing a name. - Finalize every widget definition before calling
create_dashboard. Definitions are immutable. - Call
get_dashboardimmediately before publishing and use the returneddata_revisionfor each widget. - Call
publish_dashboard_dataonce per widget update, with at most 100 records. - If a definition is wrong or a widget reports invalid stored data, delete the dashboard, recreate it, and publish corrected data.
Widget contracts
line,area,step: temporal only; 1–5 series. Each record contains onlyrecorded_atandvalues, with one number per series.pie: latest only; exactly one series. Each record contains onlycategoryand onevaluesentry.bar,horizontal_grouped_bar: temporal or latest; 1–5 series. Each record containscategoryand one value per series.funnel,horizontal_funnel: latest only; exactly one series. Publish uniquely named stages in display order with non-increasing values. Each record containscategoryand one non-negative value.sankey: latest only; exactly one series. Each record containssource,target, and a positivevalue. Source/target pairs must be unique, and all links together must form an acyclic graph.scatter: temporal or latest; 1–5 declared series andaxesmetadata forxandy. Each axis has a displaylabeland optionalunit. Each record containsseries,x,y, and an optionallabel.gauge: latest only; exactly one series, an increasingminimum/maximum, and up to five increasing thresholds. Publish exactly one record containing one value.table: temporal or latest; 1–12 columns and no series. Each record containscells, one cell per declared column. A cell must contain exactly one matching key:text,number,boolean, ordatetime.
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 Changed 3c230ea754eb
- 1mo ago First seen · 57 lines · 22 tokens per session scan A fefdf47f4c29
dashboard-creator is a skill published in the GitHub repository accuknox/agentZ (54 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 938 once invoked, about $0.0001 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
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
fixing-github-security-alerts
Remediate GitHub security / Dependabot / CodeQL / code-quality alerts via fixgithubsecurityalert.
querying-yandex-cloud
Read Yandex Cloud through its REST API. Applies to any question about VMs, metrics, logs, audit events, Kubernetes, managed databases, serverless, networking or any other Yandex Cloud resource. Never shell out to the yc CLI — it is not how this agent reaches Yandex Cloud and is usually not installed.
onboarding-github-ci
Present the available onboarding workflows and follow the selected skill. Use at interactive startup, for /demo, or when a user asks about OpenSRE capabilities. Direct workflow requests should load the matching specialist.
operating-github-ci-fixer
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.
operating-github-cli
Default GitHub skill for the action agent. Use githubcli for any GitHub request — create/list/view/close issues and PRs, assign, labels, repos, releases, checks, github.com/owner/repo URLs, or gh api. Prefer over shellrun/!gh. Run these with githubcli in the current agent turn.