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 cirwel/unitares --skill unitares-dashboardgit clone --depth 1 https://github.com/cirwel/unitaresWrote 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/cirwel/unitares/unitares-dashboard)<a href="https://agentmods.dev/skills/cirwel/unitares/unitares-dashboard"><img src="https://agentmods.dev/badge/skills/cirwel/unitares/unitares-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/cirwel/unitares/unitares-dashboard"><img src="https://agentmods.dev/badge/skills/cirwel/unitares/unitares-dashboard.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 | $0.00086 | $0.04109 |
| Opus 5 | $0.00043 | $0.02055 |
| Sonnet 5 | $0.00017 | $0.00822 |
| Haiku 4.5 | $0.00009 | $0.00411 |
Grade A, and why
unitares-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 today.
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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a Section to the UNITARES Dashboard (redesign)
Orientation
The live dashboard is dashboard/redesign/ — buildless (raw HTML/CSS/JS,
no framework, no bundle). http_dashboard_redesign now lives in
src/http_routes/dashboard.py; src/http_api.py is the registration/re-export
facade that maps it to /, /dashboard, and /dashboard/redesign/**. The
classic dashboard and its allowlist / script-load-chain / vite build were
retired — ignore older guidance about index.html, allowed_files,
MetricColors, or Chart.defaults. The redesign resolver constrains paths and
file types and has no per-asset allowlist, but it does gate one asset:
snapshot.js is served only to an authenticated caller
(_AUTHENTICATED_ONLY_FILES), and auth/*.html is 404 on this route (those
pages are served via /auth/*). Files are read per request, so a restart is
not needed for static edits. Entry HTML is no-store; relative assets receive
an mtime version query to prevent stale browser bundles.
A "section" is one nav tab. Each is a self-contained module that renders into
its own mount and is wired in app.html.
The section-module pattern
A section is an IIFE that attaches window.<Name> = { load } (add retheme
if it draws charts; add applyEvent / notifyNew if it's a live surface — see
Live-surface hooks below). load() renders into its mount on first call and
updates in place on subsequent calls (so a refresh doesn't flicker or reset
form state). Worked references: sections/eisv.js (charts, retheme,
applyEvent) and sections/metrics.js (charts + a picker that preserves its
selection across load() — exercised by its manual ↻, since Metrics is not on
the auto-refresh tick). sections/telemetry-health.js and sections/risk.js
are the newest sections and follow the same conventions.
One exception to know about: sections/landing.js (the Overview) does not
export load. It exports { render, refresh, refreshStats, applyEvent, tickSilence }, is booted by window.Landing.render() at the end of
app.html, and RELOAD.overview calls its refresh method. Do not copy it
as the template for a new section.
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.
- today Changed 2a100c2a9610
- yesterday Changed · +71 lines 6dcf8d96223b
- 9d ago First seen · 198 lines · 86 tokens per session scan A 53980bc6dc4c
unitares-dashboard is a skill published in the GitHub repository cirwel/unitares (4 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 4,109 once invoked, about $0.0004 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
adk-agent-builder
Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between agents, human-in-the-loop pauses, and pytest coverage for all of it. Use when asked to create an agent or a workflow, add a…
adk-style
Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file and test layout, and unit test structure. Use when writing or editing ADK source or tests, deciding whether a new file or…
adk-verify-snippets
Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail report with per-snippet coverage. Use when the user asks to verify, test, or validate the code samples in a README, a guide…
adk-setup
Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development…
python-best-practices
Provides Python patterns for type-first development with dataclasses, discriminated unions, NewType, and Protocol. Must use when reading or writing Python files.
Python Data Analysis
Clean datasets and create reproducible Python transformations and charts.