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 codecast-sh/codecast --skill cast-dashboardgit clone --depth 1 https://github.com/codecast-sh/codecastWrote 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/codecast-sh/codecast/cast-dashboard)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-dashboard"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-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/codecast-sh/codecast/cast-dashboard"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-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 | $0.00084 | $0.00681 |
| Opus 5.5 | $0.00034 | $0.00272 |
| Sonnet 5.5 | $0.00017 | $0.00136 |
| Haiku 4.5 | $0.00008 | $0.00068 |
Grade A, and why
cast-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 2d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A dashboard is worth building only around a question someone keeps asking: is the launch working, where does the spend go, are bugs closing faster than they arrive. Codecast's edge over a generic BI tool is that the product's numbers and the work behind them sit on one page, so look for the join: a spike in errors beside the sessions and pull requests that answered it, a signup metric beside what shipped that week.
Find the question
Start from what the person asked, and ask once if the question is unclear.
Then look at what data exists before designing anything: cast sources ls,
cast metrics ls, cast connector readers <source>, and the readers in
cast guide publish (Dashboards). A chart over data the workspace does not
have is a blank box; leave it out and say what would fill it.
Pick the queries
Each chart reads one named query in the bundle's cast-data.json. Choose
the reader and window that answer the question directly, and the refresh
interval the data actually moves at: spend and tasks change over hours, an
error rate over minutes. Name the workspace when the page is for a team;
otherwise it is the one this session works in, which the publish output
names. Keep the set small: every query is a read that runs again on its
interval while anyone has the page open.
Lay it out
Lead with the few numbers that answer the question (<cast-stat>), then
the trends that explain them (<cast-chart> lines, areas, bars), then the
detail someone drills into (tables). Give each a plain title that says what
it measures. The page carries the codecast theme tokens, so style the layout
with them and let the elements inherit; keep the page itself quiet, since
the data is the point.
Publish and verify
Publish the directory with cast publish <dir>. Then check the data, not
the picture: cast publish data <slug> --refresh runs every query now and
prints its query text and rows, so an empty result, a wrong window or a
reader error shows up before anyone else sees the page. Open the page in
your browser tab and look at it, and fix what reads wrong before you share
the link.
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.
- 2d ago First seen · 60 lines · 84 tokens per session scan A d773eac32b2c
cast-dashboard is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 681 once invoked, about $0.0003 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 2026-10-14.
Other skills, from other repositories
google-agents-cli-scaffold
This skill should be used when the user wants to "create an agent project", "start a new ADK project", "build me a new agent", "add CI/CD to my project", "add deployment", "enhance my project", or "upgrade my project". Part of the agents-cli skills suite. Covers agents-cli scaffold create, scaffold enhance, and…
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
grocery-prices
A skill to calculate grocery prices with country-specific taxes.
honey-px
Read huge read-only text as PNG pages; big input cut.
honey-memory
Per-project persistent memory files indexed in MEMORY.md.
debate
Weigh one risky change against a named alternative through an advocate, a skeptic, and a neutral investigator, then recommend.