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-motiongit 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-motion)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-motion"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-motion/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-motion"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-motion.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 | $0.00079 | $0.01825 |
| Opus 5.5 | $0.00032 | $0.00730 |
| Sonnet 5.5 | $0.00016 | $0.00365 |
| Haiku 4.5 | $0.00008 | $0.00183 |
Grade A, and why
cast-motion 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A motion page is a short film written as HTML: a composition whose every
beat, number and timing is code, published with cast publish so people
watch it in the browser, scrub to a moment and comment there. Because it is
code, a comment like "hold on the empty dock a beat longer" is a one-line
edit and a republish, not a re-edit of footage.
Start from the question and the reveal
Before anything visual, write down the one question a viewer walks in with and the reveal that answers it. "Why are the hill docks empty by 8:15?" is a question; "commuters ride downhill in the morning and nobody rides back up" is its reveal. Every beat exists to make that reveal land: set up what the viewer expects, show the evidence, turn, reveal, and leave them with what it means. A piece without a reveal is a slideshow of charts; find the surprising fact in the data first, and if there is none, say so instead of animating.
Storyboard before code
Write the beats as a list before writing markup: for each, what the viewer learns, what is on screen, and how long it holds. Explainers run 30 to 90 seconds; a beat that teaches nothing goes. Durations add up to the whole, and the reveal gets the most time. The hook lands at once: the question is on screen within the first second, and every beat shows its point as it opens rather than after a lead-in, while the reveal is earned later. Share the storyboard with the person when the direction is theirs to choose; otherwise build from it.
Numbers come from real data
Every number on screen comes from a query you ran, and the composition keeps
the source beside the value so a reader of the code can rerun it. Codecast's
own record is the usual source: cast feed, cast search "<topic>" after:7d,
cast task ls, git log --since, cast events ls, cast metrics ls, and a
dashboard's own queries. Never round a number into a better story or invent
one to fill a beat.
When the page has a live data source, bind the number instead of baking it:
<span data-cast-data="<data id>" data-cast-col="<column>" data-cast-row="-1" data-cast-format="int">1,204</span> shows the current value from
window.cast.data and follows revisions without a re-render, while the
authored text stays for renders and offline viewers. A script that needs the
value to build a tween (a count up, a bar height) reads it with
await window.castMotion?.value(id, col, row) before registering its
timeline, falling back to the authored number.
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 · 136 lines · 79 tokens per session scan A 91c1c51a1439
cast-motion is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 1,825 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.