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-passgit 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-pass)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-pass"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-pass/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-pass"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-pass.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 | $0.00071 | $0.00519 |
| Opus 5.5 | $0.00028 | $0.00208 |
| Sonnet 5.5 | $0.00014 | $0.00104 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
cast-pass 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 9d 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.
What it actually says
A session passed without a brief is a transcript the teammate has to read from the top. The pin and the message are what make it a handoff.
Pin
cast state --status blocked with a first line that stands alone for
someone who has not read the thread, then what is verified, what is open,
and Next: naming the first thing they should do. If the work is more than
an hour deep, write the handoff doc first (/cast-handoff) and put its
id in the pin.
Own
cast own <member> # adds them; the session sits in both inboxes
cast own <session> <member> # a different session of yours
They get a notification, and the session surfaces under Needs Input in
their inbox with your name on it. Use cast disown on yourself only if the
work is entirely theirs now.
Brief
cast send to this session's id is pointless; the teammate reads the pin.
When the note argument is given, or when the pass needs a reason the pin
does not carry, post it where they will see it: the bound task
(cast task comment <id>) or the team channel with their handle
(cast chat send --channel <id> "@<handle> …"), one message. If the task
should change assignee, cast task update <id> --assignee <member>.
When the work lives in uncommitted or unpushed changes, the transcript
alone leaves them without the files. Name the command that recreates this
tree on their machine, in the pin and the message:
cast ws acquire <name> --from <this session's short id> gives them a
worktree on this session's branch with its changes as uncommitted work.
It reads the snapshot this machine's daemon last pushed to the remote
(every few minutes while it runs), so the last few minutes of edits may
not be in it yet.
Then stop. The next move is theirs.
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.
- 9d ago Changed · +9 lines a6ec982a7448
- 1mo ago First seen · 39 lines · 71 tokens per session scan A a2f0deecd382
cast-pass is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 519 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 2026-09-15.
Other skills, from other repositories
prismer-notion
Notion API + ntn CLI: pages, databases, markdown, Workers.
prismer-teams-meeting-pipeline
Teams meeting summaries, job replay, Graph subscriptions.
prismer-apple-reminders
Apple Reminders via remindctl: add, list, complete.
weekly-review
Review commitments and stalled work from Prismer tasks and memory, then produce an evidence-based weekly plan with explicit coverage gaps.
document-actions
Extract cited facts, obligations, deadlines and proposed actions from documents, preserving OCR uncertainty and reconciling Prismer tasks.
meeting-actions
Turn supplied meeting notes or transcripts into cited decisions, commitments, unresolved questions, and deduplicated Prismer tasks.