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-from-callgit 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-from-call)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-from-call"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-from-call/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-from-call"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-from-call.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 | $0.00090 | $0.00516 |
| Opus 5.5 | $0.00036 | $0.00206 |
| Sonnet 5.5 | $0.00018 | $0.00103 |
| Haiku 4.5 | $0.00009 | $0.00052 |
Grade A, and why
cast-from-call 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
Action items written from memory drift from what was said. The transcript is exact and speaker attributed, so the tasks can quote it.
Read
cast calls -n 10 # find the call; the newest is the default
cast call <id> # title, participants, summary, generated action items
cast call <id> --transcript # who said what; the source of truth
For a chat thread: cast chat thread <root_id>.
Check every generated action item against the transcript: who committed, to what, by when, and whether anyone pushed back later in the call. Drop items that were floated and not agreed. Add ones the summary missed.
File
cast task create "<what, in the owner's words>" --from-call <call id> --assignee <member> -p <priority> -d - <<'DESC'
Agreed on the call <title> (<date>).
<speaker>: "<the line, quoted>"
Due: <if said>
DESC
--from-call links the task to the call, so it shows on the call's page and
in cast call <id>, and marks it as decided in a meeting, which puts it on
the human's board because a person agreed to it; never use it for work you
decided on your own. A task filed earlier joins the call with cast task update <task> --from-call <call id>. When the call named a
project or plan, file under it with --project or --plan. Decisions made
on the call that are not tasks: cast decisions add "<title>" --reason "<the quoted line>".
Report
The tasks created with their short ids and owners, the items dropped with the reason, and anything the call left unresolved that needs a follow up. Post the list on the team channel only when asked.
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 · +3 lines c6a14a0dad51
- 1mo ago First seen · 45 lines · 90 tokens per session scan A 5da5a05929cb
cast-from-call is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 516 once invoked, about $0.0004 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
to-tickets
Slice a spec or a ticket into tracer-bullet tickets with blocking edges, saved to .specs/tickets/ .md.
to-spec
Turn the settled conversation into a spec (PRD) at .specs/specs/ .md.
register-project
Register an existing project in memory. Use when starting work on a new repo or when a project needs its own context file. Triggers on: 'register project', 'add project to memory', 'track this project', 'create project file'.
idea-vault
Cross-project idea capture and review. A notebook-with-reminders that logs the user's ideas, plans, and checklists across every project, in one plain-markdown file. Use this skill whenever the conversation contains a new idea, plan, or intention the user might want to save for later, and whenever a project milestone…
status
Show project status dashboard across registered repositories.
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.