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-handoffgit 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-handoff)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-handoff"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-handoff/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-handoff"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-handoff.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 | $0.00077 | $0.00730 |
| Opus 5.5 | $0.00031 | $0.00292 |
| Sonnet 5.5 | $0.00015 | $0.00146 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
cast-handoff 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 26d 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.
Git holds what changed. Write what git does not: why it changed, where it is going, and what to do first. The reader was not here and will not read the transcript, so the doc must stand alone.
Write it
Cover, in this order and only when true:
- Goal in one sentence, and the task or plan it belongs to.
- Decisions made and the reason for each; alternatives rejected and why.
- What is verified, how (the exact command or the screenshot), and what is not. Test commands with their results, so nothing is rerun.
- Open questions and what would resolve them.
- Next steps in order; the first one concrete enough to start cold.
- Live panes with the attach command, feature flags, credentials, flaky areas.
Skip history and activity. If a section would be empty, leave it out.
File it
cast doc create "Handoff: <goal>" -t note -l handoff -c - <<'DOC'
…the doc…
DOC
cast state --status <done|blocked|dormant> - <<'STATE'
<what this session was working on, standing alone>
Next: <first step>, handoff in doc:<id>
STATE
Record any decision the doc names with cast decisions add "<title>" --reason "<why>" so it is searchable outside the doc. If the work is bound to a task,
cast task comment <id> with the doc id.
Hand it on
- Another agent or model:
cast handoff --to codex(or--to claude --model opus,--to gemini,--model sonnetfor the same agent). The server writes a brief of this session, composes the new session's first prompt from it with the read commands for this transcript, starts the session in this directory as an inbox card linked both ways, binds it to this session's task or plan, and pins this session's state as done. Add-m "<direction>"(or-m -for stdin) to steer it;--dry-runprints the prompt and starts nothing. End your turn after it: the new session continues the work. fork:cast fork --tip "<the first next step, naming doc:<id>>"keeps the history and continues in the human's inbox.spawn:cast spawn -with a self contained brief that opens with the doc id; the new session has none of this context.- A session id:
cast send <id>the doc id and the first step, one message. - A member:
cast own <session> <member>on this session, thencast sendis not needed; the state pin tells them where it stands. - No argument: the doc and the pin are the handoff. Stop.
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.
- 26d ago Changed · +8 lines 88b146158c6b
- 1mo ago First seen · 52 lines · 77 tokens per session scan A 45536cde0367
cast-handoff is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 730 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
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.