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-triagegit 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-triage)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-triage"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-triage/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-triage"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-triage.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 | $0.00080 | $0.00454 |
| Opus 5.5 | $0.00032 | $0.00182 |
| Sonnet 5.5 | $0.00016 | $0.00091 |
| Haiku 4.5 | $0.00008 | $0.00045 |
Grade A, and why
cast-triage 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 1mo 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
Every fleet tool exists because a person cannot track eight sessions at once. Triage is the agent doing that tracking and leaving the person a short list.
Read
cast sessions [--label <name>] [--mine] # grouped by who acts next
cast sessions --state needs-input --json # the ones that claim a human
For each session under Needs Input: cast state show <id> and, when the pin
does not explain the ask, cast read <id> for the last few turns. Decide
whether it truly needs a human, is finished and never said so, is stuck on
something another session or you can supply, or is dead with output.
Act
- Finished but unclassified: read its result, then
cast stash <id>; the work is in its diff and the human can restore it. - Stuck on a question you can answer from the code or another session's
work:
cast send <id>the answer. - Waiting on a peer that already delivered: point it at the delivery.
- Dead, work complete:
cast kill <id>. Dead, work incomplete:cast restart <id>and a message to continue from the pin. - Truly needs the human: leave it, and write its ask in one line.
Never kill or stash a session another person owns without saying so; their sessions get a message, not a gesture.
Report
Two lists: what needs the human, one line each with the ask and the short id; and what was tidied, with the action taken. The first list is the deliverable; the second is the receipt.
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.
- 1mo ago First seen · 42 lines · 80 tokens per session scan A 26cf440cf55b
cast-triage is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 454 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.