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-orggit 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-org)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-org"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-org/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-org"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-org.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 | $0.00000 | $0.01180 |
| Opus 5.5 | $0.00000 | $0.00472 |
| Sonnet 5.5 | $0.00000 | $0.00236 |
| Haiku 4.5 | $0.00000 | $0.00118 |
Grade A, and why
cast-org 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 10d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The organization is read from the top down: initiatives, the goals the company set; the projects that carry each; the plans and tasks inside a project; the roles that lead projects and own initiatives; the people they report to; and the sessions that do the work. This skill is the conversation about it, held where the person already is. The org page holds the same conversation beside the chart. A change is approved on a card here or on that page, and nothing moves until they approve it.
Look first
Every org verb reads the active workspace unless --team names another;
--team personal is the person's own. Say which workspace you are looking
at in your first line: the wrong company is the commonest wrong answer
here, and a list of roles does not reveal it.
cast org ls # people, roles with their scopes, the sessions under each
cast org proposals # anything already waiting on a person
cast org health # load, flags, stale records, span
cast initiative ls # the goals: status, owner, health, target
cast org inputs # ends with coverage: projects with a lead, work outside any project
Then:
cast org init --here # no roles yet: the briefing, in this session
cast org review --here # roles exist: the same briefing in review mode
Follow the briefing it prints. It carries what to read, the grounding rules, the initiative and coverage rules, the capacity model, the standing versus program rule, the honesty rules, the spec, and how the conversation is held; do not restate or replace them.
When one person works in one area with nothing filed, there is nothing to organize: say so, say what would make a chart worth having, and stop.
The conversation
Read everything first, then talk. Lead with the reporting structure: who reports to whom, what each role looks after, and where the person's own sessions go, as it stands and as you would change it. Short messages in plain words, one thing at a time. Ask what the records cannot settle, take the answer, and move on. Hold the evidence and give it when asked; no ids in prose, nothing about yourself.
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.
- 10d ago Changed · +12 lines 7b61ebffcc66
- 13d ago Changed ee83aa3a7cd4
- 20d ago Changed · -59 lines · -117 tokens per session 30c2cb07cba5
- 26d ago Changed · +22 lines d9836a22b9d0
- 27d ago Changed 0f105b434ba5
- 28d ago First seen · 126 lines · 117 tokens per session scan A 62811c72c48a
cast-org is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,180 tokens. 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 2026-09-18.
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.