cast-org

cast-org is a skill for Claude Code from codecast-sh/codecast. It costs 0 tokens per session (1,180 once invoked), scanned A, original, MIT.

A guided way to organise the people, roles, permissions, and work sessions around a project. It reads the current workspace, shows proposed changes, and applies accepted record updates with their reasons and evidence.

In plain words
What is it for?
Use it to review team members and roles, inspect workload and stale records, review pending proposals, and update organisation records with a person's approval.
Why use it?
It helps keep the organisation's records aligned with the people and work that actually exist. It also reduces mistakes caused by checking the wrong workspace or making changes without reviewing them first.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to review team members and roles, inspect workload and stale records, review pending proposals, and update organisation records with a person's approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/codecast-sh/codecast/cast-org
Install

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.

Any agent
npx skills add codecast-sh/codecast --skill cast-org
Clone the repo
git clone --depth 1 https://github.com/codecast-sh/codecast

Made for: Claude Code.

Wrote 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.

agentmods badge for cast-org

README.md
[![agentmods](https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-org/github.svg)](https://agentmods.dev/skills/codecast-sh/codecast/cast-org)
Your own site
<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.

agentmods 80×15 button for cast-org

Your own site · 80×15
<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>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,180 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash 7b61ebffcc66, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

packages/cli/skills/cast-org/SKILL.md · 101 lines

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.

Read the full file on GitHub · 101 lines

Changes

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.

  1. 10d ago Changed · +12 lines 7b61ebffcc66
  2. 13d ago Changed ee83aa3a7cd4
  3. 20d ago Changed · -59 lines · -117 tokens per session 30c2cb07cba5
  4. 26d ago Changed · +22 lines d9836a22b9d0
  5. 27d ago Changed 0f105b434ba5
  6. 28d ago First seen · 126 lines · 117 tokens per session scan A 62811c72c48a

Subscribe to this mod's changes

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.