A company-running setup in which separate AI agents act as roles such as CEO, finance, product, legal, and risk review, sharing decisions through a company state file. The founder remains the only human and answers questions raised by the agents.

Use it to create a company from an idea, ask the company questions, receive cross-department decisions, and maintain a living roadmap through agent processes.

It gives an ongoing project a way to distribute decisions across business areas while keeping shared state. It is intended to run inside Claude Code rather than merely producing a one-time business document.

startup-os — Skill for Claude Code by jordantplows

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 jordantplows/claude-skills --skill claude-plugin

Clone the repo

git clone --depth 1 https://github.com/jordantplows/claude-skills

Made for: Claude Code.

Or install startup-os, the plugin that ships this one along with the rest of its 3 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jordantplows/claude-skills/claude-plugin/github.svg)](https://agentmods.dev/skills/jordantplows/claude-skills/claude-plugin)

Your own site

<a href="https://agentmods.dev/skills/jordantplows/claude-skills/claude-plugin"><img src="https://agentmods.dev/badge/skills/jordantplows/claude-skills/claude-plugin/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jordantplows/claude-skills/claude-plugin"><img src="https://agentmods.dev/badge/skills/jordantplows/claude-skills/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 915 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.

Model	Per session	Once invoked
Fable 5.1	$0.00043	$0.00915
Opus 5	$0.00022	$0.00458
Sonnet 5	$0.00009	$0.00183
Haiku 4.5	$0.00004	$0.00092

Measured 10d ago against content hash 39fbac905004, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

startup-os 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.

The scan reads SKILL.md. This mod also ships 1 executable file (skill-handler.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude-plugin/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

startup-os · company runtime

This is not a document generator. This is a company operating system.

When you run /startup-os build you instantiate a living company where AI agents are parallel processes coordinating through shared state in company.os.json.

The CEO agent doesn't write a CEO document — it acts as CEO. The legal agent doesn't generate templates — it watches every decision. The product agent doesn't produce a roadmap PDF — it maintains the living roadmap.

The founder is the only human. Their job is to answer questions agents surface.

Commands

/startup-os build ""

Instantiate a new company from an idea string.

Process:

Parse the idea and ask 3 clarifying questions
Spawn all agents in parallel (CEO, CFO, Product, Legal, Red Team, etc.)
Each agent initializes its domain knowledge for this company
CEO gives first briefing with cross-department status
Company runs continuously in Claude Code

/startup-os ask

Talk to your company. Message is routed to relevant agents who respond.

Examples:

/startup-os ask what should I work on today
/startup-os ask legal, what are you watching
/startup-os ask give me the product roadmap
/startup-os ask red team, what's my biggest risk

/startup-os status

Get a briefing from the CEO on current company state:

What the company is focused on
What each department is doing (specific activities)
Pending decisions that need founder input
Important signals worth knowing
CEO's recommendation for today

/startup-os agents

List all active agents with their current state:

Status (watching, deciding, steering, blocked)
Current focus
Last action taken
Pending decisions

/startup-os reset

Clear all company state and start over. Use when pivoting or restarting.

How It Works

company.os.json — Shared State

Every agent reads this before acting. Every agent writes to it after acting. It's the nervous system of the company.

Contains:

Company profile (identity, stage, customers, problem)
Department states (status, focus, memory, signals)
Decisions in flight (questions waiting for answers)
Events (how agents trigger each other)
MCP connections (external tools wired in)
Founder input log

Read the full file on GitHub · 143 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

10d ago First seen · 143 lines · 43 tokens per session scan A 39fbac905004

Subscribe to this mod's changes

startup-os is a skill published in the GitHub repository jordantplows/claude-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 915 once invoked, about $0.0002 per session on Opus 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 2026-08-31.

Building agents Claude Code Project management agents ai-agents claude-skills deepagents generative-ai

work-on-ticket

Fetches Jira ticket details, creates an appropriately named branch, and initiates the task planning workflow. Use when the user says "work on [TICKETID]" or similar phrases.

jjmartres/ai-coding-agents · 41 tokens

review-spec

Independent read-only review of a frozen Product half before engineering planning. Runs the exact Product checks in a clean context and returns only SPEC-REVIEW-PASS, SPEC-REVIEW-FAIL, or NEEDS-DESIGN with a content-bound receipt. Never edits the reviewed SPEC. Triggers: "review-spec", "review the spec", "review…

gtrabanco/agentic-workflow · 77 tokens

ship-roadmap

Found or continue a roadmap autopilot one stage per invocation. Default: human merge. --fullauto is invocation-scoped and uses the transient wrapper only after a fresh audit. Triggers: "ship-roadmap", "ship the roadmap", "autopilot this project".

gtrabanco/agentic-workflow · 59 tokens

workflow-status

Read-only workflow sensor: compute repository, roadmap, dependency, PR, finding, and recovery state, then emit the fixed machine envelope. Never edits. Triggers: "workflow-status", "workflow status", "what can I build next", "state of the run".

gtrabanco/agentic-workflow · 57 tokens

manage-tickets

Create, edit, search, transition, close, and triage Jira tickets via the Atlassian MCP. Use when asked to file a bug, request a feature, create a task, log a defect, search the backlog, triage findings into the tracker, edit ticket fields, transition status, or manage Jira work items. Also use when the user says…

sergeyklay/.agents · 196 tokens

vet-dependency

Measure a candidate library's real maintenance state and its behavior against the protocol, schema, or API version the project has already pinned, before taking it as a dependency. Covers any ecosystem (Go, npm, PyPI, Cargo, Maven) and any forge (GitHub, GitLab, Gitea). Use when deciding whether to adopt, replace, or…

sergeyklay/.agents · 209 tokens