Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/living-hi/one-person-company-osnpx agentmods add skills/living-hi/one-person-company-os/claude-skillWrote 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/living-hi/one-person-company-os/claude-skill)<a href="https://agentmods.dev/skills/living-hi/one-person-company-os/claude-skill"><img src="https://agentmods.dev/badge/skills/living-hi/one-person-company-os/claude-skill/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/living-hi/one-person-company-os/claude-skill"><img src="https://agentmods.dev/badge/skills/living-hi/one-person-company-os/claude-skill.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 | $0.00033 | $0.00421 |
| Opus 5 | $0.00016 | $0.00211 |
| Sonnet 5 | $0.00007 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
one-person-company-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 12d 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
One Person Company OS For Claude Skills
Use this skill when the user wants to create, operate, or improve an AI-native one-person company.
The visible operating loop is:
promise -> buyer -> product capability -> delivery -> cash -> learning -> asset
Default Behavior
- Treat the user as founder and final decision-maker.
- Clarify the sellable promise, first buyer, and core problem before creating files.
- Persist only inside the founder-approved workspace.
- Keep the first reading surface as an operating cockpit.
- Keep markdown as editable work material and DOCX as formal deliverables.
- Use deterministic SVG/HTML for exact operating data.
- Treat AI image prompts as optional creative material.
Runtime
If local filesystem and Python execution are available, prefer the canonical scripts from the repository root:
python3 scripts/preflight_check.py --mode create-company
python3 scripts/init_business.py "North Star Lab" --path ./workspace --product-name "North Star Assistant" --target-user "independent builders" --core-problem "they need one visible loop for product, revenue, delivery, and cash" --product-pitch "a visual operating cockpit for one-person AI companies" --language en-US --confirmed
python3 scripts/validate_release.py
If script execution is unavailable, continue manually and clearly say which content is not saved.
Required Output Frame
Every substantial response should include:
- current primary goal
- current bottleneck
- primary arena:
sales / product / delivery / cash / asset - shortest action today
- saved path or unsaved reason
- next cockpit surface to open
Boundaries
- Do not auto-install system packages.
- Do not request unrelated credentials.
- Do not write outside the approved workspace.
- Ask for founder approval before pricing, budget, legal, launch, or high-risk customer-facing actions.
What ships with it
1 file 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.
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.
- 12d ago First seen · 53 lines · 33 tokens per session scan A 15a2baed017d
one-person-company-os is a skill published in the GitHub repository living-hi/one-person-company-os (1 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 421 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.
Other skills, from other repositories
add-github
Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.
add-linear
Add Linear channel integration via Chat SDK. Issue comment threads as conversations.
issue-triage
Triage Paperclip inbox issues that are stale, blocked, in-review, or assigned-but-not-progressing, and decide a single next action per issue (resume, reassign, unblock, escalate, or close).
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
task-management
Use before any Worker taskflow call or assigned-task workflow, including reading task state, acknowledging a task, executing a task, tracking progress, handling blockers/questions, submitting structured results, or reporting completion. Always use this skill when the message mentions assigned task, task ID…
task-coordination
Coordinate access to shared task directories using .processing marker files. Use before accessing a Worker's workspace to prevent conflicts when both Manager and Worker might modify files simultaneously.