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 2389-research/ceo-personal-os --skill skillsgit clone --depth 1 https://github.com/2389-research/ceo-personal-osWrote 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/2389-research/ceo-personal-os/skills)<a href="https://agentmods.dev/skills/2389-research/ceo-personal-os/skills"><img src="https://agentmods.dev/badge/skills/2389-research/ceo-personal-os/skills/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/2389-research/ceo-personal-os/skills"><img src="https://agentmods.dev/badge/skills/2389-research/ceo-personal-os/skills.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 | $0.00123 | $0.01464 |
| Opus 5 | $0.00062 | $0.00732 |
| Sonnet 5 | $0.00025 | $0.00293 |
| Haiku 4.5 | $0.00012 | $0.00146 |
Grade A, and why
ceo-personal-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 11d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CEO Personal Operating System
Overview
Build a reflection system, not a task manager. This is a private, single-user operating system for executives that combines thoughtful frameworks with coaching-style prompts.
Core principle: Clarity over productivity theater. No hustle culture. No corporate jargon.
Tone: Calm, executive-level, direct, insightful. Like an executive coach, chief of staff, and accountability partner.
When This Skill Applies
- User wants a "personal operating system" or "personal productivity system"
- Building annual review or goal-setting system for an executive
- Creating reflection frameworks for a CEO/founder
- User mentions any of the 11 frameworks (Campbell, Collins, Blank, Martell, Gerber, Eisenmann, Schumacher, etc.)
- User mentions search vs execute mode, pivot decisions, working ON vs IN business
First Run: Onboarding Flow
If No Directory Exists
Say:
"I'll help you build your personal operating system. This is a reflection system - think executive coach, not task manager.
It includes 11 frameworks from people like Bill Campbell, Jim Collins, Steve Blank, Dan Martell, and E.F. Schumacher, plus 11 coaching-style interview scripts.
Ready to set it up?"
Then use TodoWrite to track building the full structure.
If Directory Exists
Say:
"Welcome back. What would you like to do?"
- Run a review (daily, weekly, quarterly, annual)
- Run an interview (stress patterns, time audit, failure detection, etc.)
- Update goals (1-year, 3-year, 10-year)
- Explore a framework
- Extract patterns from past reviews
Required Structure
Create in ceo-personal-os/:
ceo-personal-os/
├── README.md # How to use (personalize in 15 min)
├── principles.md # User's core operating principles
├── memory.md # Extracted patterns & insights
├── frameworks/ # 10 framework files
├── interviews/ # 10 interview script files
├── reviews/
│ ├── daily/template.md
│ ├── weekly/template.md
│ ├── quarterly/template.md
│ └── annual/template.md
├── goals/
│ ├── 1_year.md
│ ├── 3_year.md
│ └── 10_year.md
└── uploads/ # Past reviews for analysis
What ships with it
12 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.
- references/frameworks/blank-customer-development.md 2.9 KB
- references/frameworks/campbell-coaching.md 1.6 KB
- references/frameworks/collins-good-to-great.md 1.9 KB
- references/frameworks/eisenmann-failure-patterns.md 2.6 KB
- references/frameworks/ferriss-lifestyle-costing.md 1010 B
- references/frameworks/gerber-emyth.md 2.2 KB
- references/frameworks/gustin-annual-review.md 875 B
- references/frameworks/lieberman-life-map.md 1001 B
- references/frameworks/martell-buyback-time.md 1.9 KB
- references/frameworks/robbins-vivid-vision.md 1.1 KB
- references/frameworks/schumacher-human-scale.md 5.5 KB
- references/interviews/interview-scripts.md 7.8 KB
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.
- 11d ago First seen · 153 lines · 123 tokens per session scan A c55ad73f148f
ceo-personal-os is a skill published in the GitHub repository 2389-research/ceo-personal-os (5 stars, last pushed 2mo ago), licensed MIT. It adds 123 tokens to every session and 1,464 once invoked, about $0.0006 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
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
phx-mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
quick
Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations. Use for single-file edits under 50 lines.
phx-freeze
Apply an advisory edit scope in this session. Use for read-only or directory-scoped work; no enforcement hook is installed.
caveman-help
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".