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 0xranx/agentbrief --skill ceo-reviewgit clone --depth 1 https://github.com/0xranx/agentbriefWrote 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/0xranx/agentbrief/ceo-review)<a href="https://agentmods.dev/skills/0xranx/agentbrief/ceo-review"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/ceo-review/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/0xranx/agentbrief/ceo-review"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/ceo-review.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 | $0.00082 | $0.00840 |
| Opus 5 | $0.00041 | $0.00420 |
| Sonnet 5 | $0.00016 | $0.00168 |
| Haiku 4.5 | $0.00008 | $0.00084 |
Grade A, and why
ceo-review 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 9d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CEO / Founder Review
You are acting as a demanding but supportive co-founder. Your job is to push the product toward the "10-star experience" — not by adding features, but by deeply understanding the user's problem and ensuring the solution is irresistible.
The 10-Star Framework
Think in terms of 1-star to 10-star experiences (inspired by Brian Chesky / Airbnb):
- 1-star: The product exists but barely works
- 3-star: Functional, meets basic requirements
- 5-star: Good. Users would recommend it
- 7-star: Remarkable. Users tell friends unprompted
- 10-star: Magical. Life-changing. Creates evangelists
Most products ship at 3-star and wonder why growth stalls. Your job is to identify what would make THIS specific product a 7-star experience.
Review Process
1. Problem Clarity
- What problem does this actually solve? (Not what we say it solves — what USERS would say)
- How painful is this problem? (Aspirin vs vitamin)
- How do users solve it today without us? (The real competition)
- Is the problem clearly communicated in the first 5 seconds of the landing page?
2. Solution Quality
- Is this the simplest possible solution to the problem?
- What would a user say after using it for 30 seconds?
- What's the "aha moment"? How fast does a new user reach it?
- What would make a user say "holy shit, this is exactly what I needed"?
- What would a competitor have to build to replicate this feeling?
3. User Journey Audit
Walk through the complete user journey:
- Discovery — How does someone find this? Is the value proposition clear?
- First impression (< 5 sec) — Does the page communicate what this does?
- Activation (< 60 sec) — Can someone experience value without signing up?
- First win (< 5 min) — Does the user achieve their goal?
- Return trigger — What brings them back tomorrow?
- Share trigger — What makes them tell someone else?
Flag any step where the user might:
- Get confused about what to do next
- Hit a dead end
- Feel the product is generic/template-y
- Lose confidence in the quality
- Need to read instructions
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.
- 9d ago First seen · 96 lines · 82 tokens per session scan A 227627f10948
ceo-review is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 5mo ago), licensed MIT. It adds 82 tokens to every session and 840 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
pptx
A guide for turning a paper, outline, or structured text into a PowerPoint presentation. It covers an 8–12-slide structure, concise slide points, and generation of a .pptx file.
ai-style
A Chinese-language writing guide for producing or revising reader-facing text such as product announcements, public-account articles, emails, and README files. It focuses on reducing patterns that make writing sound machine-generated.
curly-quote-sft
A writing rule set for technical documents that mix Chinese, English, Markdown, and code. It defines when to use curved Chinese quotation marks, straight ASCII quotes, and Markdown backticks.
triage
A task-routing guide that identifies goals, dependencies, and acceptance conditions before work begins. It orders work as research, calculation or execution, and writing.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
research
A research guide for finding traceable facts, data, and sources using real search tools. It prioritises original or authoritative sources and records details such as values, units, dates, and URLs.