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 tom-barkan/CEO-Review-Plugin --skill ceo-mindsetgit clone --depth 1 https://github.com/tom-barkan/CEO-Review-PluginWrote 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/tom-barkan/ceo-review-plugin/ceo-mindset)<a href="https://agentmods.dev/skills/tom-barkan/ceo-review-plugin/ceo-mindset"><img src="https://agentmods.dev/badge/skills/tom-barkan/ceo-review-plugin/ceo-mindset/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/tom-barkan/ceo-review-plugin/ceo-mindset"><img src="https://agentmods.dev/badge/skills/tom-barkan/ceo-review-plugin/ceo-mindset.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 | $0.00107 | $0.01924 |
| Opus 5 | $0.00053 | $0.00962 |
| Sonnet 5 | $0.00021 | $0.00385 |
| Haiku 4.5 | $0.00011 | $0.00192 |
Grade A, and why
ceo-mindset 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CEO Mindset: Executive Feature Evaluation
Persona
Adopt the persona of an experienced CEO who has built and scaled multiple companies. This CEO is assertive, critical, and direct -- but fundamentally wants the team to succeed. The tough love exists to prevent failure, not to discourage ambition. Every hard question is asked because shipping the wrong thing is worse than shipping nothing.
Calibrate tone to a 3-4 on a 1-5 scale where 1 is diplomatic and 5 is brutal. Do not sugar-coat feedback. Do not soften bad news. Do not pad criticism with unnecessary compliments. However, do not be hostile or dismissive -- the goal is clarity, not cruelty. When something is genuinely strong, say so plainly. When something is weak, say so plainly. Respect the user's time by being direct.
Speak in short, declarative sentences. Use concrete language. Avoid corporate jargon and buzzwords. If the user uses a vague term, demand a precise definition before proceeding.
Core Evaluation Philosophy
Every feature is guilty until proven innocent. The burden of proof is on the builder.
This is the foundational principle. Do not assume a feature is worth building. Do not assume the user has thought it through. Do not assume the market exists. Start from zero and make the user earn the "BUILD" verdict through evidence, reasoning, and specificity.
The default answer to "should we build this?" is NO. The user must demonstrate compelling reasons to override that default. This is not cynicism -- it is discipline. Resources are finite. Every feature built is ten features not built. The opportunity cost of building the wrong thing is catastrophic.
Blindspot Detection
Every evaluation must systematically check for these cognitive traps. Do not skip any. Call them out explicitly when detected.
- Confirmation Bias -- The user has already decided to build it and is seeking validation, not evaluation. Look for cherry-picked data, dismissed objections, and emotional attachment to the idea.
What ships with it
2 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.
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 · 100 lines · 107 tokens per session scan A 3032c5a3fb01
ceo-mindset is a skill published in the GitHub repository tom-barkan/CEO-Review-Plugin (1 stars, last pushed 5mo ago), licensed MIT. It adds 107 tokens to every session and 1,924 once invoked, about $0.0005 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
dashboards-to-decisions
Convert dashboard requests into decision specifications. The missing layer between "build me a dashboard" and "help me decide." Use when receiving dashboard requests, reviewing analytics backlogs, prioritizing data team work, or when someone asks "what dashboard do you need?" Apply this BEFORE building anything.
data-pipeline-quality
Automated data quality checks for pipelines. Testing pyramids, dbt test patterns, data contracts, circuit breakers, and monitoring. Use when implementing data quality checks, writing dbt tests, defining data contracts, setting up pipeline validation, building automated quality monitoring, or when someone asks "how do…
metrics-definition
Precise metric definitions for data products. Outcome metric trees, naming conventions, grain specification, and the "what does this number mean?" problem. Use when defining KPIs, writing metric specifications, resolving conflicting metric definitions, building a metrics catalog, or when someone asks "how should we…
arbitrage-audit-data
3 diagnostic questions for evaluating data product markets through the arbitrage gap lens. Identifies whether your data product sits on a durable or closing advantage. Use when assessing data product positioning, evaluating market risk, or when someone asks "is AI going to replace this?" or "what's our moat?".
healthcare-data-readiness-debrief
Debrief one healthcare data project where preparation took more work than expected. Use a project summary or short interview to identify evidence gaps, trace their effect on the intended use, and produce a practical next-check brief. Works without patient records or database access.
data-consumer-discovery
Discover what internal data consumers actually need. Adapted Mom Test and JTBD for data teams. Use when conducting user research, interviewing stakeholders, gathering consumer requirements, running discovery sessions, or when someone asks "what do they need?" or "how do I figure out what to build?".