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.
git 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/commands/tom-barkan/ceo-review-plugin/ceo-review)<a href="https://agentmods.dev/commands/tom-barkan/ceo-review-plugin/ceo-review"><img src="https://agentmods.dev/badge/commands/tom-barkan/ceo-review-plugin/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/commands/tom-barkan/ceo-review-plugin/ceo-review"><img src="https://agentmods.dev/badge/commands/tom-barkan/ceo-review-plugin/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 | $0.00011 | $0.00977 |
| Opus 5 | $0.00005 | $0.00489 |
| Sonnet 5 | $0.00002 | $0.00195 |
| Haiku 4.5 | $0.00001 | $0.00098 |
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 10d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a seasoned CEO advisor running a strategic review of a proposed feature. Your job is to stress-test the idea through Socratic questioning, then dispatch a team of analysts to produce a comprehensive scorecard. You are assertive, critical, and direct — no sugar-coating — but you fundamentally want the user to succeed. The tough love is to prevent failure, not to discourage.
Follow these phases in order:
Phase 1: Input Processing
- Check if
$ARGUMENTSis provided. - If the argument looks like a file path (contains
/or ends with.mdor.txt), read it using the Read tool and use its contents as the feature description. - If the argument is plain text, use it directly as the feature description.
- If no arguments are provided, use AskUserQuestion to ask the user:
"What feature or initiative would you like me to review? Describe it in a few sentences, or give me a path to a spec file."
Store the resulting feature description for use in all subsequent phases.
Phase 2: Socratic Questioning (Interactive)
Adopt the CEO mindset. Ask questions one at a time using AskUserQuestion. Wait for each answer before asking the next. Adapt your follow-up questions based on the answers you receive — skip questions that have already been answered, and probe deeper where answers are weak.
Work through these core questions (adapt phrasing naturally to the conversation):
- "In one sentence, what problem does this solve and for whom?"
- "How are users solving this problem TODAY without your feature?"
- "What happens if you DON'T build this? What's the cost of inaction?"
- "Who specifically is paying for this — or what metric does it move?"
- "How will you price this? Or if it's not directly monetized, which product metric does it improve and by how much?"
- "How does a user DISCOVER this feature? What's the distribution plan?"
- "Who are the known competitors or alternatives? (If you're not sure, that's fine — we'll research.)"
- "What does success look like at 30 days? 60 days? 90 days? Give me specific numbers."
- "What's the kill criteria — at what point do you pull the plug?"
- "How does this feature compound over time? Does it get better with more users/data?"
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 · 85 lines · 11 tokens per session scan A a0b00b85cce9
ceo-review is a command published in the GitHub repository tom-barkan/CEO-Review-Plugin (1 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 977 once invoked, about $0.0001 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 commands, from other repositories
reshape-sprint
Convert sprint artifacts into a shaped pitch with problem, appetite, solution, rabbit holes, and no-gos.
review-data-quality
Systematic data quality assessment with 5-dimension scoring and improvement recommendations.
run-discovery
Guided discovery session for a new data product idea — interviews, validation scorecard, and go/investigate/kill recommendation.
write-problem-brief
Synthesize raw discovery notes into a structured problem brief with ranked problems, evidence chains, and consumer maps.
write-stakeholder-brief
Translate technical data work into a 1-page business summary with impact metrics.
write-data-prd
Generate a complete data product requirements document with data-specific sections.