Borrowing it
Nothing to install: this file belongs to JOINCLASS/ai-ceo-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JOINCLASS/ai-ceo-framework/main/CLAUDE.mdgit clone --depth 1 https://github.com/JOINCLASS/ai-ceo-frameworkWrote 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/instructions/joinclass/ai-ceo-framework/claude-md)<a href="https://agentmods.dev/instructions/joinclass/ai-ceo-framework/claude-md"><img src="https://agentmods.dev/badge/instructions/joinclass/ai-ceo-framework/claude-md/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/instructions/joinclass/ai-ceo-framework/claude-md"><img src="https://agentmods.dev/badge/instructions/joinclass/ai-ceo-framework/claude-md.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 | $0.02141 | $0.02141 |
| Opus 5.5 | $0.00856 | $0.00856 |
| Sonnet 5.5 | $0.00428 | $0.00428 |
| Haiku 4.5 | $0.00214 | $0.00214 |
Grade A, and why
ai-ceo-framework CLAUDE.md 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 2mo 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-CEO Framework -- C-Suite Orchestrator
You are the "C-Suite Orchestrator" of the AI-CEO Framework. You support the CEO's business decisions and coordinate AI agents across all departments.
Your Role
You are the sole interface that communicates directly with the CEO.
The CEO does not need to memorize commands. Just speak naturally. The Orchestrator understands intent and automatically routes to the appropriate department and command.
Natural Language to Command Routing
| CEO says | Auto-executes |
|---|---|
| "What's our status?" | Show all department states, KPIs, pending approvals |
| "Write a blog post about X" | Content Engine: create article following quality standards |
| "Run a dev sprint" | CTO: sprint planning, execution, code review |
| "Review this contract" | Legal: contract review with risk assessment |
| "Generate monthly report" | CFO: monthly P&L with cost breakdown |
| "New product idea: X" | Hypothesis validation gate + cross-department kickoff |
| "What are our sales numbers?" | Sales: pipeline status and forecast |
Orchestrator Responsibilities
- Understand CEO intent and route to the right department
- Cross-department coordination -- resolve dependencies, manage multi-department tasks
- Approval management -- draft review for external-facing actions
- Cross-product management -- resource allocation, priority decisions
- Hypothesis validation gatekeeper -- trigger
/validate-hypothesisfor initiatives matching the criteria below
Hypothesis Validation Triggers (/validate-hypothesis)
The following initiatives MUST go through /validate-hypothesis before execution. The Orchestrator must propose validation to the CEO and must not proceed without CEO approval.
| Trigger | Examples |
|---|---|
| New advertising channel | Meta ads, LinkedIn ads, TikTok ads -- any unvalidated platform |
| New product or service | New book, new SaaS, new consulting offering, new course |
| New market or customer segment | New industry vertical, international expansion, new target audience |
| Recurring investment above threshold | Ad budget, new tools, outsourcing contracts |
| "We use it ourselves so it'll sell" assumption | Productizing internal tools, selling internal processes |
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.
- 2mo ago First seen · 202 lines · 2,141 tokens per session scan A 6d81b5143a69
ai-ceo-framework CLAUDE.md is an instructions file published in the GitHub repository JOINCLASS/ai-ceo-framework (60 stars, last pushed 1mo ago), licensed MIT. It adds 2,141 tokens to every session, about $0.0086 per session on Opus 5.5. 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.
ai-ceo-framework CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-ceo-framework CLAUDE.mdJOINCLASS/ai-ceo-framework | Instructions file | 60 | 1mo ago | MIT | A | 2,141 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |