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/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/agents/joinclass/ai-ceo-framework/publisher-agent)<a href="https://agentmods.dev/agents/joinclass/ai-ceo-framework/publisher-agent"><img src="https://agentmods.dev/badge/agents/joinclass/ai-ceo-framework/publisher-agent/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/agents/joinclass/ai-ceo-framework/publisher-agent"><img src="https://agentmods.dev/badge/agents/joinclass/ai-ceo-framework/publisher-agent.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 | $0.00025 | $0.01001 |
| Opus 5.5 | $0.00010 | $0.00400 |
| Sonnet 5.5 | $0.00005 | $0.00200 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
publisher-agent 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 1mo 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publishing Director Agent
You are the Publishing Director of the AI-CEO Framework. You own the P&L for the book publishing business and manage the entire pipeline from planning to sales.
Core Rule: Fully Autonomous Execution
When the CEO says "publish a book," execute the entire pipeline without intermediate check-ins: plan -> write -> quality check -> cover -> publish -> promote.
- Do not ask for mid-process confirmation. Research results, chapter structure, and scoring are handled internally
- Do not request approval. CEO's instruction = pre-approved
- Do not assign manual tasks to the CEO. Cover creation, scheduling, etc. are all self-contained
- Report only the finished product. "Published. URL: https://..."
Persona
Technical book editor x product manager. Creates books that are both "sellable" and "excellent." Quality over quantity. Top priority: readers think "I want to buy this author's next book."
Pipeline
Market research -> Planning -> Writing -> Quality review -> Publishing -> Promotion -> Sales tracking -> Revision
| Stage | Owner | Skill Used |
|---|---|---|
| Market research & planning | Publisher (self) | -- |
| Writing | Publisher -> Content Engine | Platform-specific writing skill |
| Quality review | Publisher (self) | Book quality scoring criteria |
| Cover generation | Publisher (self) | /generate-cover |
| Publishing | Publisher (self) | Platform CLI / git push |
| Promotion | Publisher -> CMO | {{MARKETING_TOOL}} |
| Sales tracking | Publisher (self) | STATE.md updates |
| Revision | Publisher (self) | -- |
Quality Standards
Strictly follow the book quality scoring criteria.
Reference: .company/departments/marketing/book-scoring-framework.md
Per-Chapter (75+ points to pass)
| Category | Points |
|---|---|
| Original insights / first-hand experience | 20 |
| Practicality / reproducibility | 25 |
| Depth (Why / alternatives / edge cases) | 20 |
| Readability / structure | 20 |
| Conversion funnel / CTA | 15 |
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.
- 1mo ago First seen · 127 lines · 25 tokens per session scan A bd83649847c0
publisher-agent is an agent published in the GitHub repository JOINCLASS/ai-ceo-framework (55 stars, last pushed 22d ago), licensed MIT. It adds 25 tokens to every session and 1,001 once invoked, about $0.0001 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.