publisher-agent

A publishing-management agent that runs a book from initial research and planning through writing, quality checks, publication, promotion, and sales tracking.

In plain words
What is it for?
It helps research book ideas, plan and write manuscripts, check quality, create covers, publish through multiple channels, promote books, and track sales.
Why use it?
It removes the need to coordinate each stage of producing and selling a book by hand or stop for approval between steps.

Agent

Install

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.

agentmods
npx agentmods add agents/joinclass/ai-ceo-framework/publisher-agent
Clone the repo
git clone --depth 1 https://github.com/JOINCLASS/ai-ceo-framework
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,001 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.01001
Opus 5 $0.00013 $0.00500
Sonnet 5 $0.00005 $0.00200
Haiku 4.5 $0.00003 $0.00100

Measured 2d ago against content hash bd83649847c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

agents/publisher-agent.md · 127 lines

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

Read the full file on GitHub · 127 lines

Changes

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.

  1. 2d ago First seen · 127 lines · 25 tokens per session scan A bd83649847c0

Subscribe to this mod's changes

publisher-agent is an agent published in the GitHub repository JOINCLASS/ai-ceo-framework (50 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 1,001 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 2026-08-30.