What is fanqie-publisher-skill AGENTS.md?

Instructions for publishing prepared novel chapters from local Markdown files to the Fanqie Novel writing website through Playwright, a tool that controls a browser.

Installing dependencies, checking chapter syntax, previewing parsed chapters, reconnecting an author session, filling the editor, and publishing after confirmation.

They define prerequisites, review steps, commands, and text-encoding safeguards, so an agent does not assume browsers, accounts, or dependencies are already available.

How amm10090/fanqie-publisher-skill configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to amm10090/fanqie-publisher-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/amm10090/fanqie-publisher-skill/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/amm10090/fanqie-publisher-skill

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/amm10090/fanqie-publisher-skill/agents-md/github.svg)](https://agentmods.dev/instructions/amm10090/fanqie-publisher-skill/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/amm10090/fanqie-publisher-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/amm10090/fanqie-publisher-skill/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/amm10090/fanqie-publisher-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/amm10090/fanqie-publisher-skill/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,287 This file is loaded in full into every session.

When invoked 1,287 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01287	$0.01287
Opus 5.5	$0.00515	$0.00515
Sonnet 5.5	$0.00257	$0.00257
Haiku 4.5	$0.00129	$0.00129

Measured 2mo ago against content hash 666632fb576e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fanqie-publisher-skill AGENTS.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.

AGENTS.md · 85 lines

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.

fanqie-publisher-skill — Codex CLI Agent Adapter

Publish prepared novel chapters from local Markdown files to the Fanqie Novel writer web backend via browser automation (Playwright).

Read First

All authoritative project definitions and business logic reside in the following shared files. Do not act without reading them:

SKILL.md — full skill definition, commands, safety rules, and publishing flow
references/workflow.md — validated step-by-step publish workflow
references/selectors.md — semantic CSS selectors for Fanqie backend pages
scripts/publish_fanqie.js — the sole publishing entrypoint (read flags, not copy logic)
package.json — dependency: playwright only

Prerequisites

Node.js + npm, Python 3
Chromium/Chrome browser (Playwright-controllable via CDP)
A Fanqie author account with an opened backend session
Run npm install in the repository root before first use

Do not claim that any of these are automatically installed or available.

Entry Points

Action	Command
Syntax checks + editor test	`npm run test:all`
Preview chapter parse	`python3 scripts/prepare_chapters.py --dir "/path/to/chapters" --preview`
Login / reconnect	`npm run login` (or `node scripts/login_fanqie.js --cdp http://127.0.0.1:9222`)
Safe fill-only publish	`node scripts/publish_fanqie.js --cdp http://127.0.0.1:9222 --file "/path/to/chapter.md" --mode immediate --fill-only`
Real publish	Only after explicit user confirmation: use the same reviewed arguments, remove `--fill-only`, and add `--confirm-publish`, e.g. `node scripts/publish_fanqie.js --cdp http://127.0.0.1:9222 --file "/path/to/chapter.md" --mode immediate --confirm-publish`; never combine the two flags

Login requires a manual QR code scan. The login script saves reusable browser storage state locally at state/fanqie-storage-state.json; treat it as sensitive local state, and re-run login when the session expires.

Read the full file on GitHub · 85 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.

2mo ago First seen · 85 lines · 1,287 tokens per session scan A 666632fb576e

Subscribe to this mod's changes

fanqie-publisher-skill AGENTS.md is an instructions file published in the GitHub repository amm10090/fanqie-publisher-skill (24 stars, last pushed 12d ago), licensed MIT. It adds 1,287 tokens to every session, about $0.0051 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.

Browser automation Writing and docs browser-automation fanqie novel-publishing openclaw playwright skill

fanqie-publisher-skill AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fanqie-publisher-skill AGENTS.mdamm10090/fanqie-publisher-skill	Instructions file	24	12d ago	MIT	A	1,287	Codex, OpenCode
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

fanqie-publisher-skill: Instructions file for Codex