What is toutiao-publisher?

A tool for preparing and publishing articles on Toutiao, a Chinese news and content platform. It can also check login status and fill drafts with text, inline images, and cover images.

Use it to check or restore access, prepare Markdown drafts, upload article images and covers, and publish approved content.

It reduces the manual work of moving an article into Toutiao while keeping final publishing under manual review unless automatic publishing is explicitly approved.

toutiao-publisher — Skill for Claude Code by guanyang

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.

Any agent

npx skills add guanyang/super-publisher --skill toutiao-publisher

Clone the repo

git clone --depth 1 https://github.com/guanyang/super-publisher

Made for: Claude Code.

Or install super-publisher, the plugin that ships this one along with the rest of its 10 skills.

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/skills/guanyang/super-publisher/toutiao-publisher/github.svg)](https://agentmods.dev/skills/guanyang/super-publisher/toutiao-publisher)

Your own site

<a href="https://agentmods.dev/skills/guanyang/super-publisher/toutiao-publisher"><img src="https://agentmods.dev/badge/skills/guanyang/super-publisher/toutiao-publisher/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/skills/guanyang/super-publisher/toutiao-publisher"><img src="https://agentmods.dev/badge/skills/guanyang/super-publisher/toutiao-publisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,012 The whole file, excluding the scripts and references it only reads on demand.

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

Socket pass 18 Mar 2026
Snyk warn 15 Feb 2026

How audits are shown

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	$0.00073	$0.01012
Opus 5	$0.00036	$0.00506
Sonnet 5	$0.00015	$0.00202
Haiku 4.5	$0.00007	$0.00101

Measured 13d ago against content hash 3d2618ef38bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

toutiao-publisher 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 13d ago.

The scan reads SKILL.md. This mod also ships 17 executable files (scripts/auth_manager.py, scripts/browser_utils.py, scripts/cli_utils.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/toutiao-publisher/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Toutiao Publisher

Use the scripts from this Skill directory. Resolve the directory containing this SKILL.md first and set its absolute path as SKILL_DIR; do not assume the caller's working directory is the Skill directory.

Safety rules

Default to --mode manual. Leave Chrome open for the user to review and click Publish.
Use --mode auto only when the user explicitly authorizes final publishing.
Run clear --yes or reauth --yes only after the user confirms that all local Agents may lose the shared Toutiao session.
Do not bypass input validation or treat an unconfirmed publish click as success.

Preflight authentication

Check the protected Toutiao page before asking the user to scan a QR code:

python3 "$SKILL_DIR/scripts/run.py" auth_manager.py status --verify --json

If the result status is not_authenticated, open the interactive login flow:

python3 "$SKILL_DIR/scripts/run.py" auth_manager.py setup --json

The shared profile lives under ~/.super-publisher/toutiao-publisher/ by default. Codex, Kiro, Antigravity, and direct CLI runs by the same system user reuse it. Set SUPER_PUBLISHER_DATA_DIR to override the location; relative values resolve from the user home directory.

Prepare and publish an article

Validate inputs without opening Chrome:

python3 "$SKILL_DIR/scripts/run.py" publisher.py \
  --mode validate \
  --title "AI Trends 2026" \
  --content-file "/absolute/path/article.md" \
  --cover "/absolute/path/cover.jpg" \
  --json

After validation succeeds, fill the draft and wait for manual review:

python3 "$SKILL_DIR/scripts/run.py" publisher.py \
  --mode manual \
  --title "AI Trends 2026" \
  --content-file "/absolute/path/article.md" \
  --cover "/absolute/path/cover.jpg" \
  --json

Use direct text only through --content-text. --content remains an alias for --content-file; a missing path is an error rather than literal article text.

Markdown supports headings, links, ordered and unordered lists, block quotes, tables, fenced code, inline code, emphasis, and local inline images. Resolve relative image paths from the Markdown file. If the body contains images, skip explicit cover upload. Use --no-cover only when the body has no image and no cover is supplied.

Read the full file on GitHub · 121 lines

Files

What ships with it

19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

13d ago First seen · 121 lines · 73 tokens per session scan A 3d2618ef38bc

Subscribe to this mod's changes

toutiao-publisher is a skill published in the GitHub repository guanyang/super-publisher (30 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,012 once invoked, about $0.0004 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.

Writing and docs agent agentic-ai ai-skills automated-publishing skills toutiao-publisher

agent-coverage-check

Check agent configuration coverage across hierarchy levels and phases. Use to ensure complete agent system coverage.

majiayu000/claude-skill-registry · 23 tokens

skillpack-creator

Create a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off research, coding, analysis, or content workflow into a distributable local SkillPack with skillpack.json, local skills under skills/, starter prompts, start scripts, and an optional zip package.

CreminiAI/skillpack · 67 tokens

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

CreminiAI/skillpack · 64 tokens

pdf

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When GLM needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

jjyaoao/HelloAgents · 51 tokens

frontend-design

Transform UI style requirements into production-ready frontend code with systematic design tokens, accessibility compliance, and creative execution. Use when building websites, web applications, React/Vue components, dashboards, landing pages, or any web UI requiring both design consistency and aesthetic quality.

jjyaoao/HelloAgents · 54 tokens

Video Generation

Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result…

jjyaoao/HelloAgents · 58 tokens