agentmods.dev

mediacrawler-collector

mediacrawler-collector is a skill for Codex from xwh-01/dsh-mediacrawler. It costs 80 tokens per session (1,039 once invoked), scanned A, original, MIT.

A skill for bounded, repeatable collection of posts, creator pages, and comments from Xiaohongshu, Douyin, Kuaishou, Bilibili, Weibo, Tieba, and Zhihu through a separately installed MediaCrawler checkout. It supports searches, individual post or video details, and creator pages.

In plain words
What is it for?
Use it to collect up to a controlled number of search results, posts or videos, creator feeds, first-level comments, and nested comments from the supported platforms, then inspect and export the results.
Why use it?
It provides a defined collection process for gathering original platform records and saving a credential-redacted archive, while keeping the scope limited. It distinguishes larger collection jobs from quick fact-finding, which should use ordinary web search.

Skill for Codex

Written for Codex: agents/openai.yaml present.

not rated 3repo 28d ago A scan 80 tokens original MIT

Good fit Use it to collect up to a controlled number of search results, posts or videos, creator feeds, first-level comments, and nested comments from the supported platforms, then inspect and export the results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xwh-01/dsh-mediacrawler/mediacrawler-collector
View source ↗ xwh-01/dsh-mediacrawler
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 xwh-01/dsh-mediacrawler --skill mediacrawler-collector
Clone the repo
git clone --depth 1 https://github.com/xwh-01/dsh-mediacrawler

Made for: Codex.

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.

agentmods badge for mediacrawler-collector

README.md
[![agentmods](https://agentmods.dev/badge/skills/xwh-01/dsh-mediacrawler/mediacrawler-collector/github.svg)](https://agentmods.dev/skills/xwh-01/dsh-mediacrawler/mediacrawler-collector)
Your own site
<a href="https://agentmods.dev/skills/xwh-01/dsh-mediacrawler/mediacrawler-collector"><img src="https://agentmods.dev/badge/skills/xwh-01/dsh-mediacrawler/mediacrawler-collector/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.

agentmods 80×15 button for mediacrawler-collector

Your own site · 80×15
<a href="https://agentmods.dev/skills/xwh-01/dsh-mediacrawler/mediacrawler-collector"><img src="https://agentmods.dev/badge/skills/xwh-01/dsh-mediacrawler/mediacrawler-collector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,039 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.
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 5.1 $0.00080 $0.01039
Opus 5 $0.00040 $0.00519
Sonnet 5 $0.00016 $0.00208
Haiku 4.5 $0.00008 $0.00104

Measured 11d ago against content hash ea72b2f2fab8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mediacrawler-collector 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 11d 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.

.dsh/skills/mediacrawler-collector/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MediaCrawler Collector

Use the mediacrawler MCP tools to run one isolated collection job, inspect its results, and export a credential-redacted archive.

Choose The Right Tool

Use this skill when the request needs original platform records, creator feeds, several posts, comments, nested comments, or a durable collection artifact. Use ordinary web search when the user only needs a quick answer, current fact, or a few indexed pages.

Supported platform values are xhs, dy, ks, bili, wb, tieba, and zhihu. Supported modes are:

  • search: provide query; do not provide targets.
  • detail: provide post or video URLs/IDs in targets; do not provide query.
  • creator: provide creator URLs/IDs in targets; do not provide query.

Workflow

If the user refers to an earlier run but no run_id is available in context, call mcp__mediacrawler__runs and identify the run from its platform, mode, query or targets, and timestamps.

  1. Call mcp__mediacrawler__check. Use deep=true on first use, after an upstream upgrade, or when a run fails before login.
  2. Call mcp__mediacrawler__collect with the smallest useful scope. Start with at most 20 items, keep include_comments=false unless the user explicitly needs comments, and use browser_mode=isolated.
  3. Preserve the returned run_id. Tell the user when they must complete QR-code verification in the browser opened by MediaCrawler.
  4. Poll mcp__mediacrawler__status after the returned interval. When phase=awaiting_user_login, tell the user to scan the QR code in the isolated browser, then keep polling the same run_id. Do not start a second run while one is active.
  5. Read mcp__mediacrawler__logs only when login is waiting, progress appears stuck, or the run fails. Continue from next_cursor.
  6. When complete, call mcp__mediacrawler__result for status, artifacts, and the first useful redacted records in one response. Use its record_type filter when the user specifically needs comments or creator records; use preview only for additional pages or another artifact.
  7. Call mcp__mediacrawler__export when the user needs a durable credential-redacted ZIP. State that it is not PII-anonymized and is not automatically safe to share.

Read the full file on GitHub · 56 lines

Files

What ships with it

1 file 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.

  1. 11d ago First seen · 56 lines · 80 tokens per session scan A ea72b2f2fab8

Subscribe to this mod's changes

mediacrawler-collector is a skill published in the GitHub repository xwh-01/dsh-mediacrawler (3 stars, last pushed 28d ago), licensed MIT. It adds 80 tokens to every session and 1,039 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 2026-08-31.

Browser automationResearchdeepseek-harnessdsh-pluginmcpmediacrawlerweb-crawler
Related

Other skills, from other repositories

agent-first-screenshots

Agent-first screenshots — an agent drives the real app via CDP and produces clean, defect-free product screenshots (newsletters, landing pages, social, decks, PR). Dual-channel verification (DOM + pixels + vision) in a capture loop. Use for any "take/redo screenshots of the app" task.

Devin-AXIS/iPolloWork · 69 tokens

daytona-chrome-cdp

Launch and control standalone Chrome in a Daytona sandbox via CDP. Use for web sign-in, OAuth, Den Web setup, browser-only flows, or when the app should not be driven through Electron CDP.

Devin-AXIS/iPolloWork · 49 tokens

bilibili-keywords-search

A search tool for finding newly published videos on Bilibili, a Chinese video-sharing platform, by keyword. It can sort results, limit them by publication date, and show additional result pages.

redfox-data/redfox-community-dsh · 95 tokens

wechat-video-downloader

A video-link parser for WeChat Channels, WeChat's short-video platform. Give it a shared video link to receive the title, cover image, and a temporary direct link to the original video without a watermark.

redfox-data/redfox-community-dsh · 77 tokens

control-chrome-cdp

Start or control one exact existing Chrome profile through the Agent OS Chrome CDP bridge with Codex-compatible browser operations. Use for tasks that depend on logged-in Chrome state, including when no Chrome window is open, background tab control, raw CDP, screenshots, page-exposed media saving, or page File…

bpc-oss/chrome-faithful · 95 tokens

browser-cdp

Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP…

zenstory-ai/oh-story-dsh · 94 tokens