douban

A tool for exploring Douban, a Chinese website where people rate and review movies, books, music, and television.

In plain words
What is it for?
Use it to find movies and books, inspect creators and cast, read user reviews, view photos, and discover popular or currently showing films.
Why use it?
It avoids manually searching separate media pages and collecting ratings, reviews, and related details yourself.

Skill for Claude CodeCodex

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 skills/imoonkey/openweb/douban
Any agent
npx skills add imoonkey/openweb --skill douban
Clone the repo
git clone --depth 1 https://github.com/imoonkey/openweb

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,127 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 $0.00000 $0.01127
Opus 5 $0.00000 $0.00563
Sonnet 5 $0.00000 $0.00225
Haiku 4.5 $0.00000 $0.00113

Measured 2d ago against content hash a9fbbbf2444a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

douban 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.

The scan reads SKILL.md. This mod also ships 1 executable file (adapters/douban-read.ts), 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.

src/sites/douban/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Douban

Overview

Chinese media review/rating platform (movies, books, music). Social/media archetype — 14 operations across movies, books, music, and discovery via mobile JSON API.

Workflows

Find and explore a movie

  1. searchMovies(q) → pick result → target.id
  2. getMovie(id=target.id) → full detail → rating.value, intro, genres, directors, actors
  3. getMovieCelebrities(id=target.id) → directors[], actors[] with name, character, latin_name
  4. getMovieReviews(id=target.id) → user reviews → comment, rating, user.name, vote_count
  5. getMoviePhotos(id=target.id) → stills, posters → image.large.url, dimensions

Find and explore a book

  1. searchBooks(q) → pick result → target.id
  2. getBook(id=target.id) → full detail → rating.value, intro, author_intro, pubdate
  3. getBookReviews(id=target.id) → user reviews → comment, rating, user.name, vote_count

Discover trending content

  1. getRecentHotMovies() → trending movies → id, title, rating.value
  2. getRecentHotTv() → trending TV shows → id, title, rating.value, episodes_info
  3. getNowShowingMovies() → in-theater movies → id, title, release_date
  4. getTop250(start) → all-time top movies → rank_value, title, rating.value

Find music

  1. searchMusic(q) → pick result → target.id
  2. getMusicDetail(id=target.id) → album detail → title, singer[], songs[], genres[]

Operations

Operation Intent Key Input Key Output Notes
searchMovies search movies q target.id, title, rating.value, year entry point
getMovie movie detail id <- searchMovies/getRecentHotMovies title, rating.value, genres, intro, directors, actors
getMovieReviews movie user reviews id <- searchMovies comment, rating, user.name, vote_count paginated (count, start)
getMovieCelebrities movie cast/crew id <- searchMovies directors[], actors[] with name, character, latin_name
getMoviePhotos movie photo gallery id <- searchMovies photos[].image.large.url, dimensions paginated (count, start)
getTop250 top 250 movies start (optional) rank_value, title, rating.value, id paginated by 25
searchBooks search books q target.id, title, rating.value, card_subtitle entry point
getBook book detail id <- searchBooks title, rating.value, intro, author_intro, pubdate
getBookReviews book user reviews id <- searchBooks comment, rating, user.name, vote_count paginated (count, start)
searchMusic search music q target.id, title, rating.value, card_subtitle entry point
getMusicDetail album detail id <- searchMusic title, singer[], songs[], genres[], pubdate
getRecentHotMovies trending movies limit (optional) id, title, rating.value, year entry point
getRecentHotTv trending TV shows limit (optional) id, title, rating.value, episodes_info entry point
getNowShowingMovies in-theater movies count (optional) id, title, rating.value, release_date entry point

Read the full file on GitHub · 88 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 · 88 lines · 0 tokens per session scan A a9fbbbf2444a

Subscribe to this mod's changes

douban is a skill published in the GitHub repository imoonkey/openweb (58 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,127 tokens. 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.

Related

Other skills, from other repositories

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

baoyu-youtube-transcript

Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…

JimLiu/baoyu-skills · 107 tokens

resolve-rough-cut

Assembling a short-form social rough cut from raw behind-the-scenes or vlog footage in the DaVinci Resolve MCP. Apply when asked for a rough cut, first cut, assembly, or "make me a timeline" from a folder of footage — day-in-the-life, BTS, process, or product-shoot material destined for Reels, TikTok, or Shorts.…

samuelgursky/davinci-resolve-mcp · 97 tokens