What is media-search?

A search procedure for finding movie information through TMDb and music-release information through Discogs.

Use it to look up movie titles, release years, TMDb IDs, music releases, artists, years, and Discogs IDs.

It helps identify the correct film or album and find its external ID before adding it to a collection.

How pdugan20/rewind configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to pdugan20/rewind. 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/pdugan20/rewind/main/.agents/skills/media-search/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/pdugan20/rewind

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pdugan20/rewind/media-search/github.svg)](https://agentmods.dev/skills/pdugan20/rewind/media-search)

Your own site

<a href="https://agentmods.dev/skills/pdugan20/rewind/media-search"><img src="https://agentmods.dev/badge/skills/pdugan20/rewind/media-search/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/pdugan20/rewind/media-search"><img src="https://agentmods.dev/badge/skills/pdugan20/rewind/media-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 550 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00075	$0.00550
Opus 5	$0.00037	$0.00275
Sonnet 5	$0.00015	$0.00110
Haiku 4.5	$0.00007	$0.00055

Measured 9d ago against content hash 75c6bd587526, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

media-search scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://api.themoviedb.org/3/search/movie?query=<title>&language=en-US" \

.agents/skills/media-search/SKILL.md · 58 lines

What it actually says

Media Search

Search TMDb (movies) and Discogs (music releases) to find metadata and IDs. Useful for disambiguation before adding items to the collection, or for quick lookups.

Setup

Read API keys from .dev.vars:

TMDB_API_KEY -- for movie searches (used as Bearer token)
DISCOGS_PERSONAL_TOKEN -- for music searches (used as Discogs token=<value>)

Movie Search (TMDb)

curl -s "https://api.themoviedb.org/3/search/movie?query=<title>&language=en-US" \
  -H "Authorization: Bearer <TMDB_API_KEY>"

Add &year=<year> to narrow results. If the year filter returns nothing, retry without it.

Display results as a table: TMDb ID, title, release date. For detailed info on a specific movie:

curl -s "https://api.themoviedb.org/3/movie/<tmdb_id>?language=en-US" \
  -H "Authorization: Bearer <TMDB_API_KEY>"

Music Search (Discogs)

curl -s "https://api.discogs.com/database/search?q=<query>&type=release&per_page=10" \
  -H "Authorization: Discogs token=<DISCOGS_PERSONAL_TOKEN>" \
  -H "User-Agent: RewindAPI/1.0"

Add &artist=<artist> and/or &year=<year> to narrow results.

Display results as a table: Discogs ID, title (includes artist), year, format, country. For detailed info:

curl -s "https://api.discogs.com/releases/<discogs_id>" \
  -H "Authorization: Discogs token=<DISCOGS_PERSONAL_TOKEN>" \
  -H "User-Agent: RewindAPI/1.0"

Usage

Determine the search domain from context:

Mentions of director, actor, Blu-ray, or clearly a film -> TMDb
Mentions of artist, band, album, vinyl, LP, CD -> Discogs
If unclear, search both and present results grouped by domain

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.

9d ago First seen · 58 lines · 75 tokens per session scan A 75c6bd587526

Subscribe to this mod's changes

media-search is a skill published in the GitHub repository pdugan20/rewind (5 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 550 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and media cloudflare cloudflare-workers d1 drizzle-orm hono r2

hono-cloudflare

Hono on Cloudflare Workers - bindings, KV, D1, R2, Durable Objects, and edge deployment patterns.

bobmatnyc/claude-mpm-skills · 29 tokens

cloudflare

Use when working on Cloudflare's edge platform — wrangler.jsonc bindings, choosing between D1/KV/R2/Durable Objects/Queues, deploying a Worker or SPA via Static Assets, or designing around a Workers runtime limit. NOT generic CI/release (that is deployment), NOT Next.js framework wiring (that is nextjs), NOT DNS…

ericrisco/rsc-harness · 86 tokens

hello-site

Reproduce a Davflare static site with existing MCP tools only (publishsite / imageupload). Use when onboarding or demoing “chat → site”.

fanchenggang/Davflare · 33 tokens

ui-and-theme

Frontend/design system skill for the svelteflare monorepo. Use this whenever the user wants to build or modify UI — pages, sections, components, layouts, forms, cards, tables, dialogs, dashboards, or landing pages. Also invoke for anything theme-related: light/dark mode, custom colors, design tokens, typography, or…

pinebasedev/svelteflare · 159 tokens

auth-db-billing

Backend product systems skill for the svelteflare monorepo. Invoke whenever the user wants to work with auth, sessions, protected routes, users, the database, schema changes, migrations, Stripe billing, subscriptions, paid feature gates, or any server-only logic in the Hono API. Trigger on "add a protected route"…

pinebasedev/svelteflare · 172 tokens

build-feature

Main orchestration skill for adding features to the svelteflare monorepo. Invoke whenever the user wants to add, build, implement, or create any new functionality — a page, API endpoint, DB table, form, component, auth-gated route, billing feature, or any combination. Trigger on "add X", "build X", "implement X", "I…

pinebasedev/svelteflare · 132 tokens

rewind: Skill for Claude Code