rewind: Skill for Claude Code

.agents/skills/add-media/SKILL.md

add-media is a skill for Claude Code, Codex from pdugan20/rewind. It costs 71 tokens per session (944 once invoked), scanned A, original, MIT.

A procedure for adding physical movies and music to the Rewind collection, using TMDb for films and Discogs for music.

In plain words
What is it for?
Use it to add Blu-rays, 4K discs, DVDs, vinyl records, CDs, and cassettes, with movie data synced to Trakt and music added to Discogs.
Why use it?
It turns informal lists or receipts into identified collection items while checking unclear titles and formats.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is pdugan20/rewind's own configuration. It tells Claude Code and Codex how to work on rewind itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rewind configures →

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/add-media/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.

agentmods badge for add-media

README.md
[![agentmods](https://agentmods.dev/badge/skills/pdugan20/rewind/add-media/github.svg)](https://agentmods.dev/skills/pdugan20/rewind/add-media)
Your own site
<a href="https://agentmods.dev/skills/pdugan20/rewind/add-media"><img src="https://agentmods.dev/badge/skills/pdugan20/rewind/add-media/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 add-media

Your own site · 80×15
<a href="https://agentmods.dev/skills/pdugan20/rewind/add-media"><img src="https://agentmods.dev/badge/skills/pdugan20/rewind/add-media.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 944 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.00944
Opus 5 $0.00036 $0.00472
Sonnet 5 $0.00014 $0.00189
Haiku 4.5 $0.00007 $0.00094

Measured 9d ago against content hash 3ef1e26ebbae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

add-media 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 -X POST https://api.rewind.rest/v1/admin/collecting/media \
.agents/skills/add-media/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Physical Media

Add physical media items to the Rewind collection. Supports two domains:

  • Movies (Blu-ray, 4K UHD, DVD) -- resolved via TMDb, synced to Trakt, stored locally
  • Music (Vinyl, CD, Cassette) -- resolved via Discogs, added to Discogs collection, stored locally

Treat a user request that names the items to add as authorization for those exact additions. Otherwise, preview the parsed items and formats and obtain approval before sending any production POST request. Never expose keys from .dev.vars in output.

Setup

Read the admin API key from .dev.vars (the REWIND_ADMIN_KEY line). Read the TMDB_API_KEY line as well for fallback movie searches. All API calls go to https://api.rewind.rest/v1.

Parsing Input

Extract items from freeform input -- pasted order receipts, comma-separated lists, or single items. Strip prices, quantities, and other noise. Identify each item's domain:

  • Movie indicators: Blu-ray, 4K, UHD, DVD, HD-DVD, digital, or obviously a film title
  • Music indicators: vinyl, LP, CD, cassette, record, or obviously an album/artist
  • Ask the user if the domain is unclear

Determine the default format from context. If most items share a format, apply it as the default and only note exceptions.

Adding Movies

Endpoint: POST /admin/collecting/media

curl -s -X POST https://api.rewind.rest/v1/admin/collecting/media \
  -H "Authorization: Bearer <key>" \
  -H "Content-Type: application/json" \
  -d '{"title":"<title>","year":<year>,"media_type":"<format>"}'

Required field: media_type -- one of: bluray, uhd_bluray, dvd, hddvd, digital

Identification (at least one required): tmdb_id, imdb_id, or title (with optional year)

Optional fields: resolution, hdr, audio, audio_channels

Format mapping:

  • "4K UHD", "4K UHD+Blu-ray Combo", "UHD" -> uhd_bluray
  • "Blu-ray" -> bluray
  • "DVD" -> dvd

Handling Ambiguous Matches

When the response returns status: "ambiguous", show the candidates to the user and re-call with tmdb_id. When the matched title looks wrong (different film entirely), fall back to a direct TMDb search. See references/disambiguation.md for the TMDb search pattern.

Read the full file on GitHub · 83 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. 9d ago First seen · 83 lines · 71 tokens per session scan A 3ef1e26ebbae

Subscribe to this mod's changes

add-media is a skill published in the GitHub repository pdugan20/rewind (5 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 944 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.

Related

Other skills, from other repositories

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