overcast-copycat-sweep

overcast-copycat-sweep is a skill for Claude Code from kdr/overcast. It costs 49 tokens per session (1,583 once invoked), scanned A, original, Apache-2.0.

A media-investigation skill for finding copied, re-uploaded, or altered versions of a creator’s videos across X, YouTube, and TikTok.

In plain words
What is it for?
Use it to fingerprint an original video, search for later candidate copies, compare their frames, faces, and transcripts, and create an evidence-backed copycat report.
Why use it?
Exact file matching can miss videos that have been resized, edited, or otherwise changed. It compares visual frames, faces, and spoken transcripts, escalating the checks as needed and producing findings that can be cited.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the overcast plugin — 35 skills, 1 hook shipped together

Good fit Use it to fingerprint an original video, search for later candidate copies, compare their frames, faces, and transcripts, and create an evidence-backed copycat report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kdr/overcast/overcast-copycat-sweep
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 kdr/overcast --skill overcast-copycat-sweep
Clone the repo
git clone --depth 1 https://github.com/kdr/overcast

Made for: Claude Code.

Or install overcast, the plugin that ships this one along with the rest of its 35 skills, 1 hook.

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 overcast-copycat-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/kdr/overcast/overcast-copycat-sweep/github.svg)](https://agentmods.dev/skills/kdr/overcast/overcast-copycat-sweep)
Your own site
<a href="https://agentmods.dev/skills/kdr/overcast/overcast-copycat-sweep"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-copycat-sweep/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 overcast-copycat-sweep

Your own site · 80×15
<a href="https://agentmods.dev/skills/kdr/overcast/overcast-copycat-sweep"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-copycat-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,583 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
  • NVIDIA SkillSpector pass 7 Sept 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.01583
Opus 5 $0.00024 $0.00792
Sonnet 5 $0.00010 $0.00317
Haiku 4.5 $0.00005 $0.00158

Measured 9d ago against content hash b7a5dc7b52bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

overcast-copycat-sweep 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 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.

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/overcast-copycat-sweep/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.

overcast-copycat-sweep

Use this skill when the task is to find copies, re-uploads, or reskins of a creator's original media (video theft / freebooting) and build an evidence-backed report. Use the broad overcast skill and overcast/reference/verbs.md for exact flags. Escalate tier by tier — never capture what metadata already rules out.

Workflow

  1. Fingerprint the original (once per case). Reskins defeat exact hashes, so fingerprint three ways — distinctive frames, the creator's face, and the transcript:
overcast doctor --sources --json
overcast case init --json
overcast case setup --name copycat-sweep --target "<creator / original title>" --source "x:video:<topic keywords>" --yes --no-index --json
overcast watch ./original.mp4 --json      # content + transcript into case memory
overcast index create originals --type image-ransac --local --json
overcast image add ./title-card.png --index <index-id> --json   # + diagrams, key frames
  1. Sweep sources for candidates published AFTER the original — media-targeted (x:video:) queries with topic keywords, not exact titles:
overcast source add 'youtube:search:<topic keywords>' --json
overcast scan --since <original-publish-date> --limit 20 --json
  1. Triage on scan metadata alone (no downloads): keep hits whose published postdates the original, whose duration is close to it, or whose title/snippet echoes it; carry author and views into the report.

  2. Escalate survivors — capture, then match every fingerprint layer:

overcast capture <scan-hit-id> --json
overcast image match <captured-file> --index <index-id> --draw --json   # frames survive reskins/subtitles; --draw writes match-overlay proof
overcast face <captured-file> --match ./creator.jpg --json   # the face survives re-branding
overcast listen <captured-file> --json                       # verbatim transcript = strongest signal
overcast ask "does this captured video repeat the original's content? cite moments" --json

Read the full file on GitHub · 121 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. 9d ago First seen · 121 lines · 49 tokens per session scan A b7a5dc7b52bb

Subscribe to this mod's changes

overcast-copycat-sweep is a skill published in the GitHub repository kdr/overcast (16 stars, last pushed 6d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,583 once invoked, about $0.0002 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.