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.
npx skills add kdr/overcast --skill overcast-copycat-sweepgit clone --depth 1 https://github.com/kdr/overcastWrote 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.
[](https://agentmods.dev/skills/kdr/overcast/overcast-copycat-sweep)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.01583 |
| Opus 5 | $0.00024 | $0.00792 |
| Sonnet 5 | $0.00010 | $0.00317 |
| Haiku 4.5 | $0.00005 | $0.00158 |
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.
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
- 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
- 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
-
Triage on scan metadata alone (no downloads): keep hits whose
publishedpostdates the original, whosedurationis close to it, or whosetitle/snippetechoes it; carryauthorandviewsinto the report. -
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
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 · 121 lines · 49 tokens per session scan A b7a5dc7b52bb
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.
Other skills, from other repositories
frame-data-chart-nyt
NYT-newsroom typography, staggered reveal animation, and editorial-grade charts (line, bar, or range band).
frame-flowchart-sticky
SVG curve connectors, sticky-note nodes, and cursor interaction with a whiteboard-brainstorm feel.
frame-glitch-title
Digital glitch, chromatic offset, and data-corruption title frame for video transitions or cyberpunk heroes.
frame-light-leak-cinema
Film light leaks, grain, 16:9 letterbox, and large serif type for cinematic openings or chapter cards.
frame-logo-outro
Segmented logo assembly, glow bloom, and tagline reveal for video outros or brand closing frames.
vfx-text-cursor
Cursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.