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 ur-grue/autopunk-media-skills --skill copyright-holder-findergit clone --depth 1 https://github.com/ur-grue/autopunk-media-skillsWrote 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/ur-grue/autopunk-media-skills/copyright-holder-finder)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/copyright-holder-finder"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/copyright-holder-finder/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/ur-grue/autopunk-media-skills/copyright-holder-finder"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/copyright-holder-finder.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 | $0.00044 | $0.02187 |
| Opus 5.5 | $0.00018 | $0.00875 |
| Sonnet 5.5 | $0.00009 | $0.00437 |
| Haiku 4.5 | $0.00004 | $0.00219 |
Grade A, and why
copyright-holder-finder 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 1mo 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copyright Holder Finder
What This Skill Does
Produces a step-by-step research plan for identifying the copyright holder of a specific piece of content — image, footage, text, music, or other media — tailored to the content type and jurisdiction.
When To Use This Skill
- You want to license an image, clip, or music track but cannot identify who owns the rights
- You found archival footage or a photograph with no clear attribution and need to clear it for use
- You are producing a documentary or article and need to trace rights holders for third-party material
- You need to determine whether a work is orphaned (no identifiable rights holder) before applying fair use or other exceptions
What You Need To Provide
Required:
- A description of the content you are trying to clear (what it is, where you found it, any identifying details — title, creator name, date, publication, watermark, metadata)
- The content type (photograph, video footage, music recording, text excerpt, illustration, etc.)
Optional:
- The jurisdiction you are working in (affects which registries and legal frameworks apply)
- What you already know about the provenance (e.g., "published in a magazine in the 1990s but no photographer credit," "found on a stock site with no licensing information")
- Your intended use (editorial, commercial, broadcast, online-only — this affects which rights you need to clear)
- Any deadline pressure (some research steps take weeks; knowing your timeline helps prioritise)
How the Assistant Approaches This
-
Assesses what is already known. Before proposing research steps, the assistant inventories the identifying information you have — creator name, publication, date, metadata, watermarks, reverse image search results — to determine how close you already are to an answer and which gaps remain.
-
Builds a research plan specific to the content type. The path to a copyright holder differs by medium: photographs route through image agencies, photographer registries, and publication archives; music routes through performing rights organisations, mechanical rights databases, and publisher catalogues; text routes through publishers, literary agents, and copyright registration databases. The assistant selects the relevant path and provides specific registries, databases, and organisations to contact.
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.
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.
- 1mo ago First seen · 115 lines · 44 tokens per session scan A bff7ca8d5be4
copyright-holder-finder is a skill published in the GitHub repository ur-grue/autopunk-media-skills (38 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 2,187 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
ip-trademark
Use when a non-lawyer operator needs to protect a brand or creative work — clearing and choosing a name or logo, deciding whether and where to register a trademark, using the trademark and registered symbols correctly, knowing what copyright is automatic, or checking whether they own work a freelancer was paid for.…
DMCA Takedown
Use when preparing a takedown notice for infringing content or evaluating a takedown notice received against the user's content, including whether a counter-notice may be appropriate.
Open Source License Review
Use when reviewing the open-source licenses present in or proposed for a project to identify compliance obligations and flag compatibility or disclosure risks for attorney review.
klauselinhalt-und-verbote-pruefen
Prüft eine AGB-Klausel anhand von Kontrollfähigkeit, gesetzlichen Klauselverboten und Interessenabwägung. Für B2C und B2B; liefert ein Klauselvotum mit Leitbild, Gegenposition und konkreter Rechtsfolge.
write-outreach-outreach-qa
Step of the write-outreach playbook: the checks a finished outreach pack and send file must pass before delivery, covering facts, proof, compliance, length, asks and tone. Run write-outreach instead; not for direct use.
delay-analysis
Analyze construction schedule delays for claims and recovery. Perform time impact analysis, identify delay causes, calculate damages, and document for disputes.