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 cms-metadata-taggergit 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/cms-metadata-tagger)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/cms-metadata-tagger"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/cms-metadata-tagger/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/cms-metadata-tagger"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/cms-metadata-tagger.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 | $0.01471 |
| Opus 5 | $0.00024 | $0.00736 |
| Sonnet 5 | $0.00010 | $0.00294 |
| Haiku 4.5 | $0.00005 | $0.00147 |
Grade A, and why
cms-metadata-tagger 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 12d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CMS Metadata Tagger
What This Skill Does
Takes a finished piece of content and produces a complete, archive-ready metadata record — including descriptive tags, subject classifications, rights notes, and an archival summary — for entry into a content management or digital archive system.
When To Use This Skill
- A piece has been published and needs to be formally archived with consistent metadata for long-term retrieval
- Your archive team is cataloguing a backlog of published content and needs metadata generated at volume
- You are migrating content between systems and need a metadata record that works for the destination archive structure
- A piece contains legally sensitive elements (third-party images, named individuals, licensed data) and needs rights and restrictions noted in the archive record before the file is stored
What You Need To Provide
Required:
- The full text or a detailed summary of the finished piece
- Content type (news article, feature, opinion column, video script, audio transcript, photo essay, social post series)
- Publication date
Optional:
- Named individuals, organisations, or locations that must appear in the record
- Rights or licensing information (image credits, wire service content, licensed data sources)
- Any restrictions on reuse (e.g. "not for republication", "interview subject requested anonymity in byline", "embargoed material — cleared for archive only")
- Your archive's controlled vocabulary or subject taxonomy — paste it so the assistant uses your terms rather than its own
- Internal reference number or file ID if you want it included in the record
How the Assistant Approaches This
- Reads the content and extracts the primary subject, secondary subjects, named entities (people, places, organisations, events), and content format. Notes any elements with potential rights or legal implications mentioned in what you provide.
- Drafts a short archival summary (distinct from a publish-facing standfirst) written for internal retrieval — factual, dateline-style, without promotional language.
- Assembles the full metadata record in a field-by-field format. If a controlled vocabulary was provided, all subject tags are drawn from it. Rights and restriction fields are populated with whatever you have supplied; if none was supplied, the field is flagged as requiring manual entry rather than left blank silently.
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.
- 12d ago First seen · 100 lines · 49 tokens per session scan A c704f26d7ddc
cms-metadata-tagger is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 11d ago), licensed MIT. It adds 49 tokens to every session and 1,471 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sf-metadata-parser
Use this skill whenever the user wants to parse, analyze, document, or export SAP SuccessFactors OData metadata ($metadata XML). Triggers include: any mention of 'metadata', '$metadata', 'OData entities', 'entity fields', 'SF metadata', 'SuccessFactors schema', 'data dictionary', or requests to understand, compare, or…
treatment-plans
Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
xlsx
Create, edit, analyze, or convert Excel spreadsheets (.xlsx, .xlsm, .xltx) where the workbook file is the primary deliverable. Use for formulas, formatting, financial models, multi-sheet workbooks, and tabular cleanup exported to Excel. Also applies to .csv/.tsv when the user wants spreadsheet output. Do NOT use for…
outline
Search, read, and manage Outline wiki documents. Use when: (1) searching wiki for documentation, (2) reading wiki pages or articles, (3) listing wiki collections or documents, (4) creating or updating wiki content, (5) exporting documents as markdown. Works with any Outline wiki instance (self-hosted or cloud).
google-sheets
Read and write Google Sheets spreadsheets - get content, update cells, append rows, fetch specific ranges, search for spreadsheets, and view metadata. Use when user asks to: read a spreadsheet, update cells, add data to Google Sheets, find a spreadsheet, check sheet contents, export spreadsheet data, or get cell…
google-slides
Read and write Google Slides presentations - get text, find presentations, create presentations, add slides, replace text, and manage slide content. Use when user asks to: read a presentation, create slides, find slides, add a slide, replace text in a presentation, or manage presentation content. Lightweight…