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 footnotes-formattergit 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/footnotes-formatter)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/footnotes-formatter"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/footnotes-formatter/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/footnotes-formatter"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/footnotes-formatter.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 | $0.00038 | $0.01212 |
| Opus 5 | $0.00019 | $0.00606 |
| Sonnet 5 | $0.00008 | $0.00242 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
footnotes-formatter 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 7d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Footnotes Formatter
What This Skill Does
Takes a list of messy, inconsistent, or unnumbered notes and references and returns them correctly numbered, consistently formatted, and matched to your chosen citation style.
When To Use This Skill
- A long-form article, investigation, or documentary treatment has source notes in varying formats that need standardising before publication
- A reporter has pasted their references in a mix of formats (some Chicago, some URLs only, some bare hyperlinks) and you need them uniform
- You are preparing a grant application, fund pitch, or academic-adjacent journalism piece that requires a specific citation style
- Endnotes from a Word document have lost their numbering and need to be reconstructed
What You Need To Provide
Required:
- The raw footnotes or endnotes, in whatever state they are in (pasted as a list, one per line, or as a block of text)
- The citation style you want: choose one — Chicago (author-date or notes-bibliography), AP, MLA, APA, or "house style" (if house style, describe the format you want)
Optional:
- The text of the article or document so the assistant can check that in-text reference numbers match the notes list
- Whether these are footnotes (at the bottom of each page) or endnotes (collected at the end) — affects labelling only, not formatting
- Any special rules: e.g., "shorten URLs," "do not include access dates," "use 'ibid' for repeated consecutive sources"
How the Assistant Approaches This
- Reads all the raw notes and identifies each distinct source, stripping duplicates and flagging any entry that is missing information required by the chosen style (e.g., a publisher name, a publication date)
- Applies the chosen citation format consistently: order of elements, punctuation, italics conventions, and abbreviation rules for that style
- Numbers the final list sequentially from 1 and returns the formatted block, with a brief note at the end listing any entries where required information was missing or had to be inferred
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.
- 7d ago First seen · 79 lines · 38 tokens per session scan A 52ddac2ce750
footnotes-formatter is a skill published in the GitHub repository ur-grue/autopunk-media-skills (30 stars, last pushed 11d ago), licensed MIT. It adds 38 tokens to every session and 1,212 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 2026-09-04.
Other skills, from other repositories
sources-section
Appends a Sources/References section using only web sources from the sources pool.
grounded-copy
Write clear prose using concrete facts. Use when writing, editing, translating, or reviewing text that people read, including chat replies, documentation, product copy, reports, commit messages, and code comments. Also use when asked to check copy or remove AI clichés. Preserve supplied facts and follow the user's…
xiaoyuzhou-podcast-notes
A workflow that turns a public Xiaoyuzhou FM podcast episode into structured Markdown notes and a saved transcript. Xiaoyuzhou FM is a Chinese podcast platform.
legwork
Use when the user needs research that settles a decision - market validation, build-or-buy, competitor and pricing scans, "is there demand for X", "where should we publish this", "what does the incumbent actually do". Produces a cited findings memo or report where every claim states how well it is supported. Triggers…
c-research
Summarize web URLs, PDFs, YouTube videos, and podcasts using the summarize CLI. Instantly extract key points from any content type without manual reading. Useful for research, link digests, and media review.
Citation Manager
Manage bibliographies, citations, and academic references in multiple formats.