data-footnote-writer

data-footnote-writer is a skill for Claude Code from ur-grue/autopunk-media-skills. It costs 46 tokens per session (1,411 once invoked), scanned A, original, MIT.

A writing skill that adds precise footnotes to data claims in a completed article, including sources, calculation details, and important limitations.

In plain words
What is it for?
It is for preparing sourced footnotes or endnotes for journalism, research, policy documents, and other data-heavy writing.
Why use it?
It helps readers and editors check where figures came from and how they were produced. It also highlights caveats that could change how a claim is understood.

Skill for Claude Code

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

Part of the autopunk-media-skills plugin — 187 skills shipped together

Good fit It is for preparing sourced footnotes or endnotes for journalism, research, policy documents, and other data-heavy writing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ur-grue/autopunk-media-skills/data-footnote-writer
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 ur-grue/autopunk-media-skills --skill data-footnote-writer
Clone the repo
git clone --depth 1 https://github.com/ur-grue/autopunk-media-skills

Made for: Claude Code.

Or install autopunk-media-skills, the plugin that ships this one along with the rest of its 187 skills.

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 data-footnote-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/data-footnote-writer/github.svg)](https://agentmods.dev/skills/ur-grue/autopunk-media-skills/data-footnote-writer)
Your own site
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/data-footnote-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/data-footnote-writer/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 data-footnote-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/data-footnote-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/data-footnote-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,411 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 $0.00046 $0.01411
Opus 5 $0.00023 $0.00705
Sonnet 5 $0.00009 $0.00282
Haiku 4.5 $0.00005 $0.00141

Measured 12d ago against content hash c5fae1e7b1d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

data-footnote-writer 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.

skills/data-journalism/publishing/data-footnote-writer/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Footnote Writer

What This Skill Does

Writes precise, publication-standard footnotes for data claims in a finished article — citing sources accurately, explaining how figures were derived where necessary, and flagging any caveats that qualified readers need to know.

When To Use This Skill

  • An article contains data claims that need formal sourcing in footnotes or endnotes
  • An editor or fact-checker has asked for sources to be footnoted before publication
  • You are writing a long-form data feature, annual report, or policy brief where footnoted sourcing is standard
  • You want to ensure every quantitative claim in a piece is traceable to its source

What You Need To Provide

Required: The data claims from the article that need footnotes (the exact sentences or figures). The source for each claim — dataset name, institution, publication date, and URL or file reference. Whether the figure was taken directly from the source or derived through analysis. Optional: The publication format (academic, journalism, policy report) and its citation style if known; any methodological notes that should appear in the footnote rather than the body text.

How the Assistant Approaches This

  1. For each claim, identifies whether the figure is a direct quote from a source or a calculated/derived figure — and adjusts the footnote language accordingly ("Source: X" for direct quotes; "Calculated from X using [method]" for derived figures).
  2. Writes each footnote to the minimum length required for the claim to be reproduced or verified — no padding, no duplication of the body text.
  3. Numbers the footnotes in the order they appear in the article and formats them consistently.

Output Format

Numbered footnotes, one per data claim, formatted as: source information first, then derivation note if applicable, then caveat if applicable. Each footnote is one to three sentences. Consistent citation style throughout. At the end, a complete list of all sources cited.

Quality Criteria

  • Every quantitative claim in the input has a corresponding footnote
  • Footnotes distinguish between direct citations and derived figures
  • Source information is complete: institution, publication name, date, and URL or file reference
  • Derived figures include a brief description of the calculation method
  • No footnote duplicates information already clear from the body text
  • Footnotes are numbered in the order they appear in the article

Read the full file on GitHub · 76 lines

Files

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.

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. 12d ago First seen · 76 lines · 46 tokens per session scan A c5fae1e7b1d4

Subscribe to this mod's changes

data-footnote-writer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 46 tokens to every session and 1,411 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.