paper.fix_figures

paper.fix_figures is a skill for Claude Code from gpsaggese/helpers. It costs 17 tokens per session (595 once invoked), scanned A, original, Apache-2.0.

A LaTeX paper figure editor that adds captions, labels, and text references to figures and tables. LaTeX is a markup system used to prepare technical documents.

In plain words
What is it for?
Use it to add or repair captions and labels for figures in a paper, and to ensure every figure and table is referenced in the text.
Why use it?
It makes figures identifiable and ensures the paper explains and refers to each visual element.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to add or repair captions and labels for figures in a paper, and to ensure every figure and table is referenced in the text.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gpsaggese/helpers/paper.fix_figures
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 gpsaggese/helpers --skill paper.fix_figures
Clone the repo
git clone --depth 1 https://github.com/gpsaggese/helpers

Made for: Claude Code.

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 paper.fix_figures

README.md
[![agentmods](https://agentmods.dev/badge/skills/gpsaggese/helpers/paper.fix_figures/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/paper.fix_figures)
Your own site
<a href="https://agentmods.dev/skills/gpsaggese/helpers/paper.fix_figures"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/paper.fix_figures/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 paper.fix_figures

Your own site · 80×15
<a href="https://agentmods.dev/skills/gpsaggese/helpers/paper.fix_figures"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/paper.fix_figures.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 595 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.
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 $0.00017 $0.00595
Opus 5.5 $0.00007 $0.00238
Sonnet 5.5 $0.00003 $0.00119
Haiku 4.5 $0.00002 $0.00060

Measured yesterday against content hash 36894f2353c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

paper.fix_figures 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 yesterday.

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.

.claude/skills/paper.fix_figures/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.

Check References

  • Every picture and table needs a label and a caption, and must be referenced in the text
  • Captions should only say what is done. Comments and other content go in the text

Add Captions and Labels

  • For all figures in the LaTeX files in the passed dir, add the caption and label to the commented section.

  • For instance convert

    %     ```
    % rendered_images:end
    % render_images:begin
    \begin{figure}[!ht]
      \centering
      \includegraphics[width=\linewidth]{figs/02_architecture.1.png}
      \caption{Confounding adjustment in causal inference}
      \label{fig:confounding_adjustment}
    \end{figure}
    % render_images:end
    

    to

    %     ```
    % caption=Confounding adjustment in causal inference
    % label=fig:confounding_adjustment
    % rendered_images:end
    % render_images:begin
    \begin{figure}[!ht]
      \centering
      \includegraphics[width=\linewidth]{figs/02_architecture.1.png}
      \caption{Confounding adjustment in causal inference}
      \label{fig:confounding_adjustment}
    \end{figure}
    % render_images:end
    

Create Labels and Captions From Scratch

  • If a figure has no caption or label, infer them from the filename and surrounding context
    • E.g., figs/02_architecture.1.png becomes label=fig:architecture, caption=System architecture overview
  • Use short, lowercase label names with underscores

Add References in the Text

  • If a figure has a label but no citation in the text, add a parenthetical reference near the most relevant paragraph:
    (see Fig.~\ref{fig:confounding_adjustment})
    

Verify No Orphaned References

  • Scan the text for \ref{fig:xxx} or \ref{tab:xxx} with no matching \label in any figure or table environment
  • Report orphaned references as warnings. Do not silently delete them

Verification

  • Every figure and table has a \label and a \caption
  • Every figure and table \label is referenced by a \ref in the text
  • No orphaned \ref{fig:xxx} or \ref{tab:xxx} exists without a matching \label in any figure or table environment

Read the full file on GitHub · 76 lines

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. yesterday First seen · 76 lines · 17 tokens per session scan A 36894f2353c9

Subscribe to this mod's changes

paper.fix_figures is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 595 once invoked, about $0.0001 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 2026-11-06.

Related

paper.fix_figures compared with skills from other repositories

paper.fix_figures next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
paper.fix_figuresgpsaggese/helpersSkill158todayApache-2.0A17Claude Code
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill35ktodayApache-2.0A123Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skillsSkill56k5d agoMITA83Claude Code
matlabK-Dense-AI/scientific-agent-skillsSkill56k5d agoMITA44Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skillsSkill56k5d agoMITA71Claude Code, Codex
research-engineerdavila7/claude-code-templatesSkill33ktodayMITA43Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmedSkill5.8ktodayApache-2.0A205Claude Code