papyrus-latex-comments

papyrus-latex-comments is a skill for Claude Code, Codex from kirodotdev/KiroCrew. It costs 80 tokens per session (853 once invoked), scanned A, original, Apache-2.0.

A non-destructive commenting layer for LaTeX documents. It adds visible notes next to text without rewriting the author's content, and the notes can be hidden for the final build.

In plain words
What is it for?
Use it to annotate a .tex file with review notes about specific passages, rather than proposing replacement text.
Why use it?
It separates review remarks from the document itself, so comments can be removed or disabled without changing the writing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to annotate a .tex file with review notes about specific passages, rather than proposing replacement text.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kirodotdev/kirocrew/papyrus-latex-comments
About the project

Kiro Crew is a persistent development workspace where agents continue multi-step software work across sessions, schedules, and connected interfaces. Developers use it locally or remotely through a desktop app, web dashboard, CLI, Slack, or Discord, with unattended tasks and recurring jobs. The catalogue contains skills and instructions for working with this workspace.

kirodotdev/KiroCrew · 3,823 stars · on GitHub · kiro.dev

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 kirodotdev/KiroCrew --skill papyrus-latex-comments
Clone the repo
git clone --depth 1 https://github.com/kirodotdev/KiroCrew

Made for: Claude Code, Codex.

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 papyrus-latex-comments

README.md
[![agentmods](https://agentmods.dev/badge/skills/kirodotdev/kirocrew/papyrus-latex-comments/github.svg)](https://agentmods.dev/skills/kirodotdev/kirocrew/papyrus-latex-comments)
Your own site
<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/papyrus-latex-comments"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/papyrus-latex-comments/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 papyrus-latex-comments

Your own site · 80×15
<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/papyrus-latex-comments"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/papyrus-latex-comments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 853 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 $0.00080 $0.00853
Opus 5 $0.00040 $0.00426
Sonnet 5 $0.00016 $0.00171
Haiku 4.5 $0.00008 $0.00085

Measured yesterday against content hash 655daa5cff22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

papyrus-latex-comments 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.

src/kiro_crew/builtin_skills/papyrus-latex-comments/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LaTeX Comments

Add a visible, attributable, removable layer of NOTES to a LaTeX document — remarks ABOUT the text, never a rewrite of it. Insert a macro call next to the relevant text. See papyrus-writing for the behaviour rules and the comment taxonomy. To propose concrete replacement text (accept/reject), use papyrus-latex-suggestions.

Step 1 — Setup (idempotent)

kpsewhich todonotes.sty    # non-empty = installed (ships with TeX Live — usually no install)

If the document has no comment preamble yet, inject this once at the end of the preamble, after all existing \usepackage lines (never duplicate it if it is already there):

% ==== Papyrus comment layer — safe to leave in; flip to hide ====
% Load todonotes ONLY if the document hasn't already loaded it (avoids an option clash).
\makeatletter
\@ifpackageloaded{todonotes}{}{\usepackage[textsize=scriptsize]{todonotes}}
\makeatother
\newcommand{\aicomment}[1]{\todo[color=cyan!25,bordercolor=cyan]{\textbf{AI:} #1}}   % margin note
% FINAL BUILD: hide every note by adding the `disable` option to todonotes
% (wherever it is loaded): \usepackage[disable]{todonotes}.
% ================================================================

Margin space is tight, so textsize=scriptsize keeps notes readable in a one-column margin. Comments live in the margin only — a note must never change the paper's length or reflow the text. In a two-column or narrow-margin paper, keep each note short rather than pushing it into the text flow.

Step 2 — Insert comments

Add a macro call next to the relevant text. Do NOT rewrite the prose. Tag every note with the taxonomy ([claim] [cite] [clarity] [structure] [contribution] [rigor] [style] [typo]).

The method is fast.\aicomment{[claim] by how much? add a number + CI}
This paragraph reads like Related Work.\aicomment{[structure] consider moving it there}
We imitate the baseline.\aicomment{[clarity] ``imitate'' is imprecise — say exactly what you did to the baseline}

Read the full file on GitHub · 74 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 · 74 lines · 80 tokens per session scan A 655daa5cff22

Subscribe to this mod's changes

papyrus-latex-comments is a skill published in the GitHub repository kirodotdev/KiroCrew (3,823 stars, last pushed today), licensed Apache-2.0. It adds 80 tokens to every session and 853 once invoked, about $0.0004 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 2026-09-09.