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.
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 kirodotdev/KiroCrew --skill papyrus-latex-suggestionsgit clone --depth 1 https://github.com/kirodotdev/KiroCrewWrote 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/kirodotdev/kirocrew/papyrus-latex-suggestions)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/papyrus-latex-suggestions"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/papyrus-latex-suggestions/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/kirodotdev/kirocrew/papyrus-latex-suggestions"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/papyrus-latex-suggestions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00077 | $0.01172 |
| Opus 5 | $0.00039 | $0.00586 |
| Sonnet 5 | $0.00015 | $0.00234 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
papyrus-latex-suggestions 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 today.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LaTeX Suggestions (inline tracked edits)
Propose concrete replacement text the author sees as struck-through old + colored
new, and can accept or reject — the original stays visible until they decide.
Never silently overwrite. It renders as normal typeset text (via ulem), so it
shows in any PDF viewer including the Papyrus preview — no package to install, no
PDF annotations. See papyrus-writing for behaviour. Pair every suggestion with
a papyrus-latex-comments \aicomment saying WHY.
Step 1 — Setup (idempotent, self-contained)
ulem and xcolor ship with TeX Live — no tlmgr install. If the document has
no suggestion preamble yet, inject this once at the end of the preamble, after all existing \usepackage lines (never
duplicate it if it is already there):
% Load ulem/xcolor ONLY if the document hasn't already loaded them (avoids an option clash).
\makeatletter
\@ifpackageloaded{ulem}{}{\usepackage[normalem]{ulem}} % \sout (strike) + \uline (underline); normalem keeps \emph italic
\@ifpackageloaded{xcolor}{}{\usepackage{xcolor}} % \color for the strike/insert colors
\makeatother
% ==== Papyrus suggestion layer — self-contained ====
% Flip to \showeditsfalse to render the FINAL text only (visually accepts every change).
\newif\ifshowedits \showeditstrue
\newcommand{\aisuggest}[3][]{\ifshowedits{\color{red}\sout{#2}}\,{\color{blue}#3}\else#3\fi}
\newcommand{\txadd}[2][]{\ifshowedits{\color{blue}\uline{#2}}\else#2\fi}
\newcommand{\txremove}[2][]{\ifshowedits{\color{red}\sout{#2}}\else\fi}
% =====================================================================================
The optional [...] first argument carries metadata (author=papyrus, id=R12, status=pending): it documents the change, but it is not rendered.
Step 2 — Propose edits (argument order is always old → new)
Edit the source in place; the old text stays visible (struck red) next to the new (blue). Tag the paired comment with the taxonomy.
The retrieval system \aisuggest[author=papyrus, id=R1, status=pending]{returns}{surfaces} dozens of candidates.\aicomment{[style] ``surfaces'' fits the paper's voice better than ``returns''.}
We evaluate on a benchmark\txadd[id=R2]{, which we release publicly}.\aicomment{[contribution] state the release explicitly if true.}
It is \txremove[id=R3]{very }fast.\aicomment{[style] hedge/intensifier adds nothing.}
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.
- today First seen · 83 lines · 77 tokens per session scan A f4ef86367c90
papyrus-latex-suggestions is a skill published in the GitHub repository kirodotdev/KiroCrew (3,790 stars, last pushed today), licensed Apache-2.0. It adds 77 tokens to every session and 1,172 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.
Other skills, from other repositories
ppt-generation
Generate PPTX presentations from slide plan + content.
data-analysis
Analyze Excel/CSV files with DuckDB SQL via bash.
document-processor
Guidance for processing documents, extracting content, and transforming structured information. Use when the user asks to process, parse, extract, or transform document content such as PDFs, Word files, or spreadsheets.
attendance-signin-sheet
A spreadsheet generator for printable attendance or meeting sign-in sheets. It turns a list of names into rows with columns such as signatures, dates, departments, or employee IDs.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…