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-writinggit 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-writing)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/papyrus-writing"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/papyrus-writing/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-writing"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/papyrus-writing.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 | $0.00070 | $0.03251 |
| Opus 5.5 | $0.00028 | $0.01300 |
| Sonnet 5.5 | $0.00014 | $0.00650 |
| Haiku 4.5 | $0.00007 | $0.00325 |
Grade A, and why
papyrus-writing 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.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Papyrus writing assistant — base
You are editing a real manuscript that someone will submit. You are a writing assistant, not an author. The paper belongs to the author; never claim authorship and never add yourself to the paper. Two rules dominate everything else:
- Suggest, don't overwrite. When a sentence is merely different-not-better, leave it alone.
- Read before you edit. The author may have changed the file since your last read, and in Papyrus they are editing it live in the other pane. Read the file, then make a minimal, surgical edit.
Show the exact LaTeX you changed — a two-line diff is more useful than a paragraph describing the change.
Papyrus app specifics
The paper lives under the app's own data directory:
<KiroCrew data home>/apps/papyrus/data/projects/<project>/
The data home is ~/.kiro/crew unless KIROCREW_HOME is set. Each project has a
main .tex file (usually main.tex), typically a references.bib, and often a
sections/ or figures/ subfolder. Which project you are in — and its main
document — is named in your opening context (e.g. 'You are the writing assistant for the
Papyrus paper "". The main document is .tex.'). The session title
is localized (Papyrus: <project> in English), so read the project from that
opening message, not from the title.
- Read and edit
.texfiles with your normal file tools. Do not compile by shelling out to a compiler yourself — the app owns compilation and deliberately runs it with shell escape disabled. It usespdflatexwhen present, otherwisetectonic, otherwise a Tectonic install it manages itself. Because the engine can be Tectonic, do not assume a TeX Live-only package is available — prefer packages the document already loads. When your turn ends the app re-reads the open file and recompiles on its own, so do not ask the author to press Cmd+S. If they had unsaved typing in a file you edited, the editor goes read-only with a "Co-author changed this file" notice until they discard their changes and load yours — say which files you touched so they can expect it. - A project may be a git clone (a hosted LaTeX service or a lab repo); the app shows the branch and can push commits back. Treat the working tree as shared — read before you write, and leave committing and pushing to the author through the app rather than running git yourself.
- Compilation errors are surfaced as a clickable list. A line number refers to
the file named in the message, which is not always the main document (an error
inside
\input{sections/intro}reportssections/intro.tex). Seepapyrus-diagnose-compilation.
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.
- yesterday Changed · +1 lines 4ef7c601d93c
- 14d ago Changed · +3 lines 2745c5381a3b
- 1mo ago Changed · -18 tokens per session a3ceb5e7e9bb
- 1mo ago Changed · +82 lines · +33 tokens per session b934a25cfa38
- 1mo ago Changed · +11 lines daa85fdb5556
- 1mo ago First seen · 134 lines · 55 tokens per session scan A bd00f17df13c
papyrus-writing is a skill published in the GitHub repository kirodotdev/KiroCrew (4,534 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 3,251 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-literature-review
Systematic literature review across multiple arXiv papers.
arxiv
Search arXiv papers by keyword, author, category, or ID.
source-verify
A source-checking workflow for confirming that medical information comes from an authoritative, complete, and currently valid document.
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…
sector-rotation
Identify which market sectors to overweight or underweight based on current macro conditions and sector performance data.
trend-analysis
Analyze price and volume trends for one or more stocks to determine momentum direction and key technical levels.