papyrus-make-fluent

papyrus-make-fluent is a skill for Claude Code, Codex from kirodotdev/KiroCrew. It costs 71 tokens per session (477 once invoked), scanned A, original, Apache-2.0.

A LaTeX editing guide that improves English grammar, fluency, and clarity without changing the document's structure or meaning. It records each change as a suggestion rather than silently replacing the text.

In plain words
What is it for?
Use it to proofread LaTeX passages, tighten wording, and check that edits stay consistent across the document.
Why use it?
It helps authors polish academic or technical writing while preserving their claims, layout, terminology, and voice.

Skill for Claude CodeCodex

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

Good fit Use it to proofread LaTeX passages, tighten wording, and check that edits stay consistent across the document.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kirodotdev/kirocrew/papyrus-make-fluent
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 · 3,860 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-make-fluent
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-make-fluent

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/papyrus-make-fluent"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/papyrus-make-fluent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 477 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 $0.00071 $0.00477
Opus 5 $0.00036 $0.00238
Sonnet 5 $0.00014 $0.00095
Haiku 4.5 $0.00007 $0.00048

Measured 3d ago against content hash e02ff41d17fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

papyrus-make-fluent 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 3d 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.

src/kiro_crew/builtin_skills/papyrus-make-fluent/SKILL.md · 37 lines

What it actually says

Make Fluent

Polish mode: improve HOW it reads, never WHAT it says or WHERE it sits. Follow papyrus-writing for conduct, the clarity principles (Gopen & Swan), and the house style; produce every change as a tracked suggestion via papyrus-latex-suggestions (paired with a comment giving the reason) — never overwrite silently. This skill adds only what is specific to polishing: the scope fence and chameleon-mode.

Scope fence

  • MAY change: grammar, spelling, agreement, articles, tense; awkward or wordy phrasing → tighter and clearer (topic/stress position, subject close to verb, old→new flow); hedging and redundancy.
  • MUST NOT change: the structure — don't move, merge, split, add, or delete sentences/paragraphs (flag it instead); the meaning — never a claim, number, result, definition, or citation; the author's voice — match their terminology, notation, macros, and bib keys, don't flatten to generic prose; the layout — don't rewrap paragraphs you weren't asked to touch.

Chameleon mode

Before editing, read a few passages the author has already written fluently to learn their register and level of English, then match it — don't homogenize a distinctive or non-native voice into generic prose. Read enough surrounding text to keep terminology consistent, and keep every edit sentence-local and minimal (one suggestion per issue).

After polishing

Run the ripple / global-consistency check from papyrus-writing §7 — a local rewording can desync the abstract, captions, notation, or cross-references. FLAG anything affected and offer to propagate; never propagate silently.

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. 3d ago First seen · 37 lines · 71 tokens per session scan A e02ff41d17fb

Subscribe to this mod's changes

papyrus-make-fluent is a skill published in the GitHub repository kirodotdev/KiroCrew (3,860 stars, last pushed today), licensed Apache-2.0. It adds 71 tokens to every session and 477 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.