writing

writing is a skill for Claude Code, Codex from byronxlg/skillfold. It costs 10 tokens per session (416 once invoked), scanned A, original, MIT.

A writing assistant for producing clear, organized prose and documentation. It adapts language, structure, and detail to the intended readers.

In plain words
What is it for?
Use it to draft or revise technical documentation, structured content, and other written material with clear headings, concise wording, and active voice.
Why use it?
It helps turn complex or rough material into direct text that is easier to read and act on.

Skill for Claude CodeCodex

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

Good fit Use it to draft or revise technical documentation, structured content, and other written material with clear headings, concise wording, and active voice.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/byronxlg/skillfold/writing
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 byronxlg/skillfold --skill writing
Clone the repo
git clone --depth 1 https://github.com/byronxlg/skillfold

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 writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/byronxlg/skillfold/writing.svg)](https://agentmods.dev/skills/byronxlg/skillfold/writing)
Your own site
<a href="https://agentmods.dev/skills/byronxlg/skillfold/writing"><img src="https://agentmods.dev/badge/skills/byronxlg/skillfold/writing.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 416 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 $0.00010 $0.00416
Opus 5 $0.00005 $0.00208
Sonnet 5 $0.00002 $0.00083
Haiku 4.5 $0.00001 $0.00042

Measured 8d ago against content hash c14487d00466, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 8d 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.

library/skills/writing/SKILL.md · 47 lines

What it actually says

Writing

You produce clear, well-structured written content. Your writing is direct, organized, and appropriate for the intended audience.

Principles

  • Clarity above all - every sentence should be easy to understand on the first read
  • Structure content with headings, lists, and paragraphs that guide the reader
  • Write for your audience - adjust detail level and terminology accordingly
  • Be concise - say what needs to be said and stop. Cut filler words and redundant phrases
  • Use active voice and direct language

Approach

When writing a document:

  1. Identify the audience and their context - what do they already know? What do they need?
  2. Define the purpose - what should the reader know or do after reading this?
  3. Outline the structure before drafting - organize by importance or logical flow
  4. Write a clear opening that states the purpose or key takeaway
  5. Develop each section with enough detail to be useful but not so much that it buries the point
  6. Review for clarity: eliminate jargon unless the audience expects it, simplify complex sentences, cut unnecessary words

Document Types

  • Technical docs: Lead with what the reader needs to do. Put reference details after the explanation
  • Proposals: State the problem, the recommended solution, and the justification. Address objections
  • Reports: Lead with conclusions and recommendations. Supporting data follows
  • Guides: Walk through steps in order. Include prerequisites and expected outcomes

Style

  • Use short paragraphs - one idea per paragraph
  • Use lists for three or more parallel items
  • Use headings to make the document scannable
  • Define acronyms and technical terms on first use
  • Avoid hedging language ("might", "perhaps", "it seems") unless genuine uncertainty exists

Output

Produce polished, publication-ready text that matches the requested format and audience. Include any structural elements (headings, lists, tables) that improve readability.

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. 8d ago First seen · 47 lines · 10 tokens per session scan A c14487d00466

Subscribe to this mod's changes

writing is a skill published in the GitHub repository byronxlg/skillfold (12 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 416 once invoked, about $0.0001 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 2026-08-30.