dotfiles: Skill for Claude Code

.claude/skills/org-literate/SKILL.md

org-literate is a skill for Claude Code from natsukium/dotfiles. It costs 65 tokens per session (1,638 once invoked), scanned A, original, CC0-1.0.

A writing standard for literate Org documents, which combine configuration settings with explanatory prose. It defines the voice, structure, formatting, and level of detail used in this repository.

In plain words
What is it for?
Use it when writing, rewriting, or reviewing prose in Org configuration files, modules, overlays, and related README files.
Why use it?
It keeps configuration documentation consistent and makes the reasoning behind settings easier to follow.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is natsukium/dotfiles's own configuration. It tells Claude Code how to work on dotfiles itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dotfiles configures →

Reuse

Borrowing it

Nothing to install: this file belongs to natsukium/dotfiles. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/natsukium/dotfiles/main/.claude/skills/org-literate/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/natsukium/dotfiles

Made for: Claude Code.

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 org-literate

README.md
[![agentmods](https://agentmods.dev/badge/skills/natsukium/dotfiles/org-literate/github.svg)](https://agentmods.dev/skills/natsukium/dotfiles/org-literate)
Your own site
<a href="https://agentmods.dev/skills/natsukium/dotfiles/org-literate"><img src="https://agentmods.dev/badge/skills/natsukium/dotfiles/org-literate/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 org-literate

Your own site · 80×15
<a href="https://agentmods.dev/skills/natsukium/dotfiles/org-literate"><img src="https://agentmods.dev/badge/skills/natsukium/dotfiles/org-literate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,638 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00065 $0.01638
Opus 5 $0.00032 $0.00819
Sonnet 5 $0.00013 $0.00328
Haiku 4.5 $0.00006 $0.00164

Measured 9d ago against content hash 7242bac9017e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

org-literate 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 9d 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.

.claude/skills/org-literate/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prose Standard for Literate Org Documents

Rules for writing and revising prose in this repository's Org documents. Adapted from k16shikano's japanese-tech-writing standard (https://gist.github.com/k16shikano/fd287c3133457c4fd8f5601d34aa817d), translated to English and to the register of a personal configuration narrative.

Formatting

  • Fill-wrap paragraphs at roughly 85 columns, matching the surrounding text.
  • Org markup: =code= for commands, option paths, and file names; ~verbatim~ for literal values; [[url][description]] for links, with proper nouns kept as the description.
  • Fragments of code, diffs, logs, and config belong in src blocks, not inline prose.
  • Bold a repo-specific term at its first definition; refer to it in plain text afterwards.

Voice

This configuration is a story told by its owner. The reader is a guest browsing someone's dotfiles, not a student reading a manual.

  • Narrate decisions in the first person: "I pin this to 0.9 because the 1.x series broke tangling", not "the package is pinned due to breakage".
  • Describe what software does in plain third person: "niri scrolls windows horizontally". First person is for choices, history, and opinions.
  • Real history is welcome ("after the second time a brew upgrade broke Emacs, I moved everything to Nix") — but only if it actually happened.
  • Avoid "we": there is only one author here. Avoid tutorial imperatives ("install X, then run Y") unless the section genuinely is a procedure.
  • Opinions may be blunt. "zsh's completion setup wore me down" is better material than a neutral feature comparison.

Scope per setting

  • Most settings need one or two sentences: what it enables and the visible effect.
  • Reserve the full problem-and-alternatives account for non-obvious trade-offs: architectural choices, package pins, temporary workarounds, forks.
  • Prose explains why and why-not-the-alternative; the code block already shows what. Never paraphrase the code line by line.
  • When a fact can be stated as configuration, state it in the code block even if it only repeats a default. An explicit setting is clearer than a sentence about the default.

Read the full file on GitHub · 140 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. 9d ago First seen · 140 lines · 65 tokens per session scan A 7242bac9017e

Subscribe to this mod's changes

org-literate is a skill published in the GitHub repository natsukium/dotfiles (103 stars, last pushed today), licensed CC0-1.0. It adds 65 tokens to every session and 1,638 once invoked, about $0.0003 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.