prose-conventions

prose-conventions is a skill for Claude Code, Codex from DJRHails/dotfiles. It costs 39 tokens per session (5,245 once invoked), scanned A, original, MIT.

A set of writing rules for clear prose, including short sentences, plain words, active voice, and British spelling.

In plain words
What is it for?
Writing or editing essays, documentation, reports, and other non-fiction text.
Why use it?
It reduces jargon, clichés, and unnecessary wording so prose is easier to read and understand.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/djrhails/dotfiles/prose-conventions
Any agent
npx skills add DJRHails/dotfiles --skill prose-conventions
Clone the repo
git clone --depth 1 https://github.com/DJRHails/dotfiles

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 prose-conventions

README.md
[![agentmods](https://agentmods.dev/badge/skills/djrhails/dotfiles/prose-conventions.svg)](https://agentmods.dev/skills/djrhails/dotfiles/prose-conventions)
Your own site
<a href="https://agentmods.dev/skills/djrhails/dotfiles/prose-conventions"><img src="https://agentmods.dev/badge/skills/djrhails/dotfiles/prose-conventions.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,245 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.05245
Opus 5 $0.00019 $0.02622
Sonnet 5 $0.00008 $0.01049
Haiku 4.5 $0.00004 $0.00524

Measured 4d ago against content hash 4607bdb8dccf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prose-conventions 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (prose-lint.sh, sentence-stats.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

modules/agents/skills/prose-conventions/SKILL.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prose Conventions

Apply these principles when writing or editing prose. The author is British — use British spelling (colour, organise, centre) and idioms.

Orwell's Rules ("Politics and the English Language")

  1. Avoid cliched metaphors, similes, and figures of speech
  2. Use short words instead of long ones when possible
  3. Cut unnecessary words
  4. Use active voice instead of passive voice when possible
  5. Avoid foreign phrases, scientific words, or jargon if an everyday English equivalent exists
  6. Break any rule to avoid saying something "outright barbarous"

Paul Graham

Write like you speak.

The Economist Style Guide

  1. Do not be stuffy — write as anyone would speak in common conversation
  2. Do not be hectoring or arrogant — let your analysis show weakness, don't call it "silly"
  3. Do not be too pleased with yourself — don't boast of predictions or scoops
  4. Do not be too chatty — "Surprise, surprise" is irritating, not informative
  5. Do not be too didactic — avoid sentences starting with Compare, Consider, Expect, Imagine, Note, Remember
  6. Be lucid — simple sentences help; avoid complicated constructions and gimmicks

Sentence Craft

  1. No sentence longer than 40 words — Aim for 25-35. Shorter for emphasis.
  2. Read aloud to check rhythm
  3. Check every instance of 'this' — Replace with the actor, or clarify (e.g., "This change in policy...")
  4. Conjunctions must send the right signal — Therefore = Cause + Effect. However = contrast.
  5. Connect sentences by referencing — Each sentence should refer to the theme or rheme of the previous
  6. Remove gerunds (-ing words) — Be active, not passive
  7. Flip the order — Right branch sentences (subject-verb-object first) are more assertive
  8. Verb early — Put the verb as close to the start of the sentence as possible. Early verbs make sentences easier to parse.
  9. Subject = focus — Make the thing you care about the subject of the main clause. "The model achieves 95% accuracy" not "95% accuracy is achieved by the model."
  10. Parallelism in lists — Sibling items must match in grammar, capitalisation, and structure. If the first item is an imperative verb, every item is an imperative verb.
  11. Algorithms don't try, think, or want — Attribute intentions to researchers, not methods. "Our model tries to learn X" → "We train the model to learn X." Sloppy attribution undermines interpretability and fairness claims.

Read the full file on GitHub · 279 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 279 lines · 39 tokens per session scan A 4607bdb8dccf

Subscribe to this mod's changes

prose-conventions is a skill published in the GitHub repository DJRHails/dotfiles (2 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 5,245 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

autopilot-batch

Fan out a batch of autopilot-queued issues to parallel background worktree subagents — each runs /autopilot at the build model from its 'model:' label — with a gating review at Opus 5 or above and never below the build (Opus reviews Sonnet and Opus builds, Fable reviews Fable builds).

joshukraine/dotfiles · 75 tokens

todoist-cli

Manage Todoist tasks, projects, labels, filters, sections, comments, reminders, and workspaces via the td CLI. Use when the user wants to view, create, update, complete, or organize Todoist items, or mentions tasks, inbox, today, upcoming, projects, labels, or filters.

joshukraine/dotfiles · 68 tokens

autopilot

Carry a well-scoped GitHub issue through the full dev loop autonomously, stopping at a per-run tier boundary (PR-ready, or merge+deploy for small reversible changes).

joshukraine/dotfiles · 40 tokens

qa-handoff

Generate a hands-on QA testing guide as a self-contained HTML page — for Rails apps or static (Hugo) sites. --publish uploads the HTML to the project's configured QA host.

joshukraine/dotfiles · 41 tokens

walkthrough

Generate a hands-on browser walkthrough of a PR's user-facing changes to exercise before review; --publish posts the final version to the PR for QA.

joshukraine/dotfiles · 33 tokens

dustoff

Assess a project that's been dormant for months and produce a prioritized re-entry plan — lifecycle stage, what's stale or broken, and how far the project's tooling has drifted from current conventions — delegating every fix to the skill that owns it, and optionally capturing the plan as a tracking issue that survives…

joshukraine/dotfiles · 64 tokens