draft-prose

draft-prose is a skill for Claude Code from OC-NeuralSense/reader-first-writing-skills. It costs 178 tokens per session (2,044 once invoked), scanned A, original, Apache-2.0.

A writing aid that turns an approved, checked outline into connected paragraphs. It treats the result as editable draft material and does not add claims beyond the outline.

In plain words
What is it for?
Use it to write a document from a validated plan, argument outline, and reader profile. It is for producing an initial prose draft before review or revision.
Why use it?
It removes the need to build sentences while still deciding the argument. This helps prevent unsupported ideas from appearing in the draft.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the reader-first-writing plugin — 12 skills, 3 agents shipped together

Good fit Use it to write a document from a validated plan, argument outline, and reader profile. It is for producing an initial prose draft before review or revision.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add OC-NeuralSense/reader-first-writing-skills
Claude Code
/plugin install reader-first-writing

Made for: Claude Code.

Or install reader-first-writing, the plugin that ships this one along with the rest of its 12 skills, 3 agents.

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 draft-prose

README.md
[![agentmods](https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/draft-prose/github.svg)](https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/draft-prose)
Your own site
<a href="https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/draft-prose"><img src="https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/draft-prose/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 draft-prose

Your own site · 80×15
<a href="https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/draft-prose"><img src="https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/draft-prose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 178 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,044 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 $0.00178 $0.02044
Opus 5 $0.00089 $0.01022
Sonnet 5 $0.00036 $0.00409
Haiku 4.5 $0.00018 $0.00204

Measured 10d ago against content hash f282e9cf3af9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

draft-prose 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 10d 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.

skills/draft-prose/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

draft-prose

Purpose

Turn an approved, validated outline into continuous prose. This skill is a faithful renderer: it dresses an already-sound skeleton in sentences a reader can follow, and it treats the resulting draft as revisable raw material, not a finished document. Its defining discipline is that it adds nothing the outline does not already assert.

When to use

  • A validated argument-blueprint exists and the user wants it written up.
  • The request is "draft the prose", "write this from the plan", "render the outline into paragraphs".

When NOT to use

  • No validated outline yet, or the structure is still in flux -> build-argument.
  • A draft already exists and needs fault-finding -> diagnose-draft.
  • A draft exists and needs structural or sentence-level repair -> revise-structure / revise-prose.

Inputs

  • argument-blueprint contract (validated outline: governing question, controlling idea, grouped/ordered claims, opening plan, layout map).
  • reader-frame contract (prior knowledge, standing question, expertise level, mastered vocabulary, blind spots).

If the blueprint is present but unvalidated, stop and route back to build-argument -- do not draft on an unchecked skeleton.

Workflow

  1. Read the reader-frame; fix the mastered-vocabulary set and the assumed prior knowledge that govern word choice.
  2. Walk the layout map section by section. For each section, render its parent claim as a topic sentence and its children as the supporting sentences, keeping the ordering the blueprint fixed.
  3. Write the opening from the blueprint's opening plan (context, tension, question, answer) -- assert only what the reader already accepts in the context; do not argue the premises.
  4. Maintain a node-to-prose map: every outline node points to the prose span that renders it, so a later pass can trace any sentence back to its claim.
  5. Keep flow honest: hold each topic string in or near subject position, put given information before new, mark only the coherence relations the reader would not otherwise infer, and keep wording concrete and picturable.
  6. Run the prose over the analyzer indicators and revise obvious clarity traps in place before handing off.

Read the full file on GitHub · 174 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. 10d ago First seen · 174 lines · 178 tokens per session scan A f282e9cf3af9

Subscribe to this mod's changes

draft-prose is a skill published in the GitHub repository OC-NeuralSense/reader-first-writing-skills (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 178 tokens to every session and 2,044 once invoked, about $0.0009 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

provider-integration

Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. Covers creating provider shell scripts, setting API keys, and validating connectivity. Triggers on "add provider", "new AI agent", "provider not working", "API…

hex/claude-council · 74 tokens

update-lid

Configure or reconcile a project for linked-intent development (LID). Dispatches on project state — fresh bootstrap, append directives to an existing agent-instructions file (AGENTS.md or CLAUDE.md), add missing mode marker, reconcile convention drift, or run mode transitions. Invoked as /update-lid. For fresh…

jszmajda/lid · 105 tokens

arrow-maintenance

Navigation and audit overlay for linked-intent development. Use when working with docs/arrows/ — orienting via index.yaml, auditing spec-to-code coherence, detecting reverse orphans and drift, splitting/merging/renaming/re-parenting segments. Dual-mode: ambient guidance when the overlay is present…

jszmajda/lid · 85 tokens

map-codebase

Bootstrap LID in an existing (brownfield) codebase. Deep-reads every file in the declared scope, offers lens-based clustering options, generates skeleton LLDs/HLD/EARS bottom-up, then creates arrow docs and prompts the user to flesh out the skeletons. Token-intensive by design. Use when asked to map a codebase…

jszmajda/lid · 92 tokens

design

Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…

cryndoc/polisade-orchestrator · 162 tokens

superbrain-distill

Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.

m3talux/superbrain · 36 tokens