revise-prose

revise-prose is a skill for Claude Code from OC-NeuralSense/reader-first-writing-skills. It costs 191 tokens per session (2,524 once invoked), scanned A, original, Apache-2.0.

A writing-editing procedure for improving the flow, clarity, length, or completeness of existing prose while keeping its meaning unchanged.

In plain words
What is it for?
It helps make sentences clearer, connect paragraphs, shorten passages, or strengthen overly thin prose for the same reader.
Why use it?
It fixes awkward or unclear wording without changing the claims or structure of the original content.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

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 It helps make sentences clearer, connect paragraphs, shorten passages, or strengthen overly thin prose for the same reader.

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 revise-prose

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/revise-prose"><img src="https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/revise-prose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 191 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,524 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 $0.00191 $0.02524
Opus 5 $0.00096 $0.01262
Sonnet 5 $0.00038 $0.00505
Haiku 4.5 $0.00019 $0.00252

Measured 11d ago against content hash ead2bbbf4e9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

revise-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 11d 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/revise-prose/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

revise-prose

Purpose

Repair the prose surface of a passage (its coherence, sentence geometry, word choice, length, thinness, or correctness) while holding the meaning exactly constant. This is a revisional skill working one plane only: it changes how a fixed set of claims is rendered, never what is claimed or how the argument is arranged. It emits the revised passage and a change-report that classifies every edit.

Task-mode handling (five modes, one skill)

The caller supplies task_mode; if absent, infer it from the request phrasing and confirm. Each mode carries the same strict fidelity gate.

  • cohere: "the flow is broken." Restore recoverable coherence: hold a stable topic string in or near the subject slot, anchor new material to given, repair paragraph bridges, and mark each intended relation once. Never insert a connective that names a relation the content does not actually carry.
  • clarify: "make it clearer." Remove misparse (garden-path) traps and deep center-embedding, reconcile end-weight with given-before-new, split overgrown trees when held-open load is high. Keep every participant role and referent intact; distinguish a garden path (re-insert a cue) from genuine structural ambiguity (rebuild to one tree).
  • compress: "cut it down." Delete only words that carry no meaning and no parsing value. Keep every structure-marking word (the that that blocks a misparse, the preposition that fixes attachment) and every qualifier, hedge, scope limit, condition, and exception. Length is measured in reader work, not word count.
  • expand: "it's too thin." Close the named expert blind spot with concrete, picturable material the reader needs: a definition, a worked instance, a laid given ground. Never pad, and never invent claims or support the source lacks.
  • usage: "fix the grammar / settle the punctuation." A lightweight correctness-only pass (CAP-37). Settle grammar, punctuation, and disputed usage only; distinguish ungrammatical from merely ambiguous, and grammar from register. A contested "rule" is flagged for judgment, not silently enforced. A trivial correctness fix needs no full review-document pass; it changes no claim and holds the same strict fidelity.

Read the full file on GitHub · 198 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. 11d ago First seen · 198 lines · 191 tokens per session scan A ead2bbbf4e9b

Subscribe to this mod's changes

revise-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 191 tokens to every session and 2,524 once invoked, about $0.0010 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

review-pr

A pull-request review skill for evaluating proposed code changes and posting a quality verdict. A pull request is a request to merge changes into a shared codebase.

cryndoc/polisade-orchestrator · 113 tokens