compare-versions

compare-versions is a skill for Claude Code from OC-NeuralSense/reader-first-writing-skills. It costs 171 tokens per session (1,767 once invoked), scanned A, original, Apache-2.0.

A review skill for comparing an earlier version of a text with its revision. It checks both the changes and whether important qualifications or limits were lost.

In plain words
What is it for?
Use it to align two versions, assess what changed, judge whether the revision is better for a specified reader, and report problems without rewriting the text.
Why use it?
It helps detect edits that sound clearer but change the meaning, remove caveats, or make claims too certain.

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 align two versions, assess what changed, judge whether the revision is better for a specified reader, and report problems without rewriting the text.

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 compare-versions

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/compare-versions"><img src="https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/compare-versions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 171 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,767 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 $0.00171 $0.01767
Opus 5 $0.00086 $0.00883
Sonnet 5 $0.00034 $0.00353
Haiku 4.5 $0.00017 $0.00177

Measured 12d ago against content hash d418937685c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

compare-versions 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 12d 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/compare-versions/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

compare-versions

Purpose

Judge a revision against the version it replaced. The job is not to admire the improvement but to catch what the improvement may have cost: a change that reads better yet quietly says something different, or a hedge that vanished so the prose could sound more confident. This is an evaluative skill. It reports; it does not rewrite, and it never edits the user's text.

When to use

  • Two versions of one passage or document exist and the writer wants a verdict on what changed and whether it is genuinely better.
  • The writer suspects an edit may have dropped a caveat, scope limit, or number.

When NOT to use (routing non-triggers)

  • Only one version exists -> diagnose-draft.
  • The writer wants the change applied, not judged -> revise-prose / revise-structure.
  • The writer wants a genre review or ship decision -> review-document.

Inputs

  • original (required)
  • revised (required)
  • preservation_intent (strict | standard | loose; default strict for technical/academic, standard otherwise)
  • reader-frame contract (required: reader-effort verdicts are relative to this reader)

Workflow

  1. Align. Segment both versions and pair each changed segment original-to-revised.
  2. Classify each change. Mark it meaning-altering or meaning-preserving. A silent meaning change is a fidelity problem, never a style win; record it as such.
  3. Sweep for dropped qualifications. Walk the original for every hedge, scope limit, condition, exception, modality word, and number; confirm each survives with its original force and precision. List every one that did not, with its original location.
  4. Sweep for added claims. Confirm the revised version asserts nothing the original did not: no smuggled cause, stronger generalization, or unearned conclusion.
  5. Judge the preserving changes. For each, decide whether reader effort went lower, neutral, or higher, tying the verdict to a named reader effect, not to taste.
  6. Emit the change-report.

Read the full file on GitHub · 143 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. 12d ago First seen · 143 lines · 171 tokens per session scan A d418937685c5

Subscribe to this mod's changes

compare-versions 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 171 tokens to every session and 1,767 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

recursive-decomposition

Decompose dense codebase-wide, multi-document, PDF, and aggregation work even when the input fits the context window, following Recursive Language Models (Zhang, Kraska, Khattab, 2025). Use when the user asks to analyse all files, a whole repo, all docs, large PDFs, or to aggregate or multi-hop across scattered…

massimodeluisa/recursive-decomposition-skill · 144 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