analyze-variation

analyze-variation is a skill for Claude Code, Codex from augchan42/inkstone. It costs 50 tokens per session (896 once invoked), scanned A, original, MIT.

A measurement tool for checking how much sentence lengths vary within social posts and how much post lengths vary across a batch. It flags posts with repetitive rhythm or neighboring posts of nearly identical size.

In plain words
What is it for?
Checking batches of social posts, journal drafts, or blog drafts for repetitive sentence rhythm and overly similar post lengths.
Why use it?
It helps detect writing that sounds mechanically uniform before content is scheduled or published. The measurements are produced by a bundled script rather than estimated by eye.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the inkstone plugin — 21 skills, 1 hook shipped together

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/augchan42/inkstone/analyze-variation
Any agent
npx skills add augchan42/inkstone --skill analyze-variation
Clone the repo
git clone --depth 1 https://github.com/augchan42/inkstone

Made for: Claude Code, Codex.

Or install inkstone, the plugin that ships this one along with the rest of its 21 skills, 1 hook.

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 analyze-variation

README.md
[![agentmods](https://agentmods.dev/badge/skills/augchan42/inkstone/analyze-variation.svg)](https://agentmods.dev/skills/augchan42/inkstone/analyze-variation)
Your own site
<a href="https://agentmods.dev/skills/augchan42/inkstone/analyze-variation"><img src="https://agentmods.dev/badge/skills/augchan42/inkstone/analyze-variation.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 896 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 $0.00050 $0.00896
Opus 5 $0.00025 $0.00448
Sonnet 5 $0.00010 $0.00179
Haiku 4.5 $0.00005 $0.00090

Measured 5d ago against content hash a66c8f35c65c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-variation 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 5d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/analyze-variation.mjs, scripts/analyze-variation.test.mjs), 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.

skills/analyze-variation/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Variation

Reports rhythm (within-post sentence-length variation) and length spread (across a sequence of posts), and flags monotone posts and too-similar neighbors.

Why this is a skill with a script, not a prompt: length and rhythm metrics must be deterministic. The numbers are computed by the bundled Node script — this skill just tells the agent to run it and how to read the output. Do not eyeball the counts; run the script.

When to use

  • Before scheduling a batch of social posts, to check the feed won't read as a same-length content machine.
  • Reviewing journal/blog drafts or any prose for metronomic cadence.
  • Whenever a house style asks to "vary sentence and post length" (the measurement is voice-agnostic; the style rules stay in the project's own voice doc).

How to run

Always execute the bundled script — never compute the metrics yourself.

The script lives at scripts/analyze-variation.mjs inside this skill's own directory. Resolve that directory however your harness exposes it, then run the absolute path with Node:

  • Claude Code: $CLAUDE_PLUGIN_ROOT/skills/analyze-variation/scripts/analyze-variation.mjs
  • opencode / other Agent Skills hosts: use the absolute path to this SKILL.md's directory + /scripts/analyze-variation.mjs (the env var above is Claude-Code-only).
# pick whichever resolves on your harness; SCRIPT points at the bundled .mjs
SCRIPT="$CLAUDE_PLUGIN_ROOT/skills/analyze-variation/scripts/analyze-variation.mjs"

# one post per file → sequence analysis with neighbor flags
node "$SCRIPT" posts/*.md

# a single post inline or piped
node "$SCRIPT" --text "Short. Then a noticeably longer sentence."
pbpaste | node "$SCRIPT"

# machine-readable, or write a version-tracked report
node "$SCRIPT" posts/*.md --json
REPORT_DATE=2026-06-07 node "$SCRIPT" posts/*.md --write report.md

Markdown frontmatter and JSX/HTML tags are stripped before analysis. The script is CJK-aware (Chinese characters count as tokens; wide chars weighted ×2 for length), so it works for English and mixed CJK copy alike. Dependency-free (Node built-ins).

Read the full file on GitHub · 86 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. 5d ago First seen · 86 lines · 50 tokens per session scan A a66c8f35c65c

Subscribe to this mod's changes

analyze-variation is a skill published in the GitHub repository augchan42/inkstone (4 stars, last pushed 9d ago), licensed MIT. It adds 50 tokens to every session and 896 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 2026-08-31.

Related

Other skills, from other repositories

xiaohongshu-search-full

Search Xiaohongshu (XHS / RedNote) notes by keyword with full field extraction including body text, topics/tags, image list URLs, video stream URL, publish timestamp, and all engagement stats (likes, collects, comments, shares). Supports all page filter options: sort order (general, latest, most liked, most commented…

browser-act/skills · 254 tokens

x-tweet-by-conversation

Collects every tweet in an X (Twitter) conversation thread given a conversation id (root tweet id) — the focal tweet plus all replies, sub-replies, and quote chains — and returns normalized per-tweet data with text, author, engagement counts, media, hashtags, mentions, inreplyto mapping, and cursor for pagination. Use…

browser-act/skills · 218 tokens

amazon-reviews-api-skill

This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…

browser-act/skills · 124 tokens

amazon-competitor-analyzer

Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.

browser-act/skills · 48 tokens

muapi-media-editing

Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.

SamurAIGPT/Generative-Media-Skills · 41 tokens

ctf-malware

Provides malware analysis and network traffic techniques for CTF challenges. Use when analyzing obfuscated scripts, malicious packages, custom crypto protocols, C2 traffic, PE/.NET binaries, RC4/AES encrypted communications, YARA rules, shellcode analysis, memory forensics for malware (Volatility malfind, process…

ljagiello/ctf-skills · 101 tokens