clarity-language

A collection of three writing-focused skills for making technical and Russian-language text clearer and less formulaic. It includes checks for clarity, signs of machine-like prose, and natural Russian wording.

In plain words
What is it for?
Use it to review technical documentation for clarity, assess prose style, write natural Russian, avoid invented translations of established terms, and check agreement after wording changes.
Why use it?
It helps spot vague or synthetic-sounding writing, unnecessary jargon, and awkward translations before text is published.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add spumer/i-m-senior-developer
agentmods
npx agentmods add plugins/spumer/i-m-senior-developer/clarity-language
Clone the repo
git clone --depth 1 https://github.com/spumer/i-m-senior-developer

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 3 skills, 1 hook cost 527 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

clarity-language 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 3d 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.

plugins/clarity-language/.claude-plugin/plugin.json · 10 lines

What it actually says

{
  "name": "clarity-language",
  "version": "0.4.1",
  "description": "Ясность языка: три скилла против AI-синтетики в текстах. clarity-validator (12 смысловых паттернов в тех-доках с FPF-обоснованием), ai-prose-detector (стилистика художественной прозы по 6 методам), russian-style (естественный русский без кальки и придуманных русских переводов устоявшихся заимствований, без пустых антитез и канцелярита, с проверкой согласования после замены термина).",
  "author": {
    "name": "spumer"
  },
  "keywords": ["clarity", "text-quality", "ai-slop", "russian", "prose", "fpf", "documentation", "writing"]
}
Contents

What it installs

The manifest is a name and a version. 3 skills, 1 hook travel with it, and installing the plugin installs all of them — 527 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 3d ago First seen · 10 lines scan A 8acce65b0625

Subscribe to this mod's changes

clarity-language is a plugin published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 11d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.