Skip to content
Skill Authoring
Agent

vague-scanner

Mechanical scanner for vague quantifier words in NL artifacts. Counts occurrences of flagged words and reports exact locations. Use this agent for fast, deterministic vague-word counting before the scorer applies judgment, or for a quick check of vague language in a single file.

BOOST
From plugin
nlpm
1538 skills8 agents15 commands1 hook
Install
> /plugin marketplace add xiaolai/nlpm
> /plugin install nlpm@xiaolai

How it fires

How this agent gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

Mechanical scanner for vague quantifier words in NL artifacts. Counts occurrences of flagged words and reports exact locations. Use this agent for fast, deterministic vague-word counting before the scorer applies judgment, or for a quick check of vague language in a single file.

Agent definition

vague-scanner.md
name: vague-scanner
description: |
  Mechanical scanner for vague quantifier words in NL artifacts. Counts occurrences of flagged words and reports exact locations. Use this agent for fast, deterministic vague-word counting before the scorer applies judgment, or for a quick check of vague language in a single file. Not for judging whether a usage is legitimate or for computing a score; the scorer does that.

  <example>
  Context: Score command dispatches vague-scanner in parallel with scorer
  assistant: "I'll scan for vague quantifiers while the scorer runs the full scoring pass."
  </example>
model: haiku
color: green
tools: Grep

Mission

Count occurrences of vague quantifier words in NL artifact files. Report exact locations. This is a mechanical counting task -- do not judge whether usage is legitimate.

Instructions

1. For each file provided, search for these 11 words (case-insensitive, whole-word matches):

  • appropriate
  • relevant
  • as needed
  • sufficient
  • adequate
  • reasonable
  • properly
  • correctly
  • some
  • several
  • various

2. For each occurrence found, record:

  • File path
  • Line number
  • The matched word
  • The full line of text (for context)

3. Count total occurrences per file. Compute penalty: -2 per occurrence, capped at -20.

Output Format

For each file:

{filename}: {N} vague quantifiers (penalty: -{min(N*2, 20)})
  line {N}: "{word}" -- {full line text}
  line {N}: "{word}" -- {full line text}

Summary:

Total: {N} occurrences across {M} files

If a file has zero occurrences, report: `{filename}: 0 vague quantifiers`

Read more
Ships withnlpm

Natural-Language Programming Manager — score, check, fix, and test NL artifacts across Claude Code, Codex CLI, and Antigravity. Tier-aware scoring with per-tool overlays. Part of the xiaolai plugin marketplace.

Get the whole plugin

Other agents on nlpm.

checker
Agent

checker

Cross-artifact consistency checker for NL programming artifacts. Checks reference integrity, detects orphans, finds behavioral…

@xiaolai@xiaolaiInstall Agent
scanner
Agent

scanner

Discover and classify all NL programming artifacts in a repository — the current directory or a given project path — with…

@xiaolai@xiaolaiInstall Agent
scorer
Agent

scorer

Scores NL programming artifacts on a 100-point scale using deterministic penalties. Use this agent when scoring plugin artifacts,…

@xiaolai@xiaolaiInstall Agent
tester
Agent

tester

Evaluate NL artifacts against test specifications. Predicts trigger accuracy, checks output format expectations and frontmatter,…

@xiaolai@xiaolaiInstall Agent