compensation-analysis

compensation-analysis is a skill for Claude Code from latestaiagents/agent-skills. It costs 55 tokens per session (1,483 once invoked), scanned A, original, MIT.

A framework for analyzing pay, comparing salaries with market data, creating salary bands, and checking whether employees are paid equitably.

In plain words
What is it for?
Use it to benchmark salaries, design compensation ranges, plan reviews, and analyze pay equity.
Why use it?
It helps organizations make compensation decisions consistently and identify possible pay gaps.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the hr-people-ops plugin — 6 skills, 2 commands shipped together

Good fit Use it to benchmark salaries, design compensation ranges, plan reviews, and analyze pay equity.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/latestaiagents/agent-skills/compensation-analysis
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.

Any agent
npx skills add latestaiagents/agent-skills --skill compensation-analysis
Clone the repo
git clone --depth 1 https://github.com/latestaiagents/agent-skills

Made for: Claude Code.

Or install hr-people-ops, the plugin that ships this one along with the rest of its 6 skills, 2 commands.

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 compensation-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/latestaiagents/agent-skills/compensation-analysis/github.svg)](https://agentmods.dev/skills/latestaiagents/agent-skills/compensation-analysis)
Your own site
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/compensation-analysis"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/compensation-analysis/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 compensation-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/compensation-analysis"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/compensation-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,483 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 $0.00055 $0.01483
Opus 5 $0.00028 $0.00741
Sonnet 5 $0.00011 $0.00297
Haiku 4.5 $0.00006 $0.00148

Measured 5d ago against content hash f38284e1542c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

compensation-analysis 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.

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/hr-people-ops/skills/performance/compensation-analysis/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compensation Analysis

Build fair, competitive compensation structures.

When to Use

  • Benchmarking salaries against market
  • Creating or updating salary bands
  • Analyzing pay equity
  • Planning compensation reviews
  • Building total rewards packages

Compensation Structure

Salary Band Framework

## Band Structure

| Level | Title Examples | Band Width | Typical Range |
|-------|---------------|------------|---------------|
| L1 | Associate, Junior | 20% | Entry level |
| L2 | Mid-level, Specialist | 25% | 2-4 years exp |
| L3 | Senior, Lead | 30% | 5-8 years exp |
| L4 | Staff, Principal | 35% | 8-12 years exp |
| L5 | Director, Senior Staff | 40% | 12+ years exp |

## Band Positioning

| Position | % of Midpoint | When to Use |
|----------|--------------|-------------|
| Below Min | <80% | Rarely, new to role |
| Min | 80% | New to level |
| Target | 90-100% | Fully competent |
| Midpoint | 100% | Market rate |
| Above Mid | 100-120% | High performer |
| Max | 120% | Exceptional, at cap |

Building Salary Bands

## Step 1: Market Data
- Gather salary data from 3+ sources
- Sources: Radford, Mercer, Levels.fyi, Glassdoor, Payscale
- Match to job families and levels

## Step 2: Determine Positioning
| Strategy | Market Position | When to Use |
|----------|----------------|-------------|
| Lead | 75th percentile | Talent-competitive roles |
| Match | 50th percentile | Standard roles |
| Lag | 25th percentile | Budget constraints |

## Step 3: Set Band Width
- Narrower bands (20%): Entry-level, structured roles
- Wider bands (40%): Senior, variable roles

## Step 4: Calculate Ranges
Midpoint = Market rate at target percentile
Min = Midpoint × (1 - Band Width/2)
Max = Midpoint × (1 + Band Width/2)

Example (30% band, $100K midpoint):
- Min: $100K × 0.85 = $85,000
- Max: $100K × 1.15 = $115,000

Pay Equity Analysis

Analysis Framework

## Step 1: Data Collection
Required fields:
- Base salary
- Job level/band
- Department
- Location
- Tenure
- Gender
- Race/ethnicity (where legally collected)
- Performance rating

## Step 2: Group Comparison
Compare pay within:
- Same job level
- Same department
- Same location
- Similar tenure

## Step 3: Statistical Analysis
- Calculate pay gap percentages
- Run regression analysis controlling for:
  - Job level
  - Experience
  - Performance
  - Location
  - Education (if relevant)

## Step 4: Identify Outliers
Flag individuals who are:
- >5% below expected pay
- >10% above expected pay
- Unexplained by legitimate factors

Read the full file on GitHub · 237 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. 5d ago First seen · 237 lines · 55 tokens per session scan A f38284e1542c

Subscribe to this mod's changes

compensation-analysis is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 1,483 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 2026-09-03.