variance-analysis

A command that compares actual financial results with a budget, forecast, or previous year and explains the differences.

In plain words
What is it for?
Use it for monthly or quarterly reporting, investigating cost overruns or revenue shortfalls, and deciding whether to update a forecast.
Why use it?
It helps identify why revenue, costs, or profit margins are above or below expectations instead of showing only the gap.

Command

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 commands/brainbytes-dev/everything-claude-finance/variance-analysis
Clone the repo
git clone --depth 1 https://github.com/brainbytes-dev/everything-claude-finance
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,203 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 $0.00011 $0.01203
Opus 5 $0.00005 $0.00602
Sonnet 5 $0.00002 $0.00241
Haiku 4.5 $0.00001 $0.00120

Measured 2d ago against content hash 5afe835fef0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

variance-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 2d 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.

commands/variance-analysis.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/variance-analysis — Analyze Budget Variances

What This Command Does

Performs a structured variance analysis comparing actual results to budget, prior year, or forecast. Decomposes variances into price/volume/mix effects, identifies root causes, and provides actionable recommendations. Supports revenue, cost, and margin variance decomposition.

When to Use

  • Monthly or quarterly management reporting
  • Board reporting variance explanations
  • Cost overrun investigation
  • Revenue shortfall analysis
  • Reforecast trigger assessment
  • Performance review preparation

How It Works

  1. Data Comparison: Maps actuals against budget, forecast, and prior year
  2. Materiality Screening: Filters variances by absolute amount and percentage threshold
  3. Decomposition: Breaks variances into price, volume, mix, timing, and FX components
  4. Root Cause Analysis: Identifies operational drivers behind each material variance
  5. Trend Detection: Compares current variance patterns to prior periods
  6. Action Items: Proposes corrective actions for unfavorable variances and reinforcement for favorable ones

Example Usage

Input:

/variance-analysis entity:"EMEA Sales Division" period:Q1-2026 threshold:5

Output:

# Variance Analysis — EMEA Sales Division
## Period: Q1-2026 | Currency: EUR thousands | Threshold: ≥5%

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
## Executive Summary
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

| P&L Line          | Budget | Actual | Var (EUR) | Var %  | Flag |
|-------------------|--------|--------|-----------|--------|------|
| Revenue           | 12,500 | 11,800 | (700)     | -5.6%  | ⚠    |
| COGS              | (7,500)| (7,350)| 150       | +2.0%  | —    |
| Gross Profit      | 5,000  | 4,450  | (550)     | -11.0% | 🔴   |
| Sales & Marketing | (2,200)| (2,450)| (250)     | -11.4% | 🔴   |
| G&A               | (800)  | (780)  | 20        | +2.5%  | —    |
| **EBIT**          |**2,000**|**1,220**|**(780)** |**-39.0%**| 🔴 |

Overall: EBIT EUR 780K below budget. Revenue shortfall compounded by
overspend in Sales & Marketing.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
## Revenue Variance Decomposition
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

| Component      | Impact (EUR) | Explanation                              |
|----------------|-------------|------------------------------------------|
| Volume effect  | (450)       | 3 large deals slipped to Q2              |
| Price effect   | (180)       | Competitive pressure in DACH segment     |
| Mix effect     | (120)       | Higher share of lower-margin products    |
| FX effect      | +50         | GBP stronger than budgeted               |
| **Total**      | **(700)**   |                                          |

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
## S&M Overspend Analysis
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

| Category         | Budget | Actual | Var   | Root Cause                    |
|------------------|--------|--------|-------|-------------------------------|
| Headcount costs  | 1,400  | 1,420  | (20)  | Unbudgeted overtime           |
| Digital marketing| 400    | 520    | (120) | Unplanned campaign to recover pipeline |
| Events/travel    | 250    | 340    | (90)  | Additional trade show added   |
| Other            | 150    | 170    | (20)  | Within tolerance              |
| **Total S&M**    |**2,200**|**2,450**|**(250)**|                            |

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
## Recommended Actions
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

1. **Revenue recovery**: Accelerate Q2 pipeline — 3 slipped deals worth EUR 450K
   should close by April. Weekly deal tracking recommended.
2. **Pricing discipline**: Review DACH discount authority. Implement deal desk
   approval for discounts > 15%.
3. **S&M cost control**: Freeze discretionary marketing spend until revenue
   catches up. Estimated savings EUR 80K in Q2.
4. **Reforecast**: Recommend updating full-year forecast — current trajectory
   implies EUR 1.5M–2.0M EBIT shortfall for FY2026.

### Trend Watch
This is the second consecutive quarter with revenue below budget.
Q4-2025 was -3.2%, Q1-2026 is -5.6%. Pattern suggests structural
issue rather than timing — investigate market share dynamics.

Read the full file on GitHub · 117 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. 2d ago First seen · 117 lines · 11 tokens per session scan A 5afe835fef0c

Subscribe to this mod's changes

variance-analysis is a command published in the GitHub repository brainbytes-dev/everything-claude-finance (5 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 1,203 once invoked, about $0.0001 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.