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.
npx agentmods add commands/fergupa/claude_plugins/variance-analysisgit clone --depth 1 https://github.com/fergupa/claude_pluginsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00012 | $0.01580 |
| Opus 5 | $0.00006 | $0.00790 |
| Sonnet 5 | $0.00002 | $0.00316 |
| Haiku 4.5 | $0.00001 | $0.00158 |
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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Variance / Flux Analysis
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Important: This command assists with variance analysis workflows but does not provide financial advice. All analyses should be reviewed by qualified financial professionals before use in reporting.
Decompose variances into underlying drivers, provide narrative explanations for significant variances, and generate waterfall analysis.
Usage
/flux <area> <period-comparison>
Arguments
area— The area to analyze:revenue— Revenue variance by stream, product, geography, customer segmentopex— Operating expense variance by category, department, cost centercapex— Capital expenditure variance vs budget by project and asset classheadcount— Headcount and compensation variance by department and role levelcogsorcost-of-revenue— Cost of revenue variance by componentgross-margin— Gross margin analysis with mix and rate effects- Any specific GL account or account group
period-comparison— The periods to compare. Formats:2024-12 vs 2024-11— Month over month2024-12 vs 2023-12— Year over year2024-Q4 vs 2024-Q3— Quarter over quarter2024-12 vs budget— Actual vs budget2024-12 vs forecast— Actual vs forecast2024-Q4 vs 2024-Q3 vs 2023-Q4— Three-way comparison
Workflow
1. Gather Data
If ~~erp or ~~data warehouse is connected:
- Pull actuals for both comparison periods at the detail level
- Pull budget/forecast data if comparing to plan
- Pull supporting operational metrics (headcount, volumes, rates)
- Pull prior variance analyses for context
If no data source is connected:
Connect ~~erp or ~~data warehouse to pull financial data automatically. To analyze manually, provide:
- Actual data for both comparison periods (at account or line-item detail)
- Budget/forecast data (if comparing to plan)
- Any operational metrics that drive the financial results (headcount, volumes, pricing, etc.)
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.
- 2d ago First seen · 159 lines · 12 tokens per session scan A b2fc485c73cc
variance-analysis is a command published in the GitHub repository fergupa/claude_plugins (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,580 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.
Other commands, from other repositories
earnings
财报解读 — 超预期检测 + 同比分析 + 投资逻辑影响.
audit-checklist
Perform an internal audit, review controls, or prepare for an external financial audit.
venture-debt
Evaluate or structure debt for high-growth, venture-backed startups.
monitor
Position monitoring — watchlist, thesis check, event radar, thesis tracker, catalyst calendar, morning note.
payment-compare
Compare Medicare payment for a procedure across settings of care.
report
月次クロージングレポートの自動生成.