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 skills add sandbaseai/sandbase-skills --skill variance-analysisgit clone --depth 1 https://github.com/sandbaseai/sandbase-skillsWrote 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.
[](https://agentmods.dev/skills/sandbaseai/sandbase-skills/variance-analysis)<a href="https://agentmods.dev/skills/sandbaseai/sandbase-skills/variance-analysis"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/variance-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.
<a href="https://agentmods.dev/skills/sandbaseai/sandbase-skills/variance-analysis"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/variance-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.02715 |
| Opus 5 | $0.00022 | $0.01358 |
| Sonnet 5 | $0.00009 | $0.00543 |
| Haiku 4.5 | $0.00004 | $0.00271 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Variance Analysis
Important: This skill assists with variance analysis workflows but does not provide financial advice. All analyses should be reviewed by qualified financial professionals before use in reporting.
Techniques for decomposing variances, materiality thresholds, narrative generation, waterfall chart methodology, and budget vs actual vs forecast comparisons.
When inputs are supplied through report URLs, read the SandBase API map. Resolve the current schema with sandbase_describe_tool before using a listed capability through sandbase_call_tool.
Define the sign convention before calculating and label favorable/unfavorable separately: a numerically positive variance can be favorable for revenue and unfavorable for expense. When the comparison value is zero, report the percentage as not meaningful rather than dividing by zero.
Variance Decomposition Techniques
Price / Volume Decomposition
The most fundamental variance decomposition. Used for revenue, cost of goods, and any metric that can be expressed as Price x Volume.
Formula:
Total Variance = Actual - Budget (or Prior)
Volume Effect = (Actual Volume - Budget Volume) x Budget Price
Price Effect = (Actual Price - Budget Price) x Actual Volume
Mix Effect = Residual (interaction term), or allocated proportionally
Verification: Volume Effect + Price Effect = Total Variance
(when mix is embedded in the price/volume terms)
Three-way decomposition (separating mix):
Volume Effect = (Actual Volume - Budget Volume) x Budget Price x Budget Mix
Price Effect = (Actual Price - Budget Price) x Actual Volume x Actual Mix
Mix Effect = Budget Price x Actual Volume x (Actual Mix - Budget Mix)
Example — Revenue variance:
- Budget: 10,000 units at $50 = $500,000
- Actual: 11,000 units at $48 = $528,000
- Total variance: +$28,000 favorable
- Volume effect: +1,000 units x $50 = +$50,000 (favorable — sold more units)
- Price effect: -$2 x 11,000 units = -$22,000 (unfavorable — lower ASP)
- Net: +$28,000
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 272 lines · 43 tokens per session scan A e07b4ca8c89f
variance-analysis is a skill published in the GitHub repository sandbaseai/sandbase-skills (140 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 2,715 once invoked, about $0.0002 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.
Other skills, from other repositories
surf
Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls. 83 endpoints at localhost:8402/v1/surf/ covering CEX/DEX markets, on-chain SQL over 80+ ClickHouse tables (Ethereum, Base, Arbitrum, BSC, TRON, HyperEVM, Tempo), 100M+ labeled wallets, prediction markets (Polymarket + Kalshi), social/CT…
polymarket-trading
Use when the user wants to actually PLACE, manage, or redeem bets on Polymarket (not just read odds — that's the blockrunpredexon data tools). Covers setup (deposit wallet, funding, approvals), buy/sell with confirm gating, positions, redeeming winnings, geoblock handling, and the end-to-end flow.
skill
Ten native DSH tools give a text-only agent eyes. Use these structured tools directly; do not shell out to the bundled Python scripts or reproduce their implementation. Vision API credentials and model settings are managed by the plugin, so tool calls do not receive credentials.
modsearch
Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsearch CLI to return…
ads-budget
Plan and review paid-media budgets, bidding, pacing, marginal return, forecasts, CPA, ROAS, MER, LTV:CAC, constraints, and allocation across supported platforms. Use for ad budget allocation, media budget, bidding strategy, scaling, spend pacing, budget forecast, ROAS target, or investment tradeoffs.
submit-dsh-plugin
A submission checklist and workflow for adding a DeepSeek Harness plugin to the community’s public catalogue. It prepares the catalogue entry and checks the plugin’s repository, metadata, tests, and required files.