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 skills/datarails/dr-claude-code-plugins-re/forecast-variancenpx skills add Datarails/dr-claude-code-plugins-re --skill forecast-variancegit clone --depth 1 https://github.com/Datarails/dr-claude-code-plugins-reWrote 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/datarails/dr-claude-code-plugins-re/forecast-variance)<a href="https://agentmods.dev/skills/datarails/dr-claude-code-plugins-re/forecast-variance"><img src="https://agentmods.dev/badge/skills/datarails/dr-claude-code-plugins-re/forecast-variance.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00028 | $0.09731 |
| Opus 5 | $0.00014 | $0.04866 |
| Sonnet 5 | $0.00006 | $0.01946 |
| Haiku 4.5 | $0.00003 | $0.00973 |
Grade B, and why
dr-forecast-variance scanned grade B with 1 finding 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 4d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
> **Do NOT gate analysis on `isConnected`.** Refresh, DR-formula reads, evaluate **and drill-down** all work on an unconnected workbook. `connect_file` is required **only** for `create_dynamic_range`, and **only on COM** How it starts
The opening of the file, as written. The whole thing — 555 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forecast Variance Analysis
Analyze variances between your actual, plan, and forecast data. Scenario names are discovered from your data, never assumed — many orgs have no Budget scenario at all (plan data often lives in a separate planning-version field), so the plan side of the comparison is resolved at runtime (Step 1b).
Essential for FP&A reviews, planning adjustments, and performance tracking.
Arguments
| Argument | Description | Default |
|---|---|---|
--year <YYYY> |
REQUIRED Calendar year to analyze | — |
--scenarios <list> |
Comma-separated scenario names, resolved against the discovered scenario domain (Step 1b) | Resolved at runtime — actual side + plan side + forecast, whichever exist |
--period <YYYY-MM> |
Specific period to focus on | All year |
--output-xlsx <file> |
Excel output path | tmp/Forecast_Variance_YYYY_TIMESTAMP.xlsx |
--output-pptx <file> |
PowerPoint output path | tmp/Forecast_Summary_YYYY_TIMESTAMP.pptx |
Excel Context Mode (Claude in Excel)
When this skill is invoked from within Claude in Excel (the task pane add-in), switch to in-sheet enrichment mode instead of generating output files. This mode integrates the row-commentary approach from datarails-excel-multi-table-analysis and is the preferred mode when the user is working directly in a workbook.
How to detect the context: Excel context mode activates when the user has an open workbook and wants in-sheet enrichment — with or without an existing range. This applies in Claude for Excel (task pane), Claude Code with an open workbook, or any context where the user is working directly in a spreadsheet. Do not generate .xlsx or .pptx output files. Write all output directly into the active workbook using whichever Excel cell-write tool is available to you. Never use the Write tool to write spreadsheet content in this context. If no cell-write tool is available, fall back to file output mode and tell the user.
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.
- 4d ago First seen · 555 lines · 28 tokens per session scan B f810db85a95a
dr-forecast-variance is a skill published in the GitHub repository Datarails/dr-claude-code-plugins-re (3 stars, last pushed 5d ago), licensed MIT. It adds 28 tokens to every session and 9,731 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
multi-expert-analyzer
针对通用问题进行多领域专家联合分析, 综合稿产生前必经 fact-checker 与 red-team 两道独立校验。适用场景: 用户提出跨领域或不确定领域的复杂问题, 需要从多个专家角度分别搜证并相互校验后综合成文, 例如该不该买房、该不该跳槽、是否进入某个赛道等。触发关键词: 多角度分析、专家分析、综合分析、多视角、跨领域分析、从不同角度看、深度分析。问题只属于单一明确领域时, 优先使用该领域的专门 skill, 例如纯财务用 finance-core-analysis、纯技术用 software-architect。输出 (全部 markdown 保存到当前项目 markdown/ 目录): (1) 每位专家的中间分析稿…