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/anthropics/financial-services/deck-refreshnpx skills add anthropics/financial-services --skill deck-refreshgit clone --depth 1 https://github.com/anthropics/financial-servicesWrote 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/anthropics/financial-services/deck-refresh)<a href="https://agentmods.dev/skills/anthropics/financial-services/deck-refresh"><img src="https://agentmods.dev/badge/skills/anthropics/financial-services/deck-refresh.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 | $0.00083 | $0.01505 |
| Opus 5 | $0.00042 | $0.00753 |
| Sonnet 5 | $0.00017 | $0.00301 |
| Haiku 4.5 | $0.00008 | $0.00151 |
Grade A, and why
deck-refresh 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 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.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deck Refresh
Update numbers across the deck. The deck is the source of truth for formatting; you're only changing values.
Environment check
This skill works in both the PowerPoint add-in and chat. Identify which you're in before starting — the edit mechanism differs, the intent doesn't:
- Add-in — the deck is open live; edit text runs, table cells, and chart data directly.
- Chat — the deck is an uploaded file; edit it by regenerating the affected slides with the new values and writing the result back.
Either way: smallest possible change, existing formatting stays intact.
This is a four-phase process and the third phase is an approval gate. Don't edit until the user has seen the plan.
Phase 1 — Get the data
Use ask_user_question to find out how the new numbers are arriving:
- Pasted mapping — user types or pastes "revenue $485M → $512M, EBITDA $120M → $135M." The clearest case.
- Uploaded Excel — old/new columns, or a fresh output sheet the user wants pulled from. Read it, confirm which column is which before you trust it.
- Just the new values — "Q4 revenue was $512M, margins were 22%." You figure out what each one replaces. Workable, but confirm the mapping before you touch anything — a "$512M" that you map to revenue but the user meant for gross profit is a quiet disaster.
Also ask about derived numbers: if revenue moves, does the user want growth rates and share percentages recalculated, or left alone? Most decks have "+15% YoY" baked in somewhere that's now stale. Whether to touch those is a judgment call the user should make, not you.
Phase 2 — Read everything, find everything
Read every slide. For each old value, find every instance — including the ones that don't look the same:
| Variant | Example |
|---|---|
| Scale | $485M, $0.485B, $485,000,000 |
| Precision | $485M, $485.0M, ~$485M |
| Unit style | $485M, $485MM, $485 million, 485M |
| Embedded | "revenue grew to $485M", "a $485M business", axis labels |
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 · 112 lines · 83 tokens per session scan A de179184d2d0
deck-refresh is a skill published in the GitHub repository anthropics/financial-services (34,627 stars, last pushed 9d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,505 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
Workspace Data Analyst
Analyze CSV files in the workspace and summarize insights.
octo-docs
Docs domain — create and govern documents, read and incrementally edit a doc's live body, read and batch-edit spreadsheet cells (dims + images), read and batch-edit whiteboard scenes, members and sharing, inline comments, versions/snapshots, and attachment metadata as a bot. Load after octo-shared.
cli-anything-wps
WPS Office CLI — JSON数据驱动PPT自动生成 + 命令行操控WPS文字/表格/演示文稿.
build-model
Build a multi-tab Excel financial model.
shopify-admin-gift-message-extraction
Read-only: extracts gift messages, gift recipients, and gift flags from order custom attributes and notes for fulfillment teams to print on packing slips.