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 JoelLewis/finance_skills --skill next-best-actiongit clone --depth 1 https://github.com/JoelLewis/finance_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/joellewis/finance_skills/next-best-action)<a href="https://agentmods.dev/skills/joellewis/finance_skills/next-best-action"><img src="https://agentmods.dev/badge/skills/joellewis/finance_skills/next-best-action/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/joellewis/finance_skills/next-best-action"><img src="https://agentmods.dev/badge/skills/joellewis/finance_skills/next-best-action.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00143 | $0.06721 |
| Opus 5 | $0.00072 | $0.03361 |
| Sonnet 5 | $0.00029 | $0.01344 |
| Haiku 4.5 | $0.00014 | $0.00672 |
Grade A, and why
next-best-action 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 11d 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next-Best-Action — Event-Driven Advisor Recommendations
Core Concepts
Next-Best-Action Framework
Next-best-action is an advisor productivity and client service methodology that analyzes client data across systems to surface the single most valuable action an advisor should take for each client at any given time. The concept originates in CRM and marketing automation — industries that have long used event-driven recommendation engines to guide customer-facing personnel toward high-value interactions — but its application in wealth management addresses a distinct set of challenges: advisors managing hundreds of client relationships cannot manually monitor every portfolio, life event, compliance deadline, and practice touchpoint across their entire book of business.
NBA differs fundamentally from traditional task management. Traditional task management is reactive and manual: advisors create their own to-do lists, respond to inbound client requests, and rely on memory or periodic reviews to identify outreach opportunities. NBA is proactive and data-driven: the system continuously monitors client data across custodial feeds, CRM records, financial plans, compliance calendars, and market data, automatically identifying situations that warrant advisor attention and recommending specific actions with supporting context.
The core components of an NBA system are:
- Event detection — Continuous monitoring of data sources to identify triggering events (portfolio drift, large cash movement, life milestone, compliance deadline, market dislocation).
- Action identification — Mapping detected events to a catalog of recommended actions (schedule review, propose rebalancing, discuss tax-loss harvesting, update beneficiaries).
- Prioritization — Scoring and ranking competing actions across all clients to ensure advisors focus on the highest-value activities given limited time.
- Routing — Directing each action to the appropriate person based on role, expertise, relationship, and availability.
- Delivery — Presenting recommendations through the channels advisors actually use (dashboard, mobile notification, email digest, CRM task).
- Tracking — Recording action outcomes (accepted, deferred, rejected, completed) to close the feedback loop and improve future recommendations.
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.
- 11d ago First seen · 295 lines · 143 tokens per session scan A a46c1696e6b9
next-best-action is a skill published in the GitHub repository JoelLewis/finance_skills (184 stars, last pushed 1mo ago), licensed MIT. It adds 143 tokens to every session and 6,721 once invoked, about $0.0007 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
stock-liquidity
Analyze stock liquidity using bid-ask spreads, volume profiles, order book depth, market impact estimates, and turnover ratios via Yahoo Finance data. Use this skill whenever the user asks about liquidity, trading costs, bid-ask spread, market depth, volume analysis, slippage, market impact, turnover ratio, or how…
fintel-data
Query Fintel (fintel.io) institutional market intelligence via the REST API at https://api.fintel.io/v1 with FINTELAPIKEY (X-API-KEY header), or the official MCP server at https://mcp.fintel.io/mcp. Read-only data: short interest, borrow rate/fee and shares available to borrow, daily short volume, fails-to-deliver…
estimate-analysis
Deep-dive into analyst estimates and revision trends for any stock using Yahoo Finance data. Use when the user wants to understand analyst estimate direction, how EPS or revenue forecasts changed over time, compare estimate distributions, or analyze growth projections across periods. Triggers: "estimate analysis for…
earnings-preview
Generate a pre-earnings briefing for any stock using Yahoo Finance data. Use this skill whenever the user wants to prepare for an upcoming earnings report, understand what analysts expect, review a company's beat/miss track record, or get a quick overview before an earnings call. Triggers include: "earnings preview…
earnings-recap
Generate a post-earnings analysis for any stock using Yahoo Finance data. Use when the user wants to review what happened after earnings, understand beat/miss results, see stock reaction, or get an earnings recap. Triggers: "AAPL earnings recap", "how did TSLA earnings go", "MSFT earnings results", "did NVDA beat…
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…