Investor Skills is an open-source library that organizes investing judgment—such as evaluating opportunities, managing risk, and acting under uncertainty—into structured, reusable instructions for people and AI finance agents. It is designed for studying and applying investment approaches, including inside Questflow and other agent tools. The catalogue includes portable skill packages from the library.
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 questflowai/investorskills --skill darvas-boxgit clone --depth 1 https://github.com/questflowai/investorskillsWrote 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/questflowai/investorskills/darvas-box)<a href="https://agentmods.dev/skills/questflowai/investorskills/darvas-box"><img src="https://agentmods.dev/badge/skills/questflowai/investorskills/darvas-box/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/questflowai/investorskills/darvas-box"><img src="https://agentmods.dev/badge/skills/questflowai/investorskills/darvas-box.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 | $0.00031 | $0.00523 |
| Opus 5.5 | $0.00012 | $0.00209 |
| Sonnet 5.5 | $0.00006 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
darvas-box 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 2mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Darvas Box
Use this skill to apply Nicolas Darvas-style box trading: find strong stocks making new highs, define the box, buy breakouts above the box, and place stops below the box.
When To Use
Use this skill when the user asks for:
- Darvas Box analysis
- New-high momentum stocks
- Box breakout buy points
- Mechanical stop placement below a consolidation box
- Whether a growth stock is forming a tradable range
Trigger phrases include Darvas, Darvas Box, box breakout, new highs, volume confirmation, stop below the box, and momentum growth stock.
Do Not Use When
- The stock is not liquid.
- The stock is not near highs or has no defined box.
- The user wants low-P/E value analysis.
- The general market is hostile to growth breakouts.
Inputs Needed
- Ticker and market
- Recent daily/weekly OHLCV
- Box high, box low, number of tests, and breakout volume
- Market trend and sector strength
- Risk budget and current position if sizing is requested
Process
- Confirm the stock is liquid, strong, and near new highs.
- Define the current box high and low.
- Check that price has respected the box enough to make the range meaningful.
- Treat a decisive move above box high on volume as the buy trigger.
- Put the stop below the box or a clearly defined support level.
- Move to a new box only after the stock advances and consolidates again.
Output Format
# Darvas Box View: [Stock]
## Verdict
Buy Breakout / Watch Box / Extended / Failed Box / Pass
## Box Definition
- Box high:
- Box low:
- Stop:
## Volume And Relative Strength
## Trade Plan
## Invalidation
## Missing Data
Guardrails
- Do not buy inside a sloppy box unless the plan allows anticipation.
- Do not move the stop lower after entry.
- Do not average down.
- Do not treat old highs as valid if volume and trend are weak.
- Do not ignore market direction.
Questflow Use
In Questflow, this skill is best used as a mechanical momentum module for detecting box setups, defining stops, and monitoring breakout failure.
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.
- 2mo ago First seen · 80 lines · 31 tokens per session scan A 68b26826cfbb
darvas-box is a skill published in the GitHub repository questflowai/investorskills (1,908 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 523 once invoked, about $0.0001 per session on Opus 5.5. 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.
darvas-box compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| darvas-boxquestflowai/investorskills | Skill | 1.9k | 2mo ago | MIT | A | 31 | Claude Code, Codex |
| t-investnyxandro/t-invest-skill | Skill | 47 | yesterday | MIT | B | 147 | Claude Code, Codex |
| lienfiBankrBot/skills | Skill | 1.2k | 2d ago | none | A | 83 | Claude Code, Codex |
| serenity-chokepoint-investingleospark/serenity-chokepoint-investing-skills | Skill | 11 | 5mo ago | MIT | A | 57 | Claude Code, Codex |
| thai-personal-finance-plannersatasuk03/thai-personal-finance-planner | Skill | 20 | 6mo ago | none | B | 214 | Claude Code |
| stock-liquidityhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 129 | Claude Code |
| fintel-datahimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 157 | Claude Code |