What is trader-hand-skill?

A reference guide for market analysis and trading, including price indicators such as RSI, risk management, the Alpaca trading API, and financial data sources.

Use it to calculate and interpret technical indicators, review trading risks, work with Alpaca, and find or use financial data sources.

It gives an agent practical definitions, formulas, and interpretations for examining market data and planning trades. It also provides guidance for considering risk instead of focusing only on price movements.

trader-hand-skill — Skill by librefang

Install

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.

agentmods

npx agentmods add skills/librefang/librefang-registry/trader

Any agent

npx skills add librefang/librefang-registry --skill trader

Clone the repo

git clone --depth 1 https://github.com/librefang/librefang-registry

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 11,286 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 3 findings. Scan, not verified.

Origin 100% copy Near-identical to another mod in the catalogue.

Token cost

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	$0.11286
Opus 5	$0.00014	$0.05643
Sonnet 5	$0.00006	$0.02257
Haiku 4.5	$0.00003	$0.01129

Measured 3d ago against content hash c3123ec1d72b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

trader-hand-skill scanned grade D with 3 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 3d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -s "$DATA_URL/v2/stocks/AAPL/bars?timeframe=5Min&start=$(date -d 'today' +%Y-%m-%d)&limit=78" $HEADERS

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s URL | python3 -c "import sys,json; d=json.load(sys.stdin); print(d['equity'])"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "$BASE_URL/v2/account" $HEADERS

Origin

This is a copy

100% identical to trader-hand-skill — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

hands/trader/SKILL.md · 938 lines

How it starts

The opening of the file, as written. The whole thing — 938 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trading Expert Knowledge

Reference Knowledge

1. Technical Analysis Indicators Reference

RSI (Relative Strength Index)

Formula: RSI = 100 - (100 / (1 + RS))
Where:  RS = Average Gain / Average Loss over N periods (default N = 14)

Step-by-step calculation:
  1. For each period, compute change = Close(t) - Close(t-1)
  2. Gains = max(change, 0), Losses = abs(min(change, 0))
  3. First average: simple mean of first 14 gains/losses
  4. Subsequent: AvgGain = (PrevAvgGain * 13 + CurrentGain) / 14  (Wilder smoothing)
  5. RS = AvgGain / AvgLoss
  6. RSI = 100 - (100 / (1 + RS))

Worked example (14-period):
  Avg Gain over 14 periods = 1.02
  Avg Loss over 14 periods = 0.68
  RS = 1.02 / 0.68 = 1.50
  RSI = 100 - (100 / (1 + 1.50)) = 100 - 40 = 60.0

Interpretation:

RSI < 30: Oversold territory (potential buy signal)
RSI > 70: Overbought territory (potential sell signal)
RSI = 50: Neutral — price momentum balanced

Advanced RSI Signals:

Signal	Description	Strength
Bearish divergence	Price makes new high, RSI makes lower high	Strong reversal warning
Bullish divergence	Price makes new low, RSI makes higher low	Strong reversal warning
Bullish failure swing	RSI drops below 30, bounces, pulls back above 30, breaks prior RSI high	Very strong buy
Bearish failure swing	RSI rises above 70, drops, bounces below 70, breaks prior RSI low	Very strong sell
Range shift	RSI oscillates 40-80 in uptrend, 20-60 in downtrend	Trend confirmation

Best practices: Never use RSI as a sole signal. Combine with trend direction (moving averages) and volume. In strong trends, RSI can stay overbought/oversold for extended periods.

MACD (Moving Average Convergence Divergence)

MACD Line   = EMA(12) - EMA(26)
Signal Line = EMA(9) of MACD Line
Histogram   = MACD Line - Signal Line

EMA formula: EMA(t) = Price(t) * k + EMA(t-1) * (1 - k)
Where: k = 2 / (N + 1)
  For EMA(12): k = 2/13 = 0.1538
  For EMA(26): k = 2/27 = 0.0741

Worked example:
  EMA(12) = 155.20
  EMA(26) = 152.80
  MACD Line = 155.20 - 152.80 = 2.40
  Previous Signal Line = 1.80
  Signal Line = 2.40 * (2/10) + 1.80 * (8/10) = 0.48 + 1.44 = 1.92
  Histogram = 2.40 - 1.92 = 0.48 (positive = bullish momentum increasing)

Read the full file on GitHub · 938 lines

Files

What ships with it

2 files 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.

Changes

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.

3d ago First seen · 938 lines · 28 tokens per session scan D c3123ec1d72b

Subscribe to this mod's changes

trader-hand-skill is a skill published in the GitHub repository librefang/librefang-registry (11 stars, last pushed 9d ago), licensed MIT. It adds 28 tokens to every session and 11,286 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 3 findings (sends data to an external url, downloads and executes remote code, makes network calls). It is 100% identical to trader-hand-skill, differing in 2 lines, and is treated as a copy.

Finance and fintech LLM agent ai-agents crypto librefang mcp registry risk-management stocks technical-analysis trading