sentiment-engine

sentiment-engine is a skill for Claude Code, Codex from JansenAnalytics/claudex. It costs 78 tokens per session (523 once invoked), scanned A, original, MIT.

A market-sentiment data tool covering retail forex positions, institutional futures positions, and Fear & Greed indexes for crypto and US stocks.

In plain words
What is it for?
Use it to collect and query Myfxbook retail data, CFTC Commitment of Traders data, and daily crypto or stock Fear & Greed readings.
Why use it?
It gives traders a way to compare crowd positioning and institutional positioning when looking for possible contrarian signals.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to collect and query Myfxbook retail data, CFTC Commitment of Traders data, and daily crypto or stock Fear & Greed readings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jansenanalytics/claudex/sentiment-engine
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.

Any agent
npx skills add JansenAnalytics/claudex --skill sentiment-engine
Clone the repo
git clone --depth 1 https://github.com/JansenAnalytics/claudex

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sentiment-engine

README.md
[![agentmods](https://agentmods.dev/badge/skills/jansenanalytics/claudex/sentiment-engine.svg)](https://agentmods.dev/skills/jansenanalytics/claudex/sentiment-engine)
Your own site
<a href="https://agentmods.dev/skills/jansenanalytics/claudex/sentiment-engine"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/sentiment-engine.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 523 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.00523
Opus 5 $0.00039 $0.00262
Sonnet 5 $0.00016 $0.00105
Haiku 4.5 $0.00008 $0.00052

Measured 4d ago against content hash f7da0ef98c24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sentiment-engine 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.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/collect-cot.py, scripts/collect-fear-greed.py, scripts/collect-retail.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/sentiment-engine/SKILL.md · 64 lines

What it actually says

Sentiment Engine

Quick Start

SKILL=${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/sentiment-engine/scripts

# Retail sentiment (Myfxbook — 54 forex pairs)
python3 $SKILL/collect-retail.py

# COT institutional positioning (CFTC — 11 contracts)
python3 $SKILL/collect-cot.py

# Fear & Greed indices (Crypto + CNN)
python3 $SKILL/collect-fear-greed.py

Query

# Latest retail sentiment (extremes = contrarian signals)
python3 $SKILL/query.py retail --latest

# COT data for specific instrument
python3 $SKILL/query.py cot --instrument EURUSD

# Fear & Greed
python3 $SKILL/query.py fear-greed --latest

# Database stats
python3 $SKILL/query.py stats

Data Sources

Source Instruments Update Freq Data
Myfxbook 54 forex pairs Real-time % long/short retail
CFTC COT 11 (FX, metals, energy) Weekly (Tue data, Fri release) Institutional net positions
alternative.me Crypto Daily Fear & Greed 0-100
CNN US Equities Daily Fear & Greed 0-100

Contrarian Signals

Retail sentiment is a contrarian indicator: when >70% of retail is long, consider shorting.

  • net < -20 → contrarian bullish (retail oversold)
  • net > +20 → contrarian bearish (retail overbought)

COT: Watch for speculative net position extremes and reversals.

Files

What ships with it

5 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.

  1. 4d ago First seen · 64 lines · 78 tokens per session scan A f7da0ef98c24

Subscribe to this mod's changes

sentiment-engine is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 523 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 2026-09-03.

Related

Other skills, from other repositories