market-breadth-analyzer

market-breadth-analyzer is a skill for Claude Code, Codex from ntaffzii/Skill-Agents. It costs 127 tokens per session (962 once invoked), scanned A, original, MIT.

A calculator for market breadth, meaning the share of stocks trading above a chosen moving average. A moving average is an average price over a set period, such as 50 or 200 trading days.

In plain words
What is it for?
Use it to calculate breadth from a CSV of stock symbols, prices, and moving averages, such as the percentage above a 50-day or 200-day average.
Why use it?
A major index can rise even when many individual stocks are falling. This gives a broader view of how widely a market move is shared, using price data you provide.

Skill for Claude CodeCodex

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

Good fit Use it to calculate breadth from a CSV of stock symbols, prices, and moving averages, such as the percentage above a 50-day or 200-day average.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ntaffzii/skill-agents/market-breadth-analyzer
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 ntaffzii/Skill-Agents --skill market-breadth-analyzer
Clone the repo
git clone --depth 1 https://github.com/ntaffzii/Skill-Agents

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 market-breadth-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ntaffzii/skill-agents/market-breadth-analyzer/github.svg)](https://agentmods.dev/skills/ntaffzii/skill-agents/market-breadth-analyzer)
Your own site
<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/market-breadth-analyzer"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/market-breadth-analyzer/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.

agentmods 80×15 button for market-breadth-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/market-breadth-analyzer"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/market-breadth-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 962 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 $0.00127 $0.00962
Opus 5 $0.00063 $0.00481
Sonnet 5 $0.00025 $0.00192
Haiku 4.5 $0.00013 $0.00096

Measured 8d ago against content hash e10f39868b2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

market-breadth-analyzer 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (breadth.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/trading/market-breadth-analyzer/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Market Breadth Analyzer

Overview

A cap-weighted index (S&P 500, Nasdaq) can rise while most individual stocks fall — a handful of large names carry the average. Breadth measures actual participation: what fraction of a universe is trading above a given moving average. This skill computes that from a CSV the user already has (or pastes), so it works with no paid market-data API.

Not financial advice. This is a descriptive statistic over data you supply. A single breadth reading in isolation is a weak signal — see Known limitations.

When to use

  • เช็คว่าตลาดกำลังขึ้นแบบกว้าง (broad) หรือขึ้นแค่ไม่กี่ตัว (narrow)
  • Scoring a watchlist or index-constituent CSV for % above 50-day/200-day moving average
  • Part of a daily/weekly market-regime check (pairs naturally with uptrend-analyzer and exposure-coach)

When NOT to use

  • The user wants an actual buy/sell signal from one breadth reading — breadth informs market posture, it is not a trade trigger on its own
  • No price/MA data is available at all and the user isn't willing to supply even a rough CSV — this skill has nothing to compute on

Core knowledge

Definition: breadth % = (number of tickers with price > moving average) / (total tickers with valid data) × 100. Most common MA choices: 50-day (shorter-term participation) and 200-day (longer-term trend participation).

Rough interpretation bands (starting heuristic, not calibrated — tune against your own universe's history):

Breadth % Reading
≥ 70% Broad participation
50-69% Moderate participation
30-49% Narrow participation
< 30% Weak participation

Data-quality handling: rows with missing or non-numeric price/MA values are excluded and reported, not silently treated as "below the MA" — folding bad data into the score in either direction would quietly bias the result.

Common mistakes

  1. Treating a single breadth reading as a standalone buy/sell signal instead of one input to overall market posture.
  2. Silently dropping rows with bad data instead of excluding-and-reporting them — this can shift the percentage without anyone noticing.
  3. Comparing breadth readings computed against different MAs (50-day vs. 200-day) as if they measure the same thing — always state which MA a given percentage refers to.
  4. Assuming price == ma counts as "above" — this implementation uses strict >, so an exact match counts as not-above; be explicit about that boundary when reporting results.

Read the full file on GitHub · 62 lines

Files

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.

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. 8d ago First seen · 62 lines · 127 tokens per session scan A e10f39868b2c

Subscribe to this mod's changes

market-breadth-analyzer is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 962 once invoked, about $0.0006 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 2026-08-31.