byma

byma is a skill for Claude Code, Codex from gauss314/skills. It costs 94 tokens per session (4,702 once invoked), scanned A, original, MIT.

A Spanish-language data guide for BYMA, Argentina's main stock exchange. It retrieves public market data such as shares, bonds, CEDEARs, options, indices, and historical open-high-low-close-volume prices without an API key.

In plain words
What is it for?
Use it to view market panels, look up instruments and bond details, retrieve historical prices and trading volume, and inspect Argentine stocks, funds-like depositary receipts, bonds, and derivatives.
Why use it?
It provides one way to obtain BYMA data while noting important limits: the undocumented public service may change, prices are typically delayed, and requests should be limited.

Skill for Claude CodeCodex

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

Good fit Use it to view market panels, look up instruments and bond details, retrieve historical prices and trading volume, and inspect Argentine stocks, funds-like depositary receipts, bonds, and derivatives.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gauss314/skills/byma
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 gauss314/skills --skill byma
Clone the repo
git clone --depth 1 https://github.com/gauss314/skills

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 byma

README.md
[![agentmods](https://agentmods.dev/badge/skills/gauss314/skills/byma/github.svg)](https://agentmods.dev/skills/gauss314/skills/byma)
Your own site
<a href="https://agentmods.dev/skills/gauss314/skills/byma"><img src="https://agentmods.dev/badge/skills/gauss314/skills/byma/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 byma

Your own site · 80×15
<a href="https://agentmods.dev/skills/gauss314/skills/byma"><img src="https://agentmods.dev/badge/skills/gauss314/skills/byma.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,702 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Tool Misuse · line 47
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
  • medium Tool Misuse · line 51
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
How audits are shown
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 $0.00094 $0.04702
Opus 5 $0.00047 $0.02351
Sonnet 5 $0.00019 $0.00940
Haiku 4.5 $0.00009 $0.00470

Measured 9d ago against content hash ca29b65290bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

byma 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/fetch_byma.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/byma/SKILL.md · 389 lines

How it starts

The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BYMA — Bolsas y Mercados Argentinos

Skill para extraer datos de mercado de BYMA via su API publica de market data (open.bymadata.com.ar) — sin API key, sin autenticacion.

BYMA es la bolsa principal de Argentina (sucesora del Merval) donde se negocian:

  • Acciones lideres (panel de 20 simbolos del MERVAL).
  • CEDEARs (~1143 unicos x 2 settlements).
  • Bonos publicos soberanos + LECAPs + BONCAPs (~104 unicos x 6 variantes).
  • Obligaciones Negociables (ON) corporativas (~2117 items).
  • SENEBI ON (segmento bilateral, ~3160 items).
  • Cauciones (133 items, formato DOLAR-DDMM-U-CT-USD).
  • Opciones (~429 items con strike, OI, vencimiento).
  • Indices: S&P MERVAL (M), BURCAP (G).
  • Historicos OHLCV diarios/semanales/mensuales para todos los instrumentos.
  • Ficha tecnica de bonos (forma de amortizacion, intereses step-up, ISIN, ley aplicable, emisor).

  • API publica de BYMA, sin documentacion oficial. Los endpoints pueden cambiar sin aviso.
  • Respetar terminos de uso de BYMA. No hacer mas de 1 req/segundo.
  • Los datos son delayed (~15 min tipico de mercado argentino).
  • Para uso comercial intensivo, contactar BYMA para licencias oficiales.

🔒 Nota sobre certificado SSL

BYMA presenta un certificado SSL cuya CA intermedia no esta incluida en el bundle certifi estandar de Python. Esto causa:

SSLError: CERTIFICATE_VERIFY_FAILED

El script usa verify=False — la conexion sigue siendo TLS-encriptada pero se omite la validacion de cadena. Es el patron estandar de las librerias publicas de BYMA (pyhomebroker, bymadata, etc.).

Si preferis no usar verify=False, podes instalar el cert intermedio de BYMA en tu trust store del sistema.


Scripts

Script Descripcion
fetch_byma.py Script principal: todos los endpoints disponibles

Uso rapido

# ── PANELES (POST) ────────────────────────────────────────────────────

# Panel lideres: 20 acciones MERVAL x 2 settlements (40 items)
py scripts/fetch_byma.py panel leading-equity
py scripts/fetch_byma.py panel leading-equity --t0    # solo CI (T+0)
py scripts/fetch_byma.py panel leading-equity --t1    # solo 24hs (T+1)

# Panel CEDEARs (~2000 items, lista directa)
py scripts/fetch_byma.py panel cedears

# Panel bonos publicos (1018 items, paginado a 189 por defecto)
py scripts/fetch_byma.py panel public-bonds
py scripts/fetch_byma.py panel public-bonds --all     # trae los 1018 en una llamada

# Panel ON corporativas (~2117 items, lista directa)
py scripts/fetch_byma.py panel on

# Panel cauciones (~133 items)
py scripts/fetch_byma.py panel cauciones

# Panel SENEBI ON (3160 items, paginado)
py scripts/fetch_byma.py panel senebi-on
py scripts/fetch_byma.py panel senebi-on --all        # trae los 3160 en una llamada

# Panel opciones (~429 items, con strike, OI, vencimiento)
py scripts/fetch_byma.py panel options

# ── HISTORICOS OHLCV (GET) ────────────────────────────────────────────

# Historico de un instrumento — formato simbolo: "TICKER 24HS"
py scripts/fetch_byma.py historico "GGAL 24HS"
py scripts/fetch_byma.py historico "ALUA 24HS"
py scripts/fetch_byma.py historico "AAPL 24HS"        # CEDEAR ARS
py scripts/fetch_byma.py historico "AAPLD 24HS"       # CEDEAR USD
py scripts/fetch_byma.py historico "AL30 24HS"        # Bono ARS
py scripts/fetch_byma.py historico "AL30D 24HS"       # Bono USD
py scripts/fetch_byma.py historico "AL30C 24HS"       # Bono CCL
py scripts/fetch_byma.py historico "GD30 24HS"
py scripts/fetch_byma.py historico "TZX26 24HS"       # BONCAP
py scripts/fetch_byma.py historico "TY30P 24HS"       # BONCAP

# Con rango de fechas (default: ultimos 30 dias)
py scripts/fetch_byma.py historico "GGAL 24HS" --desde 2024-05-15 --hasta 2026-06-05

# Resolutions: D (diario), W (semanal), M (mensual)
py scripts/fetch_byma.py historico "GGAL 24HS" --resolution W
py scripts/fetch_byma.py historico "GGAL 24HS" --resolution M

# ── INDICES ────────────────────────────────────────────────────────────

# Historico del S&P MERVAL
py scripts/fetch_byma.py indice M
py scripts/fetch_byma.py indice M --desde 2025-01-01 --hasta 2026-06-05

# Historico del BURCAP
py scripts/fetch_byma.py indice G

# ── FICHA TECNICA DE BONOS ─────────────────────────────────────────────

# Ficha tecnica completa: forma de amortizacion, intereses, ISIN, ley, emisor
py scripts/fetch_byma.py bond-info AE38            # Bono soberano USD 2038 step-up
py scripts/fetch_byma.py bond-info AL30            # Bono soberano USD 2030 ley local
py scripts/fetch_byma.py bond-info GD30            # Bono soberano USD 2030 ley NY
py scripts/fetch_byma.py bond-info AE38C           # Variante CCL (misma ficha)
py scripts/fetch_byma.py bond-info AE38D           # Variante USD MEP (misma ficha)
py scripts/fetch_byma.py bond-info BPOA7           # BOPREAL Serie 1 A
py scripts/fetch_byma.py bond-info TY30P           # BONCAP
py scripts/fetch_byma.py bond-info TZX26           # BONCAP CER
py scripts/fetch_byma.py bond-info S237Q           # LECAP
py scripts/fetch_byma.py bond-info SBC1C           # ON corporativa

# ── COMBINADO ──────────────────────────────────────────────────────────

# Snapshot de todos los paneles + MERVAL + BURCAP
py scripts/fetch_byma.py all

# ── OUTPUT ─────────────────────────────────────────────────────────────

# Guardar a archivo JSON
py scripts/fetch_byma.py panel leading-equity -o leading.json
py scripts/fetch_byma.py all -o snapshot_byma.json

# Modo silencioso (solo JSON, sin logs)
py scripts/fetch_byma.py panel cauciones -q

Read the full file on GitHub · 389 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.

  1. 9d ago First seen · 389 lines · 94 tokens per session scan A ca29b65290bc

Subscribe to this mod's changes

byma is a skill published in the GitHub repository gauss314/skills (237 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 4,702 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

pier-cloud

This skill should be used when the user needs to consume the Pier Cloud (Lighthouse) API for cloud cost management — including JWT authentication, listing contexts, workspaces, and FinOps data views. Trigger whenever there is a need to integrate, automate, or debug calls to the Pier Cloud platform via Python, Node.js…

fabricioctelles/skills · 72 tokens

finance

Comprehensive Finance API integration skill for real-time and historical financial data analysis, market research, and investment decision-making. Priority use cases: stock price queries, market data analysis, company financial information, portfolio tracking, market news retrieval, stock screening, technical…

jjyaoao/HelloAgents · 79 tokens

money

Revenue advisor — scans the Obsidian vault for work history and active projects, diagnoses the revenue system, and surfaces monetization opportunities the user can't see from inside their own perspective. Make sure to use this skill whenever the user says "/money", "how can I make more money", "review my revenue"…

kriscard/Skills · 103 tokens

bin-lookup-get-{bin}

Returns card metadata for the given 6–8 digit BIN prefix.

bobadilla-tech/requiems-api-skills · 21 tokens

commodities-get-{commodity}

Returns the latest annual average price and up to 10 years of historical data for the requested commodity slug.

bobadilla-tech/requiems-api-skills · 27 tokens

inflation-post-batch

Returns inflation data for up to 50 countries in a single request. Results are in the same order as the input. Countries with no data return found: false instead of failing the whole request. Billing: 1 credit per country (not per HTTP request).

bobadilla-tech/requiems-api-skills · 58 tokens