edgartools-sec-data

edgartools-sec-data is a skill for Claude Code, Codex from anthropics/cwc-workshops. It costs 64 tokens per session (1,046 once invoked), scanned A, original, Apache-2.0.

Instructions for using the edgartools Python package to retrieve U.S. Securities and Exchange Commission filings and financial data. SEC filings are official company reports such as 10-K annual reports and 10-Q quarterly reports.

In plain words
What is it for?
Researching company financials, reading 10-K and 10-Q reports, extracting XBRL financial statements, and reviewing SEC filing sections.
Why use it?
It provides a consistent way to find companies, retrieve recent filings, read financial statements, and inspect sections such as risk factors.

Skill for Claude CodeCodex ✓ vendor

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

Good fit Researching company financials, reading 10-K and 10-Q reports, extracting XBRL financial statements, and reviewing SEC filing sections.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anthropics/cwc-workshops/edgartools
About the project

CWC Workshops is a collection of materials from Anthropic-run workshops on building and evaluating AI-assisted coding workflows. The workshops cover model selection, multi-agent systems, managed agents, and product development with coding agents. The catalogue entries are examples and teaching materials from those workflows.

anthropics/cwc-workshops · 2,046 stars · on GitHub

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 anthropics/cwc-workshops --skill edgartools
Clone the repo
git clone --depth 1 https://github.com/anthropics/cwc-workshops

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 edgartools-sec-data

README.md
[![agentmods](https://agentmods.dev/badge/skills/anthropics/cwc-workshops/edgartools.svg)](https://agentmods.dev/skills/anthropics/cwc-workshops/edgartools)
Your own site
<a href="https://agentmods.dev/skills/anthropics/cwc-workshops/edgartools"><img src="https://agentmods.dev/badge/skills/anthropics/cwc-workshops/edgartools.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,046 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 pass 7 Sept 2026
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 $0.00064 $0.01046
Opus 5 $0.00032 $0.00523
Sonnet 5 $0.00013 $0.00209
Haiku 4.5 $0.00006 $0.00105

Measured 8d ago against content hash 4da2fb7e5c45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

edgartools-sec-data 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

research-desk/skills/edgartools/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

edgartools: SEC EDGAR data access

edgartools is the desk's standard way to read SEC data. It is preinstalled in your environment. Work in Python (a script or python -c), not by fetching sec.gov pages by hand.

Always set your identity first

The SEC requires a contact identity on automated requests. Do this before any other call, every session:

from edgar import set_identity
set_identity("Research Desk workshop [email protected]")  # use the EDGAR_IDENTITY value you were given

(Equivalently, the EDGAR_IDENTITY environment variable, exported before running Python.)

Companies and filings

from edgar import Company

company = Company("NVDA")              # by ticker (or CIK)
company.name, company.cik, company.industry

filings = company.get_filings(form="10-K")   # also "10-Q", "8-K", "DEF 14A", ...
latest_10k = filings.latest()                # most recent of that form
latest_10q = company.get_filings(form="10-Q").latest()

latest_10k.form, latest_10k.filing_date, latest_10k.accession_no

Pick whichever of the latest 10-K / 10-Q is more recent when asked for "the most recent filing". Foreign private issuers file 20-F instead of 10-K.

Reading the filing

filing = latest_10k
tenk = filing.obj()        # rich object for 10-K/10-Q: sections, financials

# Sections (10-K item numbers; 10-Q uses Part/Item naming)
risk_factors = tenk["Item 1A"]      # Risk Factors text
mda = tenk["Item 7"]                # Management's Discussion & Analysis
business = tenk["Item 1"]

# Plain text of the whole filing if you need to search it
text = filing.text()

Sections are long — extract what you need rather than pasting whole sections into your reply.

Financial statements (XBRL)

financials = tenk.financials          # also: company.get_financials() for the latest annual figures

income = financials.income_statement()
balance = financials.balance_sheet()
cashflow = financials.cashflow_statement()

These return tabular objects (pandas-friendly). Typical fields: total revenue, gross profit, operating income, net income, cash and equivalents, total debt, inventory, R&D expense. The same statement usually carries the prior period's column — use it for year-over-year comparisons instead of fetching another filing.

Read the full file on GitHub · 96 lines

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 · 96 lines · 64 tokens per session scan A 4da2fb7e5c45

Subscribe to this mod's changes

edgartools-sec-data is a skill published in the GitHub repository anthropics/cwc-workshops (2,046 stars, last pushed 11d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,046 once invoked, about $0.0003 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