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.
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.
npx skills add anthropics/cwc-workshops --skill edgartoolsgit clone --depth 1 https://github.com/anthropics/cwc-workshopsWrote 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.
[](https://agentmods.dev/skills/anthropics/cwc-workshops/edgartools)<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>- NVIDIA SkillSpector pass
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 5.1 | $0.00064 | $0.01046 |
| Opus 5 | $0.00032 | $0.00523 |
| Sonnet 5 | $0.00013 | $0.00209 |
| Haiku 4.5 | $0.00006 | $0.00105 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- edgartools-sec-data — 100% identical, 0 lines differ
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.
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.
- 8d ago First seen · 96 lines · 64 tokens per session scan A 4da2fb7e5c45
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.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.