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 agentmods add instructions/dgunning/edgartools/claude-mdgit clone --depth 1 https://github.com/dgunning/edgartoolsWhat 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 | $0.01291 | $0.01291 |
| Opus 5 | $0.00646 | $0.00646 |
| Sonnet 5 | $0.00258 | $0.00258 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
edgartools CLAUDE.md 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 3d 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-mcp CLAUDE.md — 89% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EdgarTools
Python library for SEC Edgar filings analysis.
Philosophy
- Simple API, complex data: Hide SEC complexity behind intuitive Python objects
- Progressive disclosure: Basic usage is easy; advanced features available when needed
- Read before write: Understand existing patterns before modifying code
Quick Navigation
| Need | Location | Key Classes |
|---|---|---|
| Filing access | edgar/_filings.py |
Filing, Filings |
| Company data | edgar/entity/core.py |
Company, Entity |
| XBRL parsing | edgar/xbrl/xbrl.py |
XBRL |
| Statements | edgar/xbrl/statements.py |
Statement, StatementLineItem |
| Notes & disclosures | edgar/xbrl/notes.py |
Note, Notes |
| Documents | edgar/documents/ |
Document, HTMLParser |
| Reports (10-K/Q/8-K) | edgar/company_reports/ |
TenK, TenQ, EightK, AuditorInfo, SubsidiaryList |
| Reference data | edgar/reference/ |
Tickers, forms |
Entry Points
from edgar import Filing, Filings, Company, find, obj
Company("AAPL")- Get company by ticker or CIKcompany.get_financials()- Financial statements from latest 10-K (recommended)company.get_quarterly_financials()- Financial statements from latest 10-Qfind(form="10-K", ticker="AAPL")- Search filingsfiling.xbrl()- Parse XBRL financialsfiling.obj()- Get typed report object (TenK, TenQ, etc.)
Data Flow
Company → company.get_financials() → Financials → income/balance/cashflow
Filing → filing.obj() → TenK/TenQ → .notes → Notes → Note → .tables/.text/.expands
Filing → filing.obj() → TenK/TenQ/EightK → .reports → Reports
Filing → filing.xbrl() → XBRL → statements
Statement → stmt['line item'] → StatementLineItem → .note → Note (drill-down)
Company → company.get_facts() → EntityFacts → Statement
Filing → filing.document() → Document → extractors
Large Files (>30KB)
When modifying these, read in chunks:
_filings.py(72KB),xbrl/rendering.py(72KB),xbrl/xbrl.py(66KB)entity/entity_facts.py(63KB),xbrl/facts.py(55KB),xbrl/statements.py(46KB)
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.
- 3d ago First seen · 122 lines · 1,291 tokens per session scan A 2186e656fd01
edgartools CLAUDE.md is an instructions file published in the GitHub repository dgunning/edgartools (2,644 stars, last pushed yesterday), licensed MIT. It adds 1,291 tokens to every session, about $0.0065 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 instructions, from other repositories
secedgar-mcp-server AGENTS.md
Instructions for cyanheads/secedgar-mcp-server, covering agent protocol, core rules, what's next?, mcp surface and tools.
financial-reports-mcp-server AGENTS.md
Instructions for financial-reports/financial-reports-mcp-server, covering agents.md, what this repo is, the one rule that matters: src/ is generated, accepted exception: synthetic (non-schema) emitted code and build / test / run.
financial-reports-mcp-server CLAUDE.md
Instructions for financial-reports/financial-reports-mcp-server: Claude Code reads the cross-harness instructions from AGENTS.md. See that file for everything (generated-src/ rule, build/test commands, code style, connect snippets, security).
secedgar-mcp-server CLAUDE.md
Instructions for cyanheads/secedgar-mcp-server, covering agent protocol, core rules, what's next?, mcp surface and tools.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.