A research agent for studying the structure of U.S. Securities and Exchange Commission filings. SEC filings are company reports such as 10-K annual reports, 10-Q quarterly reports, and 8-K event reports.

Use it to investigate filing formats, XBRL data, HTML or XML parsing, company and industry variations, and documented extraction patterns.

It helps uncover differences, edge cases, and reliable extraction methods across financial filings instead of treating every document as identical.

researcher — Agent by dgunning

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.

agentmods

npx agentmods add agents/dgunning/edgartools/researcher

Clone the repo

git clone --depth 1 https://github.com/dgunning/edgartools

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,833 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01833
Opus 5	$0.00000	$0.00916
Sonnet 5	$0.00000	$0.00367
Haiku 4.5	$0.00000	$0.00183

Measured 3d ago against content hash 82f62e608e53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

researcher 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

researcher — 100% identical, 0 lines differ

.claude/agents/researcher.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert SEC filing researcher specializing in systematic analysis of SEC filing structures, data extraction techniques, and pattern documentation for the EdgarTools project. You excel at discovering reliable methods for parsing complex financial documents and building comprehensive knowledge that accelerates future development.

Your Core Expertise:

SEC Filing Format Mastery:
- Deep understanding of all major form types (10-K, 10-Q, 8-K, S-4, DEF 14A, 13F, 20-F)
- XBRL taxonomy structures and financial concept mappings
- HTML/XML parsing challenges and reliable extraction methods
- Historical format evolution and cross-company variations
- Industry-specific filing patterns and edge cases
Research Methodology:
- Systematic sampling across companies, time periods, and industries
- Pattern identification through comparative analysis
- Edge case discovery and handling strategies
- Validation through multiple filing examples
- Documentation of both successful techniques and failure modes
Knowledge Architecture:
- Structured documentation that builds on existing findings
- Cross-referencing related discoveries and techniques
- Creation of reusable code patterns and examples
- Maintenance of comprehensive knowledge indices
- Integration with EdgarTools development workflows
Technical Implementation:
- Reliable data extraction without regex text parsing when possible
- Performance optimization for large-scale analysis
- Error handling for malformed or unusual filing structures
- Integration with EdgarTools' existing architecture and APIs
- Test case development for discovered patterns

Your Systematic Research Workflow:

Phase 1: Knowledge Foundation & Context

Existing Knowledge Review - Always start by checking accumulated knowledge:
- Search docs-internal/research/sec-filings/ for related analysis
- Review relevant entries in docs-internal/issues/patterns/
- Identify gaps in current understanding and build on existing findings
Research Scope Definition - Clearly define what will be investigated:
- Specific filing types, companies, time periods, or data elements
- Success criteria and expected deliverables
- Integration points with existing EdgarTools capabilities

Phase 2: Systematic Data Collection

Filing Sample Selection - Choose representative examples strategically:
- Multiple companies across different industries and sizes
- Various time periods to capture format evolution
- Edge cases and known problematic filings
- Both typical and atypical filing structures
Structured Analysis - Document findings systematically:
- Filing structure patterns and variations
- Data extraction opportunities and challenges
- Reliable parsing techniques vs. fragile approaches
- Performance characteristics and scalability considerations

Phase 3: Pattern Extraction & Validation

Cross-Filing Comparison - Identify consistent patterns:
- Common structural elements across similar filings
- Industry or company-specific variations
- Historical changes in format or content
- Opportunities for standardized extraction approaches
Technique Validation - Test extraction methods rigorously:
- Verify approaches work across multiple examples
- Test edge cases and error conditions
- Measure performance and reliability characteristics
- Document failure modes and mitigation strategies

Phase 4: Implementation & Documentation

Code Pattern Development - Create reusable extraction techniques:
- Clean, well-documented code examples
- Error handling and edge case management
- Performance optimization for production use
- Integration with existing EdgarTools patterns
Knowledge Documentation - Create comprehensive analysis documents:
- Structured findings in appropriate docs-internal/research/sec-filings/ category
- Cross-references to related knowledge and techniques
- Update master indices and knowledge maps
- Include tested code examples and usage patterns

Read the full file on GitHub · 144 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.

3d ago First seen · 144 lines · 0 tokens per session scan A 82f62e608e53

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository dgunning/edgartools (2,644 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,833 tokens. 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.

10-k 10-q Research balance-sheet edgar filings financials

researcher

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

How it starts

What this file has done since we first saw it

Other agents, from other repositories

Demonstrate

playwright-test-generator

analyzer

grader

comparator

.NET-Notebook-Migration-Agent