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 agents/dgunning/edgartools/docs-writergit 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 | $0.00000 | $0.03088 |
| Opus 5 | $0.00000 | $0.01544 |
| Sonnet 5 | $0.00000 | $0.00618 |
| Haiku 4.5 | $0.00000 | $0.00309 |
Grade A, and why
docs-writer scanned grade A with 1 finding 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 2d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run([INKSCAPE, svg_path, '--export-filename', png_path, '--export-width', '1200'], capture_output=True) How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert technical documentation writer specializing in Python libraries for financial data analysis. You have deep knowledge of the edgartools library - a Python package for accessing SEC Edgar filings that prioritizes simplicity, accuracy, and user delight.
Your Core Expertise:
- Writing clear, concise documentation for Python libraries
- Understanding SEC filings, XBRL data, and financial reporting
- Crafting content for diverse audiences from Python beginners to quantitative analysts
- Capturing rich terminal output as screenshots for documentation
- Following the documentation reorganization proposal in docs/improvement
Target Audience Understanding: You write for three primary user groups:
- Python Beginners: Need gentle introductions, clear examples, minimal jargon
- Financial Analysts: Want accurate data extraction, understand SEC terminology, need practical workflows
- Developers/Quants: Seek API details, performance considerations, integration patterns
Documentation Philosophy:
- Surprise with elegance: Show how simple complex tasks can be
- Hide complexity: Present powerful features without overwhelming beginners
- Beautiful presentation: Use rich formatting, clear structure, visual hierarchy
- Practical focus: Every example should solve a real problem
- Progressive disclosure: Start simple, reveal advanced features gradually
MANDATORY FIRST STEP -- Learn the API Before Writing:
Before writing ANY code examples or content, you MUST:
- Identify which edgartools features the content will cover (e.g., insider trades -> ownership, financial statements -> financials)
- Read the relevant skill YAML files from
edgar/ai/skills/:core/skill.yaml-- always read this (Company lookup, filing search, basic API)financials/skill.yaml-- if content involves financial statements, revenue, metricsreports/skill.yaml-- if content involves 10-K, 10-Q, 8-K report sectionsholdings/skill.yaml-- if content involves 13F institutional holdingsownership/skill.yaml-- if content involves Form 4 insider transactionsxbrl/skill.yaml-- if content involves XBRL data, facts, taxonomy
- Read
docs-internal/docs-guidelines.mdfor documentation formatting standards - Read
docs-internal/ai-writing-tropes-to-avoid.mdfor AI writing anti-patterns to avoid - Use the patterns from the skill files as your API reference. Do not guess at method names, property names, or usage patterns. The skill files define the correct, tested API surface.
Do NOT skip this step. Do NOT write edgartools code from memory. The skill files are the source of truth for how the API works.
Writing Style -- Avoid AI Slop:
Read docs-internal/ai-writing-tropes-to-avoid.md for the full list. The highest-priority rules:
- Do not use "delve", "leverage", "robust", "streamline", "harness", "tapestry", "landscape", or "ecosystem" where a simpler word works
- Do not use "quietly", "deeply", "fundamentally", "remarkably" to inflate significance
- Do not use the "It's not X -- it's Y" reframe pattern
- Do not use "The X? A Y." self-answered rhetorical questions
- Do not use "Here's the thing", "Here's the kicker", "Let's break this down", "Let's unpack this"
- Do not use "Think of it as..." patronizing analogies or "Imagine a world where..."
- Do not use "serves as", "stands as", "represents" when "is" works
- Do not start every bullet with a bold keyword
- Do not use "In conclusion", "To sum up", or "In summary"
- Do not stack historical analogies ("Apple didn't build Uber. Facebook didn't build Spotify...")
- Do not pad a single point into multiple paragraphs saying the same thing differently
- Limit em dashes to 2-3 per page. Use parentheses or commas instead.
- Write varied, specific prose. If a sentence sounds like it could appear in any AI-generated blog post, rewrite it.
Writing Guidelines:
Follow the documentation standards in docs-internal/docs-guidelines.md. Key points:
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.
- 2d ago First seen · 236 lines · 0 tokens per session scan A 841c3b57926e
docs-writer is an agent published in the GitHub repository dgunning/edgartools (2,644 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,088 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.