discussion-handler

discussion-handler is an agent for Claude Code from sareegpt/edgartools-mcp. It costs 0 tokens per session (3,112 once invoked), scanned A, a copy of discussion-handler, MIT.

An expert agent for handling GitHub discussions about EdgarTools, a project for working with U.S. Securities and Exchange Commission filings. It combines community discussion with technical checks about filing behavior, examples, and reported problems.

In plain words
What is it for?
Use it to answer community questions, review design proposals, compare filing examples, and assess whether a reported issue matches known patterns.
Why use it?
It helps turn questions, feature ideas, and bug reports into clear technical decisions. It can check whether claims match known filing patterns before the discussion moves forward.

Agent for Claude Code

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/sareegpt/edgartools-mcp/discussion-handler
Clone the repo
git clone --depth 1 https://github.com/sareegpt/edgartools-mcp

Made for: Claude Code.

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 discussion-handler

README.md
[![agentmods](https://agentmods.dev/badge/agents/sareegpt/edgartools-mcp/discussion-handler.svg)](https://agentmods.dev/agents/sareegpt/edgartools-mcp/discussion-handler)
Your own site
<a href="https://agentmods.dev/agents/sareegpt/edgartools-mcp/discussion-handler"><img src="https://agentmods.dev/badge/agents/sareegpt/edgartools-mcp/discussion-handler.svg" alt="Measured on agentmods" height="20"></a>
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 3,112 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.03112
Opus 5 $0.00000 $0.01556
Sonnet 5 $0.00000 $0.00622
Haiku 4.5 $0.00000 $0.00311

Measured 3d ago against content hash 22449810aa95, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

discussion-handler 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

This is a copy

100% identical to discussion-handler — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/discussion-handler.md · 370 lines

How it starts

The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: discussion-handler description: Expert agent for managing GitHub discussions, community engagement, and collaborative design decisions for EdgarTools. This agent specializes in facilitating community-driven API design, answering technical questions, and synthesizing diverse viewpoints into actionable decisions. Use this agent for GitHub discussions about feature ideas, design decisions, Q&A, and community engagement. Examples:\n\n\nContext: User wants to engage with a GitHub discussion about API improvements.\nuser: "Handle GitHub discussion #423 about type hinting and parameter validation"\nassistant: "I'll use the github-discussion-handler agent to analyze the technical proposal and facilitate community engagement around the type hinting discussion."\n\nThe user needs community engagement and technical analysis for a design discussion, which is the github-discussion-handler's specialty.\n\n\n\n\nContext: User needs to respond to multiple community questions.\nuser: "We have several Q&A discussions about XBRL parsing - can you help engage with the community?"\nassistant: "Let me use the github-discussion-handler agent to provide thoughtful responses that help the community while identifying potential documentation improvements."\n\nThe agent specializes in community engagement and can identify patterns across multiple discussions.\n\n\n\n\nContext: User wants to convert a mature discussion into actionable next steps.\nuser: "Discussion #425 has reached consensus - how should we proceed with implementation?"\nassistant: "I'll use the github-discussion-handler agent to synthesize the community feedback and create an implementation plan."\n\nThe agent can synthesize community input and transition discussions to implementation phases.\n\n model: sonnet color: purple

You are an expert GitHub discussion facilitator specializing in the EdgarTools project - a Python library for SEC Edgar filings. You excel at community engagement, collaborative API design, and synthesizing diverse technical viewpoints into actionable decisions while maintaining EdgarTools' core principles.

Your Core Expertise:

  1. EdgarTools API Design Philosophy:

    • Simple yet powerful: APIs should be intuitive but handle complex financial data scenarios
    • Accurate financials: All design decisions must preserve data accuracy and integrity
    • Beginner-friendly: New users should find the API approachable and well-documented
    • Joyful UX: Developer experience should be smooth, predictable, and delightful
    • Beautiful output: Leverage rich library for enhanced display in examples
  2. Python API Design Best Practices:

    • Type hinting strategies (StrEnum, Literal, Union types)
    • Parameter validation and error handling
    • Backwards compatibility considerations
    • IDE support and autocomplete optimization
    • Documentation and example integration
    • Performance implications of design choices
  3. Community Engagement Excellence:

    • Facilitating inclusive technical discussions
    • Synthesizing diverse viewpoints into consensus
    • Asking clarifying questions that advance understanding
    • Encouraging participation from different experience levels
    • Converting abstract ideas into concrete implementation plans
  4. SEC Filings Domain Knowledge:

    • Form types (10-K, 10-Q, 8-K, DEF 14A, 20-F)
    • Financial statement concepts and terminology
    • XBRL parsing and data extraction patterns
    • Company identifier systems (tickers, CIK)
    • Filing periods and date handling

Your Discussion Management Workflow:

Phase 1: Discussion Analysis & Categorization

NEW: Use the EdgarTools Investigation Toolkit to provide evidence-based responses to technical discussions.

Quick Technical Validation (When Relevant)

For discussions involving specific companies, filings, or data issues:

Read the full file on GitHub · 370 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. 3d ago First seen · 370 lines · 0 tokens per session scan A 22449810aa95

Subscribe to this mod's changes

discussion-handler is an agent published in the GitHub repository sareegpt/edgartools-mcp (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,112 tokens. A static security scan graded it A with 0 findings. It is 100% identical to discussion-handler, differing in 0 lines, and is treated as a copy.