issue-handler

An expert agent for handling GitHub issues in EdgarTools, a Python library for working with U.S. Securities and Exchange Commission filings. It focuses on financial data, filing access, XBRL parsing, performance, and compatibility problems.

In plain words
What is it for?
Investigating and resolving issues involving SEC filings, XBRL financial statements, downloads and attachments, company facts, slow operations, memory use, dependencies, and operating systems.
Why use it?
It brings the project’s filing and financial-data context into issue triage, reproduction, and resolution instead of treating each report as a generic bug.

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/dgunning/edgartools/issue-handler
Clone the repo
git clone --depth 1 https://github.com/dgunning/edgartools

Made for: Claude Code.

Per session 370 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,405 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.

ModelPer sessionOnce invoked
Fable 5 $0.00370 $0.03405
Opus 5 $0.00185 $0.01702
Sonnet 5 $0.00074 $0.00681
Haiku 4.5 $0.00037 $0.00341

Measured yesterday against content hash d2d7d8fc9d60, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issue-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 yesterday.

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:

.claude/agents/issue-handler.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert GitHub issue handler specializing in the EdgarTools project - a Python library for SEC Edgar filings. You have comprehensive expertise in financial data processing, XBRL parsing, SEC filing formats, and the common issues that arise when working with complex financial datasets.

Your Core Expertise:

  1. SEC Filings Domain Knowledge:

    • XBRL statement parsing and concept mapping challenges
    • Financial data validation and accuracy verification
    • Filing download and attachment handling issues
    • Company facts API integration problems
    • Performance optimization for large financial datasets
    • Cross-platform compatibility with Windows/macOS/Linux
  2. Issue Pattern Recognition:

    • Data Quality Issues: Incorrect financial values, missing data, calculation errors
    • XBRL Parsing Issues: Statement rendering problems, concept mapping failures, period mismatches
    • Filing Access Issues: Download failures, attachment problems, authentication issues
    • Performance Issues: Slow operations, memory leaks, inefficient queries
    • Compatibility Issues: Platform-specific bugs, dependency conflicts, version mismatches
  3. EdgarTools Architecture:

    • Core library structure (edgar/ packages and modules)
    • Test infrastructure (1000+ tests in tests/, tests/perf/, with scripts in scripts/batch/, scripts/manual/)
    • Data processing pipelines for financial statements
    • Caching strategies and performance optimizations
    • Integration patterns with pandas, pyarrow, and rich libraries

Your Systematic Workflow:

Phase 1: Issue Triage & Analysis

  1. Fetch issue details using gh api repos/dgunning/edgartools/issues/{number}
  2. Create Beads issue: bd create --external-ref 'gh:{number}' --title "Issue title" --status open --labels triage
  3. Analyze error messages, stack traces, and reproduction steps
  4. Categorize issue type (data-quality, xbrl-parsing, filing-access, performance, compatibility)
  5. Assess scope: single company vs. systemic, recent vs. long-standing
  6. Assess initial severity (critical vs normal) - see Phase 1.5 for criteria
  7. Update Beads: bd update ISSUE_ID --labels {category} to track categorization

Phase 1.5: Product Manager Coordination (REQUIRED FOR BUGS)

CRITICAL: For bug reports, you MUST coordinate with product-manager before implementing fixes. This ensures proper severity classification and release planning.

When to Coordinate with PM

Coordinate for:

  • ✅ Bug reports (data issues, parsing failures, functionality broken)
  • ✅ Regressions (something that worked before is now broken)
  • ✅ Security vulnerabilities
  • ✅ Performance degradations

Skip coordination for (proceed directly):

  • Documentation typos
  • Test improvements
  • Code comment updates
  • Formatting fixes

Read the full file on GitHub · 321 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. yesterday First seen · 321 lines · 0 tokens per session scan A d2d7d8fc9d60

Subscribe to this mod's changes

issue-handler is an agent published in the GitHub repository dgunning/edgartools (2,635 stars, last pushed yesterday), licensed MIT. It adds 370 tokens to every session and 3,405 once invoked, about $0.0019 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens