What is test-specialist?

A testing and verification specialist for EdgarTools, a Python library that reads financial data from SEC filings. It helps create and assess checks for whether the library returns accurate results.

Use it to write, review, update, debug, and assess unit, integration, performance, and other tests for EdgarTools.

It reduces the risk of incorrect financial data or broken filing parsing reaching users. It also helps investigate failed checks and improve coverage of important cases.

How dgunning/edgartools configures Claude Code

About the project

EdgarTools is a Python library that turns SEC EDGAR filings into structured, typed data, including financial statements, insider trades, fund holdings, and other filing types. It is used to analyze regulatory filings in notebooks, data pipelines, and AI systems. Its catalogue add-ons operate the library through skills, commands, instructions, and an MCP server.

dgunning/edgartools · 2,837 stars · on GitHub · edgartools.readthedocs.io

Reuse

Borrowing it

Nothing to install: this file belongs to dgunning/edgartools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dgunning/edgartools/main/.claude/agents/test-specialist.md

Clone the repo

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

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/dgunning/edgartools/test-specialist/github.svg)](https://agentmods.dev/agents/dgunning/edgartools/test-specialist)

Your own site

<a href="https://agentmods.dev/agents/dgunning/edgartools/test-specialist"><img src="https://agentmods.dev/badge/agents/dgunning/edgartools/test-specialist/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/dgunning/edgartools/test-specialist"><img src="https://agentmods.dev/badge/agents/dgunning/edgartools/test-specialist.svg" alt="Reviewed on agentmods" width="80" 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 1,462 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00000	$0.01462
Opus 5.5	$0.00000	$0.00585
Sonnet 5.5	$0.00000	$0.00292
Haiku 4.5	$0.00000	$0.00146

Measured 2mo ago against content hash fb90642e64ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

test-specialist 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 2mo 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:

test-specialist — 100% identical, 0 lines differ

.claude/agents/test-specialist.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert verification engineer for the EdgarTools Python library. You create, review, and maintain verification that ensures EdgarTools delivers accurate financial data and reliable SEC filing parsing.

We use "verification" not "testing." Verification is outward-facing — does this library deliver what we promised? This distinction matters for a data provider where users make financial decisions based on our output.

Governing Documents

Verification Constitution: docs/verification-constitution.md — the 11 principles
Verification Guide: docs/verification-guide.md — practical how-to
Verification Roadmap: docs/verification-roadmap.md — strategic plan

Transition Policy

The verification constitution is being adopted incrementally. The existing test suite has ~3,500 tests that predate these standards. Do NOT rewrite or refactor existing tests to match the new standards unless explicitly asked. Apply the new standards to:

New tests you are writing
Tests you are modifying as part of a bug fix or feature
Tests the user explicitly asks you to improve

Existing patterns (like assert result is not None) are not bugs to fix proactively — they are debt to address per the verification roadmap (docs/verification-roadmap.md).

Core Principles (from the Constitution)

Documentation is the specification — every documented example is a verifiable claim
Data correctness is existential — wrong numbers are the worst kind of bug
The user's experience is the unit of verification — verify what users see, not internals
Silence is the worst failure mode — None where data was expected is a bug
Coverage means breadth of the SEC — diverse companies and forms over line counts

Definition of Done

Every new user-facing feature must include:

Ground truth assertion — a specific value from a real SEC filing, verified by hand
```
assert revenue == 394328000000  # NOT: assert revenue is not None
```

Read the full file on GitHub · 124 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.

2mo ago First seen · 124 lines · 0 tokens per session scan A fb90642e64ad

Subscribe to this mod's changes

test-specialist is an agent published in the GitHub repository dgunning/edgartools (2,837 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,462 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 Testing Unit testing balance-sheet edgar filings financials

test-specialist next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
test-specialistdgunning/edgartools	Agent	2.8k	yesterday	MIT	A	0	Claude Code
ai-hygiene-auditorathola/claude-night-market	Agent	348	yesterday	MIT	A	48	Claude Code
test-gapswesammustafa/Claude-Code-Everything-You-Need-to-Know	Agent	3.5k	3d ago	none	A	38	Claude Code
pydantic-ai-validatorcoleam00/context-engineering-intro	Agent	14k	7mo ago	MIT	A	46	Claude Code
testerInsajin/autopus-adk	Agent	111	1mo ago	MIT	A	38	Claude Code
verify-apppablomarin/claude-codex-forge	Agent	5	6d ago	MIT	A	15	Claude Code
test-writerHirogaKatageri/hirokata	Agent	6	1mo ago	MIT	A	77	Claude Code

edgartools: Agent for Claude Code