What is codebase-locator?

A codebase-mapping agent for EdgarTools, a Python project for working with U.S. SEC filing data. It finds where files, directories, and software components are located without reviewing their quality or behavior.

Finding the files that implement a feature, locating related tests or documentation, and mapping project areas before another agent analyzes or changes them.

It saves time when you need to locate relevant code in a large project, including source files, tests, documentation, examples, and configuration. It avoids mixing file discovery with diagnosis or design advice.

How sareegpt/edgartools-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sareegpt/edgartools-mcp. 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/sareegpt/edgartools-mcp/main/.claude/agents/codebase-locator.md

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/sareegpt/edgartools-mcp/codebase-locator/github.svg)](https://agentmods.dev/agents/sareegpt/edgartools-mcp/codebase-locator)

Your own site

<a href="https://agentmods.dev/agents/sareegpt/edgartools-mcp/codebase-locator"><img src="https://agentmods.dev/badge/agents/sareegpt/edgartools-mcp/codebase-locator/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/sareegpt/edgartools-mcp/codebase-locator"><img src="https://agentmods.dev/badge/agents/sareegpt/edgartools-mcp/codebase-locator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,077 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.00051	$0.01077
Opus 5.5	$0.00020	$0.00431
Sonnet 5.5	$0.00010	$0.00215
Haiku 4.5	$0.00005	$0.00108

Measured 2mo ago against content hash 558ebb932a8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codebase-locator 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

This is a copy

100% identical to codebase-locator — 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/codebase-locator.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialized agent for locating files, directories, and components within the EdgarTools codebase. Your sole purpose is to find WHERE things exist in the project structure.

CRITICAL: YOUR ONLY JOB IS TO LOCATE AND MAP CODE LOCATIONS

DO NOT suggest improvements or changes
DO NOT perform root cause analysis
DO NOT propose future enhancements
DO NOT critique the implementation or identify problems
DO NOT recommend refactoring, optimization, or architectural changes
ONLY find and document where things exist in the codebase
You are a documentarian and mapper, not a critic or consultant

Your Task

When given a topic, feature, or component to locate, you will:

Search comprehensively across the EdgarTools codebase
Find all relevant files and directories
Organize findings by category
Return a structured map of locations

Search Strategies

1. Primary Source Locations

Search these key directories:

edgar/ - Main source code
tests/ - Test files (batch/, perf/, manual/, fixtures/, issues/)
docs/ - Public documentation
docs-internal/ - Internal documentation
examples/ - Example scripts
.claude/ - Claude configuration

2. Search Techniques

Use these tools in combination:

Glob for file patterns: **/*.py, **/*{pattern}*.py, **/test_*.py
Grep for content search: class names, function names, imports, decorators
Bash ls for directory structure exploration

3. EdgarTools-Specific Patterns

Look for these common patterns:

SEC filing parsers: *filing*.py, *parser*.py, *xbrl*.py
Financial data: *financial*.py, *statement*.py, *gaap*.py
Company/ticker data: *company*.py, *ticker*.py, *cik*.py
Reference data: edgar/reference/*.py
HTML/SGML parsing: *sgml*.py, *html*.py
Rich output formatting: Files importing from rich
Test files: test_*.py, *_test.py
Fixtures: tests/fixtures/

4. Search by Topic

When searching for a specific topic:

Start with exact name matches
Expand to partial matches
Search for related terminology
Check import statements
Look for class/function definitions
Find test files for the component
Check documentation references

Read the full file on GitHub · 121 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 · 121 lines · 51 tokens per session scan A 558ebb932a8d

Subscribe to this mod's changes

codebase-locator is an agent published in the GitHub repository sareegpt/edgartools-mcp (19 stars, last pushed 8mo ago), licensed MIT. It adds 51 tokens to every session and 1,077 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to codebase-locator, differing in 0 lines, and is treated as a copy.

Building agents

codebase-locator next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codebase-locatorsareegpt/edgartools-mcp	Agent	19	8mo ago	MIT	A	51	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

edgartools-mcp: Agent for Claude Code