Courtlistener ApiSAFE
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库,覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文,并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
Overview
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库,覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文,并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
e1ba289846fdOBSERVED · 2026-10-08Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| openclaw | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: courtlistener-api
description: "Legal case law database with PACER data and judge profiles"
metadata:
openclaw:
emoji: "🔍"
category: "domains"
subcategory: "law"
keywords: ["law", "case law", "legal theory", "compliance analysis", "jurisprudence"]
source: "https://www.courtlistener.com/api/rest-info/"
---
# CourtListener API Guide
## Overview
CourtListener is a free legal research platform operated by Free Law Project, a non-profit organization dedicated to making legal data freely accessible. The platform hosts one of the largest open collections of U.S. case law, containing millions of court opinions, docket entries, oral arguments, and judge profiles sourced from PACER (Public Access to Court Electronic Records), state court websites, and historical digitization efforts.
The CourtListener REST API provides programmatic access to this extensive legal database, enabling searches across court opinions, dockets, judge biographical data, and court information. The API covers federal courts (Supreme Court, Circuit Courts, District Courts, Bankruptcy Courts) and many state courts, with records spanning from the founding of the republic to the present day.
Legal scholars, law students, practicing attorneys, journalists, policy researchers, and civic technologists use the CourtListener API to conduct legal research, perform empirical legal studies, build litigation analytics tools, track judicial behavior, monitor active litigation, and analyze trends in case law. It serves as a critical resource for computational legal studies and access-to-justice initiatives.
## Authentication
No authentication is required for basic API access. The CourtListener API is publicly accessible for read operations. However, creating an account and using an API token provides higher rate limits and access to additional features. Authentication is recommended for production applications.
To obtain an API token:
1. Create a free account at https://www.courtlistener.com/
2. Navigate to your profile settings
3. Generate an API token
4. Include it in the `Authorization` header
```bash
# Unauthenticated request
curl "https://www.courtlistener.com/api/rest/v4/opinions/?q=first+amendment"
# Authenticated request (higher rate limits)
curl -H "Authorization: Token YOUR_TOKEN" \
"https://www.courtlistener.com/api/rest/v4/opinions/?q=first+amendment"
```
## Core Endpoints
### opinions: Search Court Opinions
Search and retrieve the full text of court opinions (judicial decisions) across all indexed courts.
- **URL**: `GET https://www.courtlistener.com/api/rest/v4/opinions/`
- **Parameters**:
| Parameter | Type | Required | Description |
|----------------|--------|----------|------------------------------------------------------|
| q | string | No | Full-text search query |
| court | string | No | Court identifier (e.g., `scotus`, `ca9`) |
| date_filed_min | string | No | Minimum filing date (YYYY-MM-DD) |
| date_filed_max | string | No | Maximum filing date (YYYY-MM-DD) |
| type | string | No | Opinion type: `010combined`, `020lead`, etc. |
| ordering | string | No | Sort order: `date_filed`, `-date_filed` |
| page | int | No | Page number for pagination |
- **Example**:
```bash
curl "https://www.courtlistener.com/api/rest/v4/opinions/?q=privacy+fourth+amendment&court=scotus&ordering=-date_filed"
```
- **Response**: Returns paginated results with `count`, `next`, `previous`, and `results` array. Each opinion includes `id`, `absolute_url`, `cluster` (case metadata), `author` (judge), `type`, `date_filed`, `plain_text` or `html` (opinion text), `download_url`, and `citations`.
### dockets: Access Case Dockets
Search and retrieve docket information including case metadata, parties, attorneys, and docket entries from PACER and other sources.
- **URL**: `GET https://www.courtlistener.com/api/rest/v4/dockets/`
- **Parameters**:
| Parameter | Type | Required | Description |
|-----------------|--------|----------|---------------------------------------------------|
| q | string | No | Full-text search query |
| court | string | No | Court identifier |
| date_filed_min | string | No | Minimum filing date |
| date_filed_max | string | No | Maximum filing date |
| case_name | string | No | Filter by case name |
| docket_number | string | No | Filter by docket number |
| ordering | string | No | Sort order field |
- **Example**:
```bash
curl "https://www.courtlistener.com/api/rest/v4/dockets/?q=antitrust&court=scotus&ordering=-date_filed"
```
- **Response**: Returns `count`, `results` array with `id`, `case_name`, `docket_number`, `court`, `date_filed`, `date_terminated`, `nature_of_suit`, `assigned_to` (judge), `referred_to`, and `docket_entries`.
### courts: Court Information
Retrieve information about courts in the CourtListener database, including jurisdiction, location, and identifiers.
- **URL**: `GET https://www.courtlistener.com/api/rest/v4/courts/`
- **Parameters**:
| Parameter | Type | Required | Description |
|--------------|--------|----------|-------------------------------------------------|
| jurisdiction | string | No | Filter by jurisdiction type: `F` (federal), `S` (state) |
- **Example**:
```bash
curl "https://www.courtlistener.com/api/rest/v4/courts/?jurisdiction=F"
```
- **Response**: Returns court objects withTrust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
e1ba289846fdfull audit observations/trust-audit/skill/brycewang-stanford__courtlistener-api.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | e1ba289846fd | SAFE | B | 89 | first audit |
Questions
What does the Courtlistener Api skill do?
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库,覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文,并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
Is Courtlistener Api safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Courtlistener Api access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Courtlistener Api work with?
Its documentation mentions openclaw. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (e1ba289846fd), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.