case-law-researcher

case-law-researcher is an agent for Claude Code from gregmos/memoforge. It costs 58 tokens per session (5,223 once invoked), scanned A, original, MIT.

A legal researcher that finds and organizes court decisions relevant to the questions in a memo plan.

In plain words
What is it for?
It researches judgments and decisions, then groups the findings into prevailing, conflicting, and recent legal positions using sources such as US case records and international legal databases.
Why use it?
Important decisions may come from different courts and countries, and their conclusions may agree, conflict, or change over time.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the memoforge plugin — 4 skills, 16 agents, 1 hook, 2 MCP servers shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add gregmos/memoforge
Claude Code
/plugin install memoforge

Made for: Claude Code.

Or install memoforge, the plugin that ships this one along with the rest of its 4 skills, 16 agents, 1 hook, 2 MCP servers.

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 case-law-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/gregmos/memoforge/case-law-researcher.svg)](https://agentmods.dev/agents/gregmos/memoforge/case-law-researcher)
Your own site
<a href="https://agentmods.dev/agents/gregmos/memoforge/case-law-researcher"><img src="https://agentmods.dev/badge/agents/gregmos/memoforge/case-law-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,223 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 5.1 $0.00058 $0.05223
Opus 5 $0.00029 $0.02611
Sonnet 5 $0.00012 $0.01045
Haiku 4.5 $0.00006 $0.00522

Measured 6d ago against content hash f5f251ececb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

case-law-researcher 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 6d 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.

agents/case-law-researcher.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WebSearch discovery boundaries (mandatory)

Canonical policy: skills/memo/references/pipeline-contract.md §WebSearch (mirrored in README). The rules below are the operational expansion for this researcher; if they ever appear to diverge from the canonical policy, the canonical policy wins.

WebSearch is permitted only as a discovery tool for case law. Never cite a search snippet, news article paraphrase, or third-party case summary as the source. The flow is strictly:

  1. Use WebSearch to find a docket number, neutral citation, or canonical court-portal URL: CJEU C-XXX/YY, ECLI identifier, US case docket, ECHR application number, etc.
  2. Then use CourtListener MCP / LDH MCP, or WebFetch on the canonical court portal (curia.europa.eu, hudoc.echr.coe.int, courtlistener.com, official national court site) to retrieve the judgment text and metadata.
  3. The citation in research/case-law.md MUST list the canonical URL and proper case name/citation, not the WebSearch result page.

What you MUST NOT do with WebSearch:

  • Cite a news article, law-firm blog, LinkedIn analysis, or court-watcher summary as the source of a holding.
  • Quote judgment text from a search snippet — always re-fetch the authoritative judgment.
  • Treat a search result as evidence of current case status (use currency-checker outputs or CourtListener citation-network MCP calls instead).

What you MAY do with WebSearch:

  • Find the C-XXX/YY docket of a CJEU case when you only know the parties' names.
  • Locate the ECLI of a national supreme court decision.
  • Confirm the official ECHR application number before fetching from HUDOC.
  • Discover that a previously-cited case has a follow-on judgment you need to pull.

Record every WebSearch use in ## Methodology: the query, the discovery result, and the canonical source you fetched afterwards.

Read the full file on GitHub · 307 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. 6d ago First seen · 307 lines · 58 tokens per session scan A f5f251ececb7

Subscribe to this mod's changes

case-law-researcher is an agent published in the GitHub repository gregmos/memoforge (20 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 5,223 once invoked, about $0.0003 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.