agentmods.dev

class-action-finder: Instructions file for Claude Code

CLAUDE.md

class-action-finder CLAUDE.md is an instructions file for Claude Code, Codex from yingying-chu/class-action-finder. It costs 2,942 tokens per session, scanned A, original, MIT.

Repository instructions for a tool that finds possible class-action settlement claims. A class action is a legal case where one settlement can cover many people; the instructions describe checking email notices, matching purchases with public settlement information, and keeping a record of claims and payments.

In plain words
What is it for?
Use it to scan connected email for settlement notices, compare purchase evidence with open public settlements, create an HTML report, and track what has been filed or paid.
Why use it?
They define how the workflow should separate direct settlement notices from purchase-based matches and avoid treating a receipt as proof of eligibility. They also preserve a record that can be refreshed after corrections.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: reads ~/.codex or $CODEX_HOME, but also the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is yingying-chu/class-action-finder's own configuration. It tells Claude Code and Codex how to work on class-action-finder itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything class-action-finder configures →

not rated 3repo 15d ago A scan 2,942 tokens original MIT
View source ↗ yingying-chu/class-action-finder yingying-chu.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to yingying-chu/class-action-finder. 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/yingying-chu/class-action-finder/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/yingying-chu/class-action-finder

Made for: Claude Code, Codex.

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 class-action-finder CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yingying-chu/class-action-finder/claude-md/github.svg)](https://agentmods.dev/instructions/yingying-chu/class-action-finder/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/yingying-chu/class-action-finder/claude-md"><img src="https://agentmods.dev/badge/instructions/yingying-chu/class-action-finder/claude-md/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.

agentmods 80×15 button for class-action-finder CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yingying-chu/class-action-finder/claude-md"><img src="https://agentmods.dev/badge/instructions/yingying-chu/class-action-finder/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,942 This file is loaded in full into every session.
When invoked 2,942 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02942 $0.02942
Opus 5 $0.01471 $0.01471
Sonnet 5 $0.00588 $0.00588
Haiku 4.5 $0.00294 $0.00294

Measured 9d ago against content hash ed5244aad359, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

class-action-finder CLAUDE.md 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 9d 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.

CLAUDE.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This repo contains a single portable skill for capable AI assistant and agent environments in skills/class-action-finder/. ChatGPT, Claude, and Codex are the currently packaged and tested integrations, not the boundary of the core workflow. Run ./install.sh to install it into Claude's global skills directory (~/.claude/skills/). Use ./install.sh --codex for Codex.

The skill

class-action-finder does three jobs that feed each other, in one SKILL.md:

  • Find notices — scans the user's connected email for direct class action settlement notices and produces a styled HTML report (SKILL.md Part A)
  • Match purchases — extracts minimal, non-sensitive evidence from purchase confirmations and checks public sources for potentially matching open settlements (SKILL.md Part D)
  • Remember — reads and writes a persistent record of what the user has filed and been paid (SKILL.md Part B), and can refresh the current report after a correction without re-scanning email (Part C)

Purchase Match is deliberately separate from direct-notice discovery. It uses a source badge plus a categorical eligibility match, never treats a receipt as proof of class membership, never sends personal receipt details to web search, and does not persist purchase history automatically.

Architecture

Connected mail
    │
    ├── Direct notices                      (SKILL.md Part A)
    │     Search inbox, spam, and promotions
    │     Verify case and score legitimacy
    │     Extract deadlines, payouts, IDs, PINs, and claim URLs
    │
    └── Purchase confirmations              (SKILL.md Part D)
          Extract merchant, product, and purchase date only
          Search verified public settlement sources
          Compare product, class period, and eligibility facts
                  │
                  ▼
        Match settlement identity
                  │
            ┌─────┴─────┐
            ▼           ▼
      Tracker JSON   HTML report
      filed + paid   actions + reviews + alerts
            │           │
            └─ refresh ─┘            (SKILL.md Parts B and C)

Read the full file on GitHub · 142 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. 9d ago First seen · 142 lines · 2,942 tokens per session scan A ed5244aad359

Subscribe to this mod's changes

class-action-finder CLAUDE.md is an instructions file published in the GitHub repository yingying-chu/class-action-finder (3 stars, last pushed 15d ago), licensed MIT. It adds 2,942 tokens to every session, about $0.0147 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 2026-08-31.

Legal and complianceResearchclass-actionclass-action-lawsuitclass-actionsclassactionslegal-ai
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens