l402-kit CLAUDE.md

l402-kit CLAUDE.md is an instructions file for coding agents from ShinyDapps/l402-kit. It costs 1,727 tokens per session, scanned A, original, MIT.

A project instruction file for l402-kit, an open-source middleware project for the L402 payment protocol, plus its VERITY AI agent and deployment services.

In plain words
What is it for?
Use it as session guidance when managing l402-kit code, Cloudflare services, Supabase, Lightning payments, Mintlify documentation, or GitHub deployment work.
Why use it?
It records the project's owner, purpose, infrastructure, credentials location, and deployment commands so an agent can operate the project with its context.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/shinydapps/l402-kit/claude-md
Clone the repo
git clone --depth 1 https://github.com/ShinyDapps/l402-kit
Per session 1,727 This file is loaded in full into every session.
When invoked 1,727 The same file — it is already loaded in full.
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 $0.01727 $0.01727
Opus 5 $0.00864 $0.00864
Sonnet 5 $0.00345 $0.00345
Haiku 4.5 $0.00173 $0.00173

Measured 3d ago against content hash 695505c8134e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

l402-kit 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 3d 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 · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

l402-kit — Project Operations Guide

This file is read by Claude Code at the start of every session. It gives full context to manage this project without re-explaining everything.


Owner

Thiago Yoshiaki[email protected] / [email protected] GitHub: ThiagoDataEngineer | Org: ShinyDapps Lightning: [email protected]


What this project is

l402-kit — open-source L402 protocol middleware. TypeScript, Python, Go, Rust. VERITY — autonomous AI agent built on l402-kit. Lives at https://l402kit.com/api/verity.

All credentials are in memory: ~/.claude/projects/c--Users-thiag-l402-kit/memory/credentials.md


Infrastructure

Service What URL / ID
Cloudflare Workers API + VERITY l402kit-api worker
Cloudflare Pages Landing site wrangler.jsonc
Supabase Database urcqtpklpfyvizcgcsia
Blink Lightning wallet (main) [email protected]
Mintlify Docs docs.l402kit.com
GitHub Code ShinyDapps/l402-kit

Deploy commands

# API Worker (VERITY + all endpoints)
# Token in memory: credentials.md → Cloudflare → API Token (Workers)
$env:CLOUDFLARE_API_TOKEN = "<see credentials.md>"
cd cloudflare
npx wrangler deploy --config wrangler.toml

# Landing site (static)
npx wrangler deploy --config ../wrangler.jsonc

Docs deploy automatically via Mintlify on git push to main.


Active branches

Branch Purpose
main Production
feat/lawn-events LAW-N behavioral events + VERITY (pending merge after Peace validation)

VERITY — autonomous agent

Live: https://l402kit.com/api/verity Treasury: [email protected] Agent ID: agent:shinydapps.verity

11 services (preços dinâmicos — valores base)

Service Endpoint Price Key needed
Search /api/verity/search 500 sats SERPER_API_KEY
Scrape /api/verity/scrape 500 sats FIRECRAWL_API_KEY
BTC Price /api/verity/btc-price 100 sats
Summarize /api/verity/summarize 500 sats ANTHROPIC_API_KEY
Sentiment /api/verity/sentiment 300 sats ANTHROPIC_API_KEY
Domain Intel /api/verity/domain-intel 2,000 sats
Integration /api/verity/integration 200,000 sats ANTHROPIC_API_KEY
World State /api/verity/worldstate 300 sats
Translate /api/verity/translate 500 sats ANTHROPIC_API_KEY
Research /api/verity/research 2,000 sats ANTHROPIC_API_KEY
Alpha /api/verity/alpha 5,000 sats ANTHROPIC_API_KEY + SERPER_API_KEY

Read the full file on GitHub · 186 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. 3d ago First seen · 186 lines · 1,727 tokens per session scan A 695505c8134e

Subscribe to this mod's changes

l402-kit CLAUDE.md is an instructions file published in the GitHub repository ShinyDapps/l402-kit (3 stars, last pushed 3mo ago), licensed MIT. It adds 1,727 tokens to every session, about $0.0086 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.

Related

Other instructions, from other repositories