l402-kit AGENTS.md

A navigation and contribution guide for the l402-kit software project. It tells coding agents which project documents to read for orientation, deployment, debugging, security, and code changes.

In plain words
What is it for?
Use it when working on l402-kit to find architecture and operations documentation, understand its Lightning and HTTP payment-related protocols, locate source code and tests, and follow contribution requirements.
Why use it?
Large repositories are difficult to understand safely because important information is spread across many files. This guide points to the right source of information and records project rules that should remain unchanged.

Instructions file for CodexOpenCode

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/agents-md
Clone the repo
git clone --depth 1 https://github.com/ShinyDapps/l402-kit

Made for: Codex, OpenCode.

Per session 1,570 This file is loaded in full into every session.
When invoked 1,570 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01570 $0.01570
Opus 5 $0.00785 $0.00785
Sonnet 5 $0.00314 $0.00314
Haiku 4.5 $0.00157 $0.00157

Measured 2d ago against content hash 01d27f0c9728, 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 AGENTS.md scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `gh` | GitHub CLI (if installed). Not installed by default on this machine — use API + curl |
AGENTS.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — machine-readable navigation

Why this file: anyone driving this repo from an AI agent (Claude Code, Cursor, etc.) reads this first to orient. Structured for grep + cheap context.

Companion: CLAUDE.md (Claude-specific ops), HANDBOOK.md (deep walkthrough), ARCHITECTURE.md (where-is-what).


Entry points by question

If you're trying to... Read this first
Understand the project in 60s README.md
Find where a file lives ARCHITECTURE.md
Operate / deploy / debug CLAUDE.md
Deep walkthrough of every flow HANDBOOK.md
Report or understand security SECURITY.md
Contribute code CONTRIBUTING.md
See live state STATUS.md

File invariants

# This block is meant to be parsed by tools.
project:
  name: l402-kit
  primary_branch: main
  license: MIT
  org: ShinyDapps
  maintainer: ThiagoDataEngineer
  domain: l402kit.com
  docs: docs.l402kit.com

protocols:
  - L402  # HTTP 402 + BOLT11 + macaroon
  - Lightning Network
  - CloudEvents 1.0  # LAW-N events
  - MCP  # Model Context Protocol (npx l402-kit-mcp)

sdks:
  typescript:
    path: src/
    tests: src/__tests__/
    config: package.json
    registry: npmjs.com/package/l402-kit
  python:
    path: python/l402kit/
    tests: python/tests/
    config: python/pyproject.toml
    registry: pypi.org/project/l402kit
  rust:
    path: rust/src/
    tests: rust/tests/
    config: rust/Cargo.toml
    registry: crates.io/crates/l402kit
  go:
    path: go/
    tests: go/*_test.go
    config: go.mod
    registry: pkg.go.dev/github.com/shinydapps/l402-kit/go

server_side:
  api_worker:
    config: cloudflare/wrangler.toml
    code: cloudflare/src/
    deploys_to: l402kit.com/api/*, l402kit.com/admin/*, docs.l402kit.com/*
  landing_worker:
    config: wrangler.jsonc
    code: landing-worker.ts + backend/
    deploys_to: l402kit.com/*

ci_cd:
  ci: .github/workflows/ci.yml  # tests 4 langs in parallel, gitleaks scan
  release: .github/workflows/release.yml  # tag vX.Y.Z triggers 4-way publish
  release_secrets_required: [NPM_TOKEN, PYPI_TOKEN, CARGO_TOKEN]

security:
  pre_commit_guard: .githooks/pre-commit
  ci_secret_scan: gitleaks
  gitleaks_config: .gitleaks.toml
  revoked_secrets:
    - "shdp_dash_mK9pL2xQwRtNvJ4eHcBfUu3YsA7dZiXo"  # revoked 2026-05-19

private_paths:
  - .private/                # strategic docs, drafts, internal research, credentials-local.md
  - ~/.claude/projects/...   # per-machine memory (not in repo)
  - CREDENTIALS.md           # if exists, gitignored; canonical is memory/credentials.md

never_break:
  - cross_lang_parity: "any feature in src/ must port to python/, rust/, go/ before next minor"
  - tdd_first: "test before implementation, in __tests__/"
  - sovereign_mode: "cannot become paid upsell"
  - bitcoin_only: "reject x402/USDC/Solana/Polygon/Rootstock at scoring time"
  - all_secrets_via_env: "no hardcoded tokens, ever"

Read the full file on GitHub · 150 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. 2d ago First seen · 150 lines · 1,570 tokens per session scan A 01d27f0c9728

Subscribe to this mod's changes

l402-kit AGENTS.md is an instructions file published in the GitHub repository ShinyDapps/l402-kit (3 stars, last pushed 3mo ago), licensed MIT. It adds 1,570 tokens to every session, about $0.0078 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 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 · 4,345 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

next.js 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