402-mcp: Instructions file for Codex

AGENTS.md

402-mcp AGENTS.md is an instructions file for Codex, OpenCode from forgesworn/402-mcp. It costs 2,277 tokens per session, scanned A, original, MIT.

Project instructions for AI coding agents working on the 402-mcp codebase. AGENTS.md is a file that tells coding tools how a project is built, tested, structured, and written.

In plain words
What is it for?
It helps agents build the project, run Vitest tests, check TypeScript types, follow its file structure and coding conventions, and apply its security patterns.
Why use it?
It gives an agent the project rules and commands it needs to make changes that fit the existing codebase.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is forgesworn/402-mcp's own configuration. It tells Codex and OpenCode how to work on 402-mcp 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 402-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to forgesworn/402-mcp. 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/forgesworn/402-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/forgesworn/402-mcp

Made for: Codex, OpenCode.

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 402-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/forgesworn/402-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/forgesworn/402-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/forgesworn/402-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/forgesworn/402-mcp/agents-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 402-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/forgesworn/402-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/forgesworn/402-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,277 This file is loaded in full into every session.
When invoked 2,277 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 $0.02277 $0.02277
Opus 5.5 $0.00911 $0.00911
Sonnet 5.5 $0.00455 $0.00455
Haiku 4.5 $0.00228 $0.00228

Measured 18d ago against content hash 024a73eec790, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

402-mcp AGENTS.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 18d 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.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - 402-mcp

L402 client MCP: AI agents discover, pay for, and consume Lightning and ecash payment-gated APIs within human-set limits. x402 support is experimental and uses a custom format, not the x402 specification.

Commands

npm run build       # tsc -> build/
npm test            # vitest run
npm run typecheck   # tsc --noEmit
npm run lint        # eslint src/

Running

# Stdio transport (default - used by MCP clients like Claude Desktop)
node build/index.js

# HTTP transport (needs a bearer token file; stateless, one server per request)
TRANSPORT=http HTTP_AUTH_TOKEN_FILE=~/.402-mcp/http.token PORT=3402 node build/index.js

Key environment variables:

Variable Default Purpose
NWC_URI_FILE - Absolute path to a private 0600 file containing the NWC bearer URI
CASHU_TOKENS - Path to Cashu token store file (must be within home dir)
LNURLCASH_NOTES - Path to LNURLcash (LUD-25) bearer note store file (must be within home dir)
MAX_AUTO_PAY_SATS 1000 Auto-pay threshold per request (0 disables auto-pay)
MAX_SPEND_PER_MINUTE_SATS 10000 Rolling 60s spend cap (0 blocks auto-pay)
MAX_SPEND_PER_DAY_SATS 5000 Rolling 24h spend cap, persisted in ~/.402-mcp/spend-ledger.json (0 blocks auto-pay)
CREDENTIAL_STORE ~/.402-mcp/credentials.json Path to credential store (must be within home dir)
TRANSPORT stdio stdio or http
PORT 3402 HTTP transport listen port
BIND_ADDRESS 127.0.0.1 HTTP transport bind address
HTTP_AUTH_TOKEN_FILE - Private 0600 bearer token file; required for TRANSPORT=http
HTTP_ALLOWED_HOSTS - Extra Host header values for DNS rebinding protection
CORS_ORIGIN false CORS origin for HTTP transport (* or specific origin)
TRANSPORT_PREFERENCE onion,hns,https,http Preferred transport order for multi-URL services (comma-separated)
TOR_PROXY - SOCKS5 proxy for .onion requests only (e.g. socks5h://127.0.0.1:9050)
SOCKS_PROXY - SOCKS5 proxy for every paid-API request. Set this or TOR_PROXY, not both
HNS_GATEWAY_URL https://query.hdns.io/ DNS-over-HTTPS resolver for Handshake names
HUMAN_PAY_TIMEOUT_S 600 Timeout for human wallet QR payment (seconds)
HUMAN_PAY_POLL_S 3 Poll interval for human wallet payment (seconds)
FETCH_TIMEOUT_MS 30000 Outbound HTTP request timeout
FETCH_MAX_RETRIES 2 Max retries for non-mutating requests
FETCH_MAX_RESPONSE_BYTES 10485760 Max response body size (10 MiB)
SSRF_ALLOW_PRIVATE false Allow requests to private IPs (local dev only)
ALLOW_INSECURE_TLS false Acknowledge risk when NODE_TLS_REJECT_UNAUTHORIZED=0; without it (or SSRF_ALLOW_PRIVATE=true) startup fails

Read the full file on GitHub · 118 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. 18d ago Changed · +24 lines · +880 tokens per session 024a73eec790
  2. 1mo ago Changed · +69 lines · +1,162 tokens per session 761b0529cbb1
  3. 2mo ago First seen · 25 lines · 235 tokens per session scan A f6486665acf9

Subscribe to this mod's changes

402-mcp AGENTS.md is an instructions file published in the GitHub repository forgesworn/402-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 2,277 tokens to every session, about $0.0091 per session on Opus 5.5. 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

402-mcp AGENTS.md compared with instructions from other repositories

402-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
402-mcp AGENTS.mdforgesworn/402-mcpInstructions file05d agoMITA2,277Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode