cursorrules

A server and command-line tool for giving AI agents Nostr identities, where Nostr is a decentralized network for signed messages and social activity. It includes groups of tools for identity, social features, trust, relays, payments, privacy, and other Nostr tasks.

In plain words
What is it for?
Use it to manage Nostr identities, publish or find content, communicate, connect to relays, handle trust and moderation, make payments, and run related workflows. It also supports building, testing, and type-checking the server.
Why use it?
It lets an agent use one shared Nostr implementation through either an MCP connection or a command-line interface. Built-in identity handling, relay connections, validation, caching, and safety controls reduce the need to implement these pieces separately.

Cursor rule for Cursor

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 rules/forgesworn/bray/cursorrules
Clone the repo
git clone --depth 1 https://github.com/forgesworn/bray

Made for: Cursor.

Per session 447 This file is loaded in full into every session.
When invoked 447 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 $0.00447 $0.00447
Opus 5 $0.00224 $0.00224
Sonnet 5 $0.00089 $0.00089
Haiku 4.5 $0.00045 $0.00045

Measured yesterday against content hash cfc3668d3a16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

.cursorrules · 42 lines

What it actually says

nostr-bray

MCP server + CLI giving AI agents sovereign Nostr identities. 238 tools across 27 groups.

Commands

  • npm run build — compile TypeScript
  • npm test — run all tests (vitest, 1400 tests)
  • npm run lint — type-check (tsc --noEmit)

Architecture

Entry points:

  • src/index.ts — MCP server (config → IdentityContext → RelayPool → tools → transport)
  • src/cli.ts — CLI wrapper (same handlers, no MCP)

Each tool group: src/<group>/handlers.ts (logic) + src/<group>/tools.ts (Zod schemas + MCP registration). Groups: identity, social (social/dm/blossom/articles/calendar/badges/communities/groups/wiki/search/scheduled/community-NIPs), trust, relay, zap, safety, signet, vault, util, workflow, dispatch, marketplace, privacy, moderation, handler.

Core modules:

  • src/context.ts — IdentityContext (nsec-tree root, LRU cache, zeroise, signing)
  • src/trust-context.ts — trust signal aggregation (Signet, WoT, Dominion)
  • src/relay-pool.ts — relay connections, SOCKS5h, Tor policy, write queue
  • src/nip65.ts — NIP-65 relay list (signature-verified, TTL cache)
  • src/validation.ts — shared Zod validators (hexId, relayUrl)

Conventions

  • British English (colour, initialise, behaviour)
  • ESM only
  • Commits: type: description (feat:, fix:, test:, docs:)
  • No Co-Authored-By lines
  • Work on branches, merge to main (semantic-release auto-publishes)

Security Rules

  • Never return private keys in tool responses
  • Zeroise Buffers in finally blocks
  • Validate all external input via src/validation.ts
  • Use verifyEvent() before trusting Nostr events from relays
  • Enforce Tor policy on runtime relay additions
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. yesterday First seen · 42 lines · 447 tokens per session scan A cfc3668d3a16

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository forgesworn/bray (1 stars, last pushed 7d ago), licensed MIT. It adds 447 tokens to every session, about $0.0022 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.