cursorrules

A set of rules for a Python 3.12+ Discord frontend that connects to the Claude Code command-line tool. It defines the project structure, testing approach, code style, logging, and security requirements; TDD means writing a failing test before the implementation.

In plain words
What is it for?
Use it when developing this Discord-to-Claude Code bridge, especially for adding features, writing tests, validating input, running subprocesses, or reviewing security before a commit.
Why use it?
It keeps the Discord bridge consistent and reduces risks when running commands, handling user input, or changing session and runner code.

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/ebibibi/ebi-agent-chat-relay/cursorrules
Clone the repo
git clone --depth 1 https://github.com/ebibibi/ebi-agent-chat-relay

Made for: Cursor.

Per session 435 This file is loaded in full into every session.
When invoked 435 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 $0.00435 $0.00435
Opus 5 $0.00217 $0.00217
Sonnet 5 $0.00087 $0.00087
Haiku 4.5 $0.00044 $0.00044

Measured 2d ago against content hash 076e634df2b5, 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 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.

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 · 46 lines

What it actually says

discord-claude-code-bridge — Cursor Rules

Discord frontend for Claude Code CLI. Python 3.12+ with discord.py v2.

Architecture

  • CLI spawn approach: claude -p --output-format stream-json as async subprocess
  • Thread = Session: Discord thread maps 1:1 to Claude Code session
  • Cog pattern for modular features
  • Repository pattern for SQLite data access

Code Standards

  • Type hints required on ALL function signatures
  • from __future__ import annotations in EVERY file
  • ruff for linting/formatting (line-length: 100)
  • TDD enforced: Write tests FIRST (RED), implement (GREEN), refactor. No exceptions.
  • pytest with pytest-asyncio (auto mode) for testing
  • Logging via logging.getLogger(__name__), never print()
  • Security audit mandatory before committing changes to runner/Cog code

Security (Non-Negotiable)

  • NEVER use shell=True in subprocess calls
  • ALWAYS use create_subprocess_exec with args as list
  • ALWAYS validate user input (session IDs: ^[a-f0-9\-]+$, skill names: ^[\w-]+$)
  • ALWAYS use -- before user prompt in CLI args
  • Strip secrets from subprocess environment (_STRIPPED_ENV_KEYS)
  • Use contextlib.suppress(discord.HTTPException) for non-critical Discord calls

File Layout

  • claude_discord/cogs/ — Discord Cogs (use _run_helper.run_claude_in_thread())
  • claude_discord/claude/ — CLI runner, stream parser, types
  • claude_discord/database/ — SQLite repository
  • claude_discord/discord_ui/ — Status, chunker, embeds
  • tests/ — pytest suite

Commands

uv run pytest tests/ -v --cov=claude_discord
uv run ruff check claude_discord/
uv run ruff format claude_discord/
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 · 46 lines · 435 tokens per session scan A 076e634df2b5

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository ebibibi/ebi-agent-chat-relay (56 stars, last pushed 3d ago), licensed MIT. It adds 435 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 2026-08-30.