Borrowing it
Nothing to install: this file belongs to Rastrian/DiscordMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Rastrian/DiscordMCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/Rastrian/DiscordMCPWrote 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.
[](https://agentmods.dev/instructions/rastrian/discordmcp/claude-md)<a href="https://agentmods.dev/instructions/rastrian/discordmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rastrian/discordmcp/claude-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.
<a href="https://agentmods.dev/instructions/rastrian/discordmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rastrian/discordmcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02198 | $0.02198 |
| Opus 5.5 | $0.00879 | $0.00879 |
| Sonnet 5.5 | $0.00440 | $0.00440 |
| Haiku 4.5 | $0.00220 | $0.00220 |
Grade A, and why
DiscordMCP 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discord MCP Platform — Claude Project Instructions
Project Identity
Project name: discord-mcp-platform
Working description:
A multi-server Discord MCP control plane that allows users to connect their Discord identity, install/configure Discord bots, and manage Discord server automation through MCP-compatible AI clients.
This project is a Discord MCP because it exposes Discord operations as Model Context Protocol tools, resources, and prompts.
The product must use official Discord bot and OAuth2/application flows.
Core Framing
Users do not connect their Discord account so the system can control the account.
Users connect their Discord account so the platform can:
- identify them;
- discover relevant guild context when permitted;
- verify whether they should be allowed to manage a guild;
- connect them to workspaces;
- authorize bot installation/configuration flows;
- audit actions performed through MCP clients.
Actual Discord automation must be executed through authorized Discord bot accounts or official webhooks.
Strict Non-Goals
Do not implement self-bot behavior.
Do not use Discord user tokens.
Do not ask a user to paste their Discord token.
Do not automate a normal Discord user account.
Do not send messages as a personal Discord user.
Do not read user DMs by imitating a user.
Do not use browser automation to control Discord.
Do not bypass Discord permissions, rate limits, OAuth scopes, gateway restrictions, or API limits.
Do not build spam, raid, mass-DM, invite-spam, reaction-spam, or stealth-monitoring tools.
Product Goal
Build a platform where a user can say, through an MCP-capable AI client:
- "Create a support channel in my server."
- "Summarize the last 100 messages in #general."
- "Create a moderation bot for #support."
- "Post this announcement in #updates."
- "Create a private incident thread and invite moderators."
- "Create an automation that answers FAQs and escalates unresolved questions."
- "List users with the Trial Member role."
- "Draft a moderation warning for this message."
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.
- 1mo ago Changed 9518b9423902
- 2mo ago Changed · +11 lines · +185 tokens per session 46ccb872589a
- 2mo ago First seen · 414 lines · 2,013 tokens per session scan A badea6b2945d
DiscordMCP CLAUDE.md is an instructions file published in the GitHub repository Rastrian/DiscordMCP (10 stars, last pushed 5d ago), licensed Apache-2.0. It adds 2,198 tokens to every session, about $0.0088 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.
DiscordMCP CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| DiscordMCP CLAUDE.mdRastrian/DiscordMCP | Instructions file | 10 | 5d ago | Apache-2.0 | A | 2,198 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |