discord-ops

discord-ops is a skill for Claude Code, Codex from sandraschi/discord-mcp. It costs 0 tokens per session (782 once invoked), scanned A, original, MIT.

A set of operations for managing Discord servers through an agent. Discord is a chat platform organized into servers, channels, members, and roles.

In plain words
What is it for?
Browsing servers and channels, reading or sending messages, managing channels and roles, handling invitations and webhooks, and banning or removing members.
Why use it?
It gives the agent a defined way to inspect servers, post messages, and handle moderation tasks without guessing how Discord is structured.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Browsing servers and channels, reading or sending messages, managing channels and roles, handling invitations and webhooks, and banning or removing members.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sandraschi/discord-mcp/discord-ops
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.

Any agent
npx skills add sandraschi/discord-mcp --skill discord-ops
Clone the repo
git clone --depth 1 https://github.com/sandraschi/discord-mcp

Made for: Claude Code, Codex.

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 discord-ops

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandraschi/discord-mcp/discord-ops/github.svg)](https://agentmods.dev/skills/sandraschi/discord-mcp/discord-ops)
Your own site
<a href="https://agentmods.dev/skills/sandraschi/discord-mcp/discord-ops"><img src="https://agentmods.dev/badge/skills/sandraschi/discord-mcp/discord-ops/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 discord-ops

Your own site · 80×15
<a href="https://agentmods.dev/skills/sandraschi/discord-mcp/discord-ops"><img src="https://agentmods.dev/badge/skills/sandraschi/discord-mcp/discord-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 782 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00782
Opus 5 $0.00000 $0.00391
Sonnet 5 $0.00000 $0.00156
Haiku 4.5 $0.00000 $0.00078

Measured 12d ago against content hash ef4d4394b94c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

discord-ops 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 12d 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.

mcpb/src/discord_mcp/skills/discord-ops/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discord Ops Skill

Overview

Core operations for Discord server management via the discord(operation=...) portmanteau tool. Covers guild browsing, channel management, messaging, moderation, roles, invites, webhooks, and RAG search.

Key Operations

Discovery

  • discord(operation="list_guilds") — All guilds the bot has joined. Start here.
  • discord(operation="list_channels", guild_id="...") — Browse channels in a guild.

Messaging

  • discord(operation="send_message", channel_id="...", content="...") — Post a message. Subject to anti-spam limits (10/min global, 3/min per channel, 5s interval).
  • discord(operation="get_messages", channel_id="...", limit=50) — Recent messages.
  • discord(operation="edit_message", channel_id="...", message_id="...", content="...") — Edit bot messages only.
  • discord(operation="delete_message", channel_id="...", message_id="...") — Delete bot messages.

Moderation

  • discord(operation="ban_member", guild_id="...", user_id="...", reason="...", delete_message_seconds=0) — Ban with optional message purge.
  • discord(operation="unban_member", guild_id="...", user_id="...") — Lift a ban.
  • discord(operation="kick_member", guild_id="...", user_id="...", reason="...") — Kick a member.
  • discord(operation="timeout_member", guild_id="...", user_id="...", duration_minutes=60, reason="...") — Timeout member.
  • discord(operation="list_bans", guild_id="...") — List banned users.
  • discord(operation="get_audit_log", guild_id="...", limit=50) — Fetch audit log.

Channel Management

  • discord(operation="create_channel", guild_id="...", name="...", channel_type=0) — type: 0=text, 2=voice, 5=announcement.
  • discord(operation="delete_channel", channel_id="...") — Permanent delete.
  • discord(operation="export_messages", channel_id="...", limit=50) — Markdown export.

Roles

  • discord(operation="list_roles", guild_id="...") — All roles with colors/positions.
  • discord(operation="create_role", guild_id="...", name="...") — New role.
  • discord(operation="delete_role", guild_id="...", role_id="...") — Delete role.
  • discord(operation="assign_role", guild_id="...", user_id="...", role_id="...") — Assign.
  • discord(operation="remove_role", guild_id="...", user_id="...", role_id="...") — Remove.

Read the full file on GitHub · 57 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. 12d ago First seen · 57 lines · 0 tokens per session scan A ef4d4394b94c

Subscribe to this mod's changes

discord-ops is a skill published in the GitHub repository sandraschi/discord-mcp (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 782 tokens. 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.