discord-manager: Instructions file for Claude Code

CLAUDE.md

discord-manager CLAUDE.md is an instructions file for Claude Code from seasonedcc/discord-manager. It costs 4,134 tokens per session, scanned A, original, MIT.

Development instructions for Discord Manager, a self-hosted tool that saves messages from one Discord server and lets an AI assistant search bookmarks, catch-up digests, and triage through MCP. Its data store is append-only, meaning existing records are not edited or deleted; new events record every change.

In plain words
What is it for?
Use it when developing Discord Manager, especially when changing its database tables, queries, migrations, tests, or development workflow.
Why use it?
It gives developers the project’s rules for data storage, commands, and TypeScript work, reducing inconsistent changes and accidental loss of history.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions subagents.

This is seasonedcc/discord-manager's own configuration. It tells Claude Code how to work on discord-manager 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 discord-manager configures →

Reuse

Borrowing it

Nothing to install: this file belongs to seasonedcc/discord-manager. 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/seasonedcc/discord-manager/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/seasonedcc/discord-manager

Made for: Claude Code.

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-manager CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/seasonedcc/discord-manager/claude-md/github.svg)](https://agentmods.dev/instructions/seasonedcc/discord-manager/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/seasonedcc/discord-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/seasonedcc/discord-manager/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.

agentmods 80×15 button for discord-manager CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/seasonedcc/discord-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/seasonedcc/discord-manager/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,134 This file is loaded in full into every session.
When invoked 4,134 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 $0.04134 $0.04134
Opus 5 $0.02067 $0.02067
Sonnet 5 $0.00827 $0.00827
Haiku 4.5 $0.00413 $0.00413

Measured 9d ago against content hash a45e379f7273, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

discord-manager 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 9d 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.

CLAUDE.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discord Manager

Self-hosted Discord bookmarks, catch-up digests, and triage for your AI assistant, over MCP — no Nitro required. The product is headless: a discord.js bot ingests one guild's messages into a local append-only SQLite event store, and an MCP stdio server is the entire user surface. Every deployment is single-owner — one bot token, one owner user id, one guild, one database file. docs/architecture.md is the reference for the whole design.

The append-only doctrine

The application schema is 100% append-only and event-sourced, with zero exceptions: INSERT is the only write, current state is derived from events at query time, and deletion/archival/correction are events too. ALWAYS load the database-design skill before designing tables, writing migrations, or writing any query that changes data. The kysely skill covers the query-side rules (updateTable/deleteFrom/doUpdateSet are banned on application tables).

SQLite forces exactly five sanctioned divergences, and no others:

  • Ids are monotonic UUIDv7 values from newId() in application code — there is no gen_random_uuid(), and a random id would turn the latest-event-wins id desc tie-break into a coin flip whenever two events share a millisecond. Insert helpers own this; migrations declare text primary keys. The guarantee is per process: the daemon and the MCP server each issue ids in their own order, so two processes writing to one reversible pair in the same millisecond stay unordered. That is accepted — see single-writer WAL below — and no ordering machinery exists to fix it.
  • Timestamps are ISO-8601 UTC text columns; createdAt defaults to strftime('%Y-%m-%dT%H:%M:%fZ','now'), so lexicographic order equals chronological order.
  • Latest-event-wins uses row_number() over (partition by parentId order by createdAt desc, id desc) filtered to 1 instead of distinct on. The id desc tie-break stays mandatory.
  • Booleans are integer 0/1 at the schema level; Zod coerces at the boundary.
  • Single-writer WAL replaces Postgres advisory locks: the ingest daemon is the only gateway writer and MCP writes are transactional, so there is no cross-process ordering machinery.

Read the full file on GitHub · 168 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. 9d ago First seen · 168 lines · 4,134 tokens per session scan A a45e379f7273

Subscribe to this mod's changes

discord-manager CLAUDE.md is an instructions file published in the GitHub repository seasonedcc/discord-manager (3 stars, last pushed 1mo ago), licensed MIT. It adds 4,134 tokens to every session, about $0.0207 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens