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.
npx agentmods add instructions/wdwdev/discord-archive/claude-mdgit clone --depth 1 https://github.com/wdwdev/discord-archiveWrote 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/wdwdev/discord-archive/claude-md)<a href="https://agentmods.dev/instructions/wdwdev/discord-archive/claude-md"><img src="https://agentmods.dev/badge/instructions/wdwdev/discord-archive/claude-md.svg" alt="Measured on agentmods" 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 | $0.01643 | $0.01643 |
| Opus 5 | $0.00822 | $0.00822 |
| Sonnet 5 | $0.00329 | $0.00329 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
discord-archive 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 4d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Discord Archive is a four-stage pipeline: Ingest (Discord API → PostgreSQL) → Chunk (messages → semantic chunks) → Embed (NV-Embed-v2 → LanceDB vectors) → Visualize (3D galaxy via FastAPI + React Three Fiber). An MCP server exposes retrieval tools (semantic search, SQL, attachment URL refresh) to Claude Code via stdio transport.
Commands
Setup & Install
uv sync # Core only (ingest)
uv sync --extra rag # + RAG pipeline & MCP server
uv sync --extra galaxy # + 3D visualizer (includes rag)
uv sync --extra test # + test dependencies
Run Pipeline Stages
discord-archive ingest --config config.toml # Discord API → PostgreSQL
discord-archive chunk --config config.toml # Messages → semantic chunks
discord-archive embed --config config.toml # Chunks → NV-Embed-v2 vectors
discord-archive graph --config config.toml # Messages → user interaction graph
discord-archive project --config config.toml # Embeddings → 3D (PCA + UMAP)
discord-archive serve --host 0.0.0.0 --port 8000 # Galaxy web server
Common flags for ingest/chunk/embed/graph: --guild-id INT, --channel-id INT, -v (debug), --show-sql, --log-file PATH. graph also takes --rebuild (recount from scratch; needed after backfilling older history).
Database
docker compose up -d # Start PostgreSQL 18 (port 5432)
Credentials in .env (see .env.example). Config in config.toml (see config.example.toml).
Migrations (Alembic)
uv run alembic upgrade head # Apply pending migrations
uv run alembic revision --autogenerate -m "message" # Generate migration after model changes
uv run alembic check # Verify models match the database
Schema changes require a migration: edit the ORM model, then autogenerate and review the revision (alembic/versions/). Pipeline commands auto-upgrade to head on startup (BaseOrchestrator.init_db); a pre-Alembic database is stamped with the baseline revision automatically (db/migrate.py). The DB URL comes from config.toml (override with ALEMBIC_DATABASE_URL).
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.
- 4d ago First seen · 96 lines · 1,643 tokens per session scan A f978330813f3
discord-archive CLAUDE.md is an instructions file published in the GitHub repository wdwdev/discord-archive (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,643 tokens to every session, about $0.0082 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.
Other instructions, from other repositories
plexmcp AGENTS.md
AGENTS.md instructions for sandraschi/plexmcp, covering plexmcp — agent context, project overview, key commands, lint and test.
discord-mcp AGENTS.md
Instructions for sandraschi/discord-mcp, covering discord-mcp — agent guide, standards, key files and quick ref.
discord-mcp CLAUDE.md
Instructions for sandraschi/discord-mcp, covering discord-mcp — claude code guide, standards and key files.
memory-lancedb-mcp CLAUDE.md
Claude Code instructions for cablate/memory-lancedb-mcp, covering claude.md, project principles, git workflow, development commands and architecture.
mscodebase-intelligence AGENTS.md
Instructions for ManSio/mscodebase-intelligence, covering 0. first step in any session, 0.1. mcp tool call protocol (mandatory), формат вызова: json raw input (zed mcp), 0.2. mcp-first mode (mandatory when mcp online) and замена ide-инструментов на mcp.
plexmcp CLAUDE.md
Claude Code instructions for sandraschi/plexmcp, covering plexmcp — claude code guide, entry points, standards and key files.