tiger-slack CLAUDE.md

tiger-slack CLAUDE.md is an instructions file for coding agents from timescale/tiger-slack. It costs 2,515 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Tiger Slack, an AI-accessible Slack analytics platform that imports workspace messages into TimescaleDB, a database designed for time-based data.

In plain words
What is it for?
It helps develop and operate the Slack ingestion service and MCP server, manage Docker Compose services, and connect to the TimescaleDB database.
Why use it?
It explains the project's architecture and commands, reducing guesswork when starting services, inspecting logs, or accessing the database.

Instructions file

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 instructions/timescale/tiger-slack/claude-md
Clone the repo
git clone --depth 1 https://github.com/timescale/tiger-slack

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 tiger-slack CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/timescale/tiger-slack/claude-md.svg)](https://agentmods.dev/instructions/timescale/tiger-slack/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/timescale/tiger-slack/claude-md"><img src="https://agentmods.dev/badge/instructions/timescale/tiger-slack/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,515 This file is loaded in full into every session.
When invoked 2,515 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 $0.02515 $0.02515
Opus 5 $0.01257 $0.01257
Sonnet 5 $0.00503 $0.00503
Haiku 4.5 $0.00251 $0.00251

Measured 5d ago against content hash 0fdb03def689, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tiger-slack 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 5d 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 · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tiger Slack - AI-Powered Slack Analytics Platform

This project provides AI-accessible Slack workspace analytics through real-time data ingestion, TimescaleDB storage, and MCP (Model Context Protocol) integration for Claude Code.

Architecture Overview

  • ingest/ - Python service for real-time Slack event ingestion and historical data import
  • mcp/ - TypeScript MCP server providing AI-accessible APIs for Slack data analysis
  • TimescaleDB - Time-series database optimized for Slack message storage and analytics
  • Docker Compose - Local development environment with all services

Development Commands

Service Management

docker compose up -d          # Start all services (TimescaleDB, ingest, MCP server)
docker compose down           # Stop all services  
docker compose logs -f        # View service logs
docker compose restart        # Restart all services
docker compose down -v && docker compose up -d  # Reset with fresh volumes
docker compose down -v --remove-orphans && docker system prune -f --volumes && docker compose up -d --build  # Complete rebuild (destroys all data)

Database Access

psql -d "postgres://tsdbadmin:password@localhost:5432/tsdb"  # Connect to TimescaleDB via psql

MCP Integration Setup

# Add Logfire MCP to Claude Code (requires LOGFIRE_READ_TOKEN in .env)
claude mcp add -s project logfire -e LOGFIRE_READ_TOKEN="your-token-here" -- uvx logfire-mcp@latest

# Add Tiger Slack MCP to Claude Code
claude mcp add -s project --transport http tiger-slack http://localhost:3001/mcp

Service-Specific Commands

Ingest Service (ingest/)

cd ingest/
just deps                    # Install/sync dependencies
just run                     # Run ingest service locally
just migrate                 # Run database migrations
just jobs                    # Run scheduled sync jobs manually
just import /path/to/export  # Import Slack workspace export
just lint && just format && just typecheck  # Code quality checks
just build-image             # Build Docker image

Read the full file on GitHub · 306 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. 5d ago First seen · 306 lines · 2,515 tokens per session scan A 0fdb03def689

Subscribe to this mod's changes

tiger-slack CLAUDE.md is an instructions file published in the GitHub repository timescale/tiger-slack (49 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,515 tokens to every session, about $0.0126 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.